Journal of Geographic Information System, 2022, 14, 1-28

[Link]
ISSN Online: 2151-1969
ISSN Print: 2151-1950

Developments in Land Use and Land Cover

Classification Techniques in Remote Sensing:
A Review

Lucrêncio Silvestre Macarringue1,2*, Édson Luis Bolfe1,3, Paulo Roberto Mendes Pereira1
1
Department of Geography, Institute of Geosciences, State University of Campinas, Campinas, Brazil
2
Department of Research, Instituto Politécnico de Ciências da Terra e Ambiente, Matola, Mozambique
3
Embrapa Agricultura Digital, Brazilian Agricultural Research Corporation, Campinas, Brazil

How to cite this paper: Macarringue, L.S., Abstract

Bolfe, É.L. and Pereira, P.R.M. (2022) De-
velopments in Land Use and Land Cover Studies on land use and land cover changes (LULCC) have been a great con-
Classification Techniques in Remote Sens- cern due to their contribution to the policies formulation and strategic plans
ing: A Review. Journal of Geographic In- in different areas and at different scales. The LULCC when intense and on a
formation System, 14, 1-28.
global scale can be catastrophic if not detected and monitored affecting the key
[Link]
aspects of the ecosystem’s functions. For decades, technological developments
Received: December 23, 2021 and tools of geographic information systems (GIS), remote sensing (RS) and
Accepted: February 14, 2022 machine learning (ML) since data acquisition, processing and results in diffu-
Published: February 17, 2022 sion have been investigated to access landscape conditions and hence, differ-
Copyright © 2022 by author(s) and
ent land use and land cover classification systems have been performed at
Scientific Research Publishing Inc. different levels. Providing coherent guidelines, based on literature review, to
This work is licensed under the Creative examine, evaluate and spread such conditions could be a rich contribution.
Commons Attribution International Therefore, hundreds of relevant studies available in different databases (Science
License (CC BY 4.0).
Direct, Scopus, Google Scholar) demonstrating advances achieved in local, re-
[Link]
gional and global land cover classification products at different spatial, spectral
Open Access
and temporal resolutions over the past decades were selected and investi-
gated. This article aims to show the main tools, data, approaches applied for
analysis, assessment, mapping and monitoring of LULCC and to investigate
some associated challenges and limitations that may influence the performance
of future works, through a progressive perspective. Based on this study, despite
the advances archived in recent decades, issues related to multi-source, mul-
ti-temporal and multi-level analysis, robustness and quality, scalability need to
be further studied as they constitute some of the main challenges for remote
sensing.

Keywords
Big Spatial Data, Cloud Computing, Machine Learning, Remote Sensing

DOI: 10.4236/jgis.2022.141001 Feb. 17, 2022 1 Journal of Geographic Information System

L. S. Macarringue et al.

1. Introduction
The acquisition of information on the terrestrial surface and its resources has
been accelerated since the launch of the first artificial Earth Observation (EO)
satellite by the Earth Observation System (EOS) program in 1972. It is partly due
to the efforts of World Space Agencies (WSA) that in recent years have provided
several images of remote sensors coupled mainly to aircraft and satellites public-
ly available [1] [2] [3] and to technological advances in the computing field with
powerful and efficient processors to manage large volumes of data, as well as ef-
forts to develop robust algorithms for processing such data [2] [4].
The demand for remote sensing data for land use and land cover mapping has
been growing due to the impact of land use and land cover changes for the terre-
strial ecosystems. Through these spatial data it is possible to understand and as-
sess the effects of landscape changes on the environment. Images with high spa-
tial, temporal, radiometric and spectral resolution, allow the mapping of large
areas in a relatively short time [5] [6] [7] [8], reinforced the improvement of
techniques and algorithms, which allowed the automation of the mapping, with
reliable results for reality.
Countries that still adopt traditional approaches to remote sensing data processing
using commercial image processing software on workstation PC-based systems with
proposals to demonstrate how remote sensing data can be used and presentation
of GIS packages (due to technical, educational and institutional constraints), leav-
ing aside deeper studies, such as subsurface modeling based on GIS [9], present
limited performance in their studies, as related to Big Data management [6] [10]
[11], because no matter how powerful the operating systems are, the entire data
analysis process, including pre-processing over large areas involving thousands
of images, is cumulative, slow and tedious, and it can still be expensive as it re-
quires a lot of resources.
However, in countries which have chosen to change their approach challenges
have been overcome. The advance has occurred thanks to the development and
application of powerful Machine Learning Algorithms (MLAs) in cloud compu-
ting environments, such as Google Earth Engine (GEE), which process images
on a planetary scale and at high spatial resolutions [6] [12]. According to Mu-
tanga and Kumar [7], this new approach can be undertaken by researchers of
less developed countries due to the fact that does not need the large processing
powers of the computers.
Thus, files with several petabytes of referenced data sets (climatic, land use
and land cover, digital elevation models) product or not of earth observation sa-
tellite images and airborne sensors may be combined and integrated into a com-
puting environment in the cloud. However, the remote sensing data processing,
regardless of the approach followed, has limitations associated with the size and
quality of training samples, thematic precision, choice of algorithm and the size
of the study area to be considered [13] [14].
Recently, new trends have stood out in data production and processing, dri-

DOI: 10.4236/jgis.2022.141001 2 Journal of Geographic Information System

 L. S. Macarringue et al.

ven mainly by cooperation among space agencies around the world. The coop-
eration has resulted in great availability of data (free access), instruments (soft-
ware), and techniques (algorithms) for processing such data [2] [9] [10], pro-
viding to the remote sensing community new applications and tools to conduct
researches. This article aims to provide and highlight main tools, data, approaches
related to Land Use and Land Cover (LULC) mapping issues and investigate
some challenges might arise for evaluating and monitoring land use/land cover
using remote sensing data and provide a critical perspective about LULC issues
achievements in progress.
The article presents the following topics in sequence: 1) it addresses the process
of acquiring and processing remote sensing data obtained at different scales; 2)
presents the main categories of platforms and software’s that can be used to
process such data; 3) addresses techniques for processing geospatial data for pur-
poses of land use and land cover mapping framing them into different approach-
es (pixel, subpixel, object and hybrid); 4) impacts of the application of machine
learning algorithms for the land use and land cover assessment with time-series,
multi-source and multi-scale data; 5) assessment of the accuracy of the maps; 6)
advances achieved, challenges and future perspectives.

2. Remote Sensing Data Acquisition and Processing

Data are the key element in a research, and remote sensing is configured as one
of the main means of acquiring spatial data [15]. Data acquisition in remote
sensing (RS) involves four essential elements: Electromagnetic Radiation (EMR),
light source, sensor and target and an interaction of the EMR with the targets.
To generate relevant information, it involves the fundamental elements in inte-
raction as shown in Figure 1.
For understanding the process, it’s fundamental to know the EMR, sensor
(egg. Resolutions), targets essential characteristics for RS and its properties which
are well documented in [16] [17] [18]. Figure 2 shows the intensity of sun and
earth, the atmosphere transmittance zones and an electromagnetic spectrum hig-
hlighting the visible light.
According to Zwinkels [16], when light interacts with matter, different phe-
nomena can occur depending upon the interaction of the wavelength (frequen-
cy) of the light with the physical size (resonant frequencies) of the interfering
matter. Figure 3 shows spectral reflectance of different targets of the surface.
Considering all the aspects mentioned above, following the steps of remote
sensing data processing, it is possible to generate a product for specific propose.
A list of sources and providers of free remotely sensed data for coarse, medium
and fine scale is extent (Glovis, NASA Earth Observation, USGS Earth Explorer,
ESA’s Sentinel data, VITO Vision, IPPMUS Terra, and so on), and can be ac-
cessed partially in Table 1. The fine scale assessment data are in general pur-
chased.
Recently, data availability problems have been overcome by policies for free

DOI: 10.4236/jgis.2022.141001 3 Journal of Geographic Information System

L. S. Macarringue et al.

Figure 1. Remote sensing data acquisition and processing. Source: Authors (2021).

Figure 2. Electromagnetic spectrum highlighting the visible light, the sun and earth intensity. Source: Authors (2021).

DOI: 10.4236/jgis.2022.141001 4 Journal of Geographic Information System

 L. S. Macarringue et al.

Table 1. Characteristics of different sensors applied to land cover studies.

Spatial Spectral Temporal

Level/
sensors resolution resolution Frequency Provider/website
scale
(m) (bands) (days)
MODIS 250 - 1000 36 1-2 NASA; [Link]
NOAA;
NOAA-AVHRR 1000 6 1-2 [Link]
Coarse scale
oceanic-and-atmospheric-administration-noaa
assessment
ESA;
ENVISAT 30 - 1200 1 (C) 35 [Link]
onal-eo-missions/envisat
LANDSAT USGS;
30 - 100 4 - 11 16
MSS/TM/ETM+/OLI [Link]
ISRO-NRSC;
IRS LISS-III 23.5 4 5 [Link]
UC00GTD
Medium AIRBUS;
scale SPOT MSS 20 4 26 [Link]
assessment nstellation/spot/
ASTER 15 - 90 14 4 - 16 NASA; [Link]
Sentinel 2 10 - 60 1 - 13 5 - 10 ESA; [Link]
CSA;
RADARSAT 8 - 100 1 (C) 24
[Link]
SATIMAGINGCORP;
IKONOS PAN/MS 1-4 1-4 3-5
[Link]
WorldView 4 [Link]
0.31 - 1.24 1-4 3
PAN/MSS w-4/
SATIMAGINGCORP;
Quickbird PAN/MS 0.6 - 2.8 1-3 1-4
Fine scale [Link]
assessment
ISRO-NRSC;
IRS LISS-IV 5.8 3 5 [Link]
UC00GTD
ESA;
RapidEye 5 5 6 [Link]
missions/current-missions/rapideye

Source: Authors (2021).

distribution of remote sensing data initiated by NASA [1] [8] [19]. However, be-
hind benefits, challenges concerning the management of big data emerged such
as complexity, scalability, robustness and quality [11] [20].
Landsat 7 and 8 satellites may collect up to 1200 images per day, demanding
1200 GB storage space per day [2]. In 2019, the volume of the open data pro-
duced by Landsat-7 and Landsat-8, MODIS (Terra and Aqua) and the first three
Sentinel missions (Sentinel-1, -2 and -3) was about 5 PB [10], not counting sev-
eral other programs and remote sensing products available.

DOI: 10.4236/jgis.2022.141001 5 Journal of Geographic Information System

L. S. Macarringue et al.

Figure 3. Electromagnetic spectrum highlighting the visible light, the sun and earth intensity. Source: Au-
thors (2021).

The big data sets, in addition to exceeding memory, storage, and processing
capacities of ordinary personal computers, impose substantial limits that lead
users to take advantage of a small part of data available for scientific research
and operational applications [10]. In reference to the demand, several platforms,
software, and data processing algorithms have been developed as addressed in
subsequent topics.
Data use applying the correct techniques by qualified professionals is the key
to the maximum benefit of these tools. However, pre-processing and validation
present challenges in remote sensing technology [13] [21]. Several remote sens-
ing data products are available for specific research and do not satisfy users’
needs for the integrated study of a given phenomenon as their resolutions vary
among themselves [22] [23]. For instance, forest fire assessment needs high spa-
tial and temporal resolution, however, a sensor cannot provide high resolution
for both Moderate Resolution Imaging Spectroradiometer (MODIS) data pro-
vide 1-day high temporal resolution, but low spatial resolution. According to
Sajjad and Kumar [22], hyperspectral sensors offer the solution to the impasse,
due to their capacity of reducing the processing time for numerous spectral
bands. Even though, their spatial resolution must be improved to achieve better
results.

Free and Open Source and Proprietary Software

In the scientific field of GIS and remote sensing, we highlight two categories of

DOI: 10.4236/jgis.2022.141001 6 Journal of Geographic Information System

 L. S. Macarringue et al.

data processing programs—free/open source (Free and Open Source—FOSS) and

commercial (Proprietary) Software [24] [25], based on the following criteria: User
platform, Graphical User Interface, support/cost, available tools, effort, com-
pleteness, license, operating system dependency, scalability; maximal control [24]
[26].
Researchers consider the terminologies free (established by the Free Software
Foundation), and open source (established by the Open Source Initiative) as
synonyms [24] [27] [28]. However, the terms differ regarding the restrictions on
modifications and redistribution. According to Anand et al. [29] the only re-
striction on free software is that any redistributed version must be distributed
with the original free use, modification, and distribution terms known as copy
left.
The definition of a free software is not related to its cost, but to the freedom of
reuse, modification or not, and distribution, and to execute some of the freedom,
you must have access to the source code [26] [29] [30]. Thus, the categories are
not antagonistic but rather complementary, since their developers have shared
their findings [24] [26]. It is recommended to use the terms free and open source
software together (FOSS) as they allow: 1) to run for any purpose; 2) study how
the program works and adapt it to needs; 3) redistribute copies; 4) improve the
program and make it available to the benefit of the entire community [26] [27]
[29].
The main purpose of developing proprietary software is making monetary
profit. They are developed by individuals or companies that employ engineers
who work on improving them [31]. As a result, they inhibit users from being
able to make copies of the software and redistribute it, sell the license to others
and/or reverse engineer and infringe copyrights and patents [29] [32]. In addi-
tion, it rarely allows end users to purchase or view the source code and may re-
quire annual license fees. It limits users’ understanding of what the code, and/or
tools are doing [25] [31] [32].
Commercial software’s are available in packages (e.g., ERDAS Imagine) and
each package has its limitations requiring users to access to the complete pack-
age to be able to use all its functions. Table 2 presents a list of the most used free
and proprietary software in geoprocessing.
Commercial and open-source software providers have distinct perspectives on
technical support. The lack of support and documentation for users and specific
training skills with technical profile are some disadvantages of FOSS [30]. Com-
mercial software support is a service for licensed users [25].
Although several countries recommend the use of FOSS in public institutions
[30] [32], cost should not be the main factor in the choice. Aspects such as secu-
rity as well as manageability must be considered, due to institutional needs and
capacities. Free software requires national programs to support their develop-
ment and maintenance, training to adapt it to local needs. Conversely, commer-
cial software requires institutional capacity to provide equipment to run the
programs, continuous training of human resources and renewal of licenses.

DOI: 10.4236/jgis.2022.141001 7 Journal of Geographic Information System

L. S. Macarringue et al.

Table 2. Characteristics of different free and proprietary software applied to land cover studies.

Development
Software/Release Platform/
Developed by Useful for application
year/Reference Language support/
Software License
Research institutes, universities, Analysis scientific and visualization,
C, Shell, Tcl/Tk,
GRASS, 1982 [33] companies, volunteers cartography, modeling and
Python GPL
worldwide simulation
ILWIS, 1985 [34] Universities, companies, (Raster) Analysis MS Visual C GPL
Brazilian National Institute Vector and Raster analysis, Statistical
TerraView, 2001 [35] C++, R GPL
for Space Research (INPE) analysis

Analysis, modeling, scientific C++ (MS Visual C++)

Open Source SAGA, 2001 [36] Universities
visualization LGPL (API), GPL

Universities, companies, Viewing, Editing, Analysis,

QGIS, 2002 [37] C++, Qt4, Python GPL
volunteers worldwide Grass-GUI, SAGA-GUI,

Companies, universities, Viewing, Editing, Analysis (Mobile

gvSIG, 2003 [38] JAVA GPL
government Applications)

Brazilian National Institute Digital Image Processing, spatial

SPRING, 1991 [39] GPL
for Space Research (INPE) analysis, modelling, visualization

Digital analysis and visualization of

IDRISI/TerrSet, 1987 Clark Labs at Clark University,
spatial data, including the remotely C++
[40] Worcester, and Massachusetts.
sensed imagery, in a single package

Hexagon, Leica Geosystems Digital analysis of remotely sensed

ERDAS, 1978 [41] C, C++
Geospatial Imaging data.

Research Systems (now

Processing large multispectral and
ENVI, 1994 [42] called ITT Visual Information IDL
Proprietary hyperspectral remote sensing data
Solutions)
ER Mapper, 1990 [43] Australian software company Digital image analysis. C, C++
PCI Geomatica, 1982 Headquartered in Toronto, Remote sensing, Digital
Python
[44] Canada photogrammetry, and cartography.

Digital analysis and visualization of

Environmental Systems
ArcGIS, 1999 [45] spatial data, including the remotely C++, Python
Research Institute (ESRI)
sensed imagery, in a single package

Source: Adapted from Maurya et al. [24].

3. Remote Sensing Data Processing Techniques for the

Purpose of Land Use and Land Cover (LULC) Mapping
3.1. Mapping Land Use and Land Cover
The terms land use and land cover, although used in associated ways, would ra-
ther be defined in a dissociated way. Land use refers to the way the biophysical
attributes of the land are manipulated and the underlying intention to its mani-
pulation. Land cover refers to the biophysical state of the Earth’s surfaces and
the immediate subsoil [46] [47]. Land use causes changes in land cover, and such

DOI: 10.4236/jgis.2022.141001 8 Journal of Geographic Information System

 L. S. Macarringue et al.

changes when intense and on a global scale affect the key aspects of the terrestri-
al systems functions.
According to Briassoulis [47], and Nedd et al. [48] biophysical factors (cli-
mate, temperature, topography, soil type, surface water, humidity, vegetation, and
fauna) and social (population, technology, socioeconomic, cultural and institu-
tional organization, and political changes) are responsible for such changes and
seen interconnected in a space-time perspective. Gómez et al. [46] highlight that
distinct types of land cover provide specific habitats and determine the energy
and carbon exchange between terrestrial and atmospheric regions. The Know-
ledge and mapping of land use and land cover are essential to plan and manage
natural resources, modeling of environmental variables, and to comprehend the
distribution of habitats [48]. Land cover naturally changes over time, also due to
the influence and result of anthropogenic activities.
According to Gómez et al. [46], Earth Observation (EO) data provide land use
and land cover mapping and monitoring in a consistent and robust manner over
large areas, and results are available by different world space agencies at different
spatial and temporal scales, matching scientific and political information needs.
Geotechnologies have been relevant in the study of land use and land cover as
they have enabled observation, identification, mapping, assessment, and moni-
toring of land cover in spatial, temporal, and thematic scales [46] [49].
Identifying types of land cover provides basic information to generate other
thematic maps, and to establish a baseline for monitoring activities. According
to Rogan and Chen [49] an effective approach to identify changes for a specific
period may maximize exploration in the domains of spatial and spectral resolu-
tions, as using additional data, such as vegetation indexes. On the other hand, 2 sig-
nificant taxon to separate cover from use changes namely: 1) categorical—known
as post-classification comparison, which occurs between a set of thematic cate-
gories of land use and land cover (i.e., urban, forest); and 2) continuous—known
as pre-classification enhancement, where changes occur in the quantity or con-
centration of some attribute of the built or natural landscape that may be meas-
ured continuously.
Most approaches to monitoring land use and land cover have used traditional
image classification algorithms that assume: 1) image data is normally distributed,
2) objects of interest on the surface are larger than the pixel size (H-resolution),
and 3) the pixels are composed of a single type of land cover or land use.
However, some approaches argue that objects of interest on the surface are
smaller than the pixel size (L-resolution), and therefore, they used empirical
models to estimate biophysical, demographic and socioeconomic information
[49] [50].

3.2. Remote Sensing Data Processing Techniques for LULC

Over the years, several studies on land cover have been conducted [3] [23] [51]
[52] by using data from various sensors with different resolutions, techniques,

DOI: 10.4236/jgis.2022.141001 9 Journal of Geographic Information System

L. S. Macarringue et al.

and methods of data processing with the purpose to map and monitor land use
and land cover. The methods may be grouped into supervised/semi-supervised,
and unsupervised classification, and the classifiers grouped into parametric and
non-parametric, rigid and flexible (diffuse), or based on pixel/subpixel and ob-
ject [21] [46].
The parametric such as maximum likelihood, minimum distance and Baye-
sian classifiers are based on probabilistic theories, modeling the decision boun-
daries between classes from a fixed number of parameters, independent of the
number of samples, using global criteria for the classification [53]. Conversely,
the non-parametric, such as support vector machine (SVM), artificial neural
network (ANN), guide the grouping of classes based on the digital number (sin-
gle band/image) or spectral reflectance (multispectral image) and other charac-
teristics such as shape and textural attributes of the scene. The distribution of the
image values are independent and its focusing on the local data structure, requir-
ing a high set of samples for the classification process [54] [55] [56] [57].
According to Phiri and Morgenroth [55], advances in object pattern recogni-
tion techniques through artificial intelligence and machine learning approaches
have contributed significantly to develop advanced non-parametric classifiers,
commonly used in GIS and Digital Image Processing commercial software, as
well as open source.
The pixel approach, such as Random Forest and spectral matching techniques,
is based on the use of the pixel spectral information to find its most likely class,
plotting a probability that a given pixel belongs to a certain class or not, i.e., the
pixels of a class are more similar from a spectral point of view than the pixels
from other classes [55] [58].
The Object-Based Image Analysis (OBIA) approach uses geographic objects as
basic units to classify land use and land cover reducing variations in targets
within the class and it removes the effects of “salt and pepper” that result from
isolated pixels incorrectly classified. It presents the advantage of incorporating
several sources of information, such as texture, shape, and position as a basis for
the classification [54] [55] [58]. Its main limitation is associated with choosing
the appropriate segmentation scale and dealing with different steps, which may
be a source of variation if not treated properly.
The sub-pixel-based approach was developed to address divergences in pix-
el-based classification, such as the separation of land uses and land cover in
mixed pixels [50] [51] [59]. The approach proved to be suitable from medium to
low spatial resolution sensors, and widely used in regional, continental, or even
global mapping [51] [60]. Statistical algorithms, such as Maximum Likelihood
(Maxver), Linear Mixture Model (LSMM), and those based on set theories, such
as the Possibilistic C-Means (PCM)), and the Fuzzy C-Means (FCM) are some
examples of sub-pixel classification.
These are already incorporated into distinct image processing software availa-
ble on the market, both proprietary and open-source. However, the choice of

DOI: 10.4236/jgis.2022.141001 10 Journal of Geographic Information System

 L. S. Macarringue et al.

classifier proves to be complex and challengeable, due to each method presents

its strengths and weaknesses as shown in Table 3.
In this regard, Ackom et al. [61], Mohammady et al. [62] suggest hybrid ap-
proaches to solve the issues which have become more powerful and diversified,
due to the development of powerful and advanced classifiers.
Other strategies can be incorporated such as those which possibility to infer
proportions of vegetation cover, commonly known as vegetation indexes. The
most used are Normalized Difference Vegetation Index—(NDVI)—Normalized
Difference Water Index (NDWI)—Soil-adjusted Vegetation Index (SAVI)—the
Normalized Difference Built Index (NDBI)—Spectral Mixture Analysis Modified
Soil Adjusted Vegetation Index (MSAVI).
Nevertheless, the success of this approach depends on several factors, such as
quality of pre-processing, analyst experience, and classifier performance. How-
ever, depending on the complexity of the subject, Gómez et al. [46] point out the
following criteria to be considered when choosing the classification algorithm:
type of data, statistical distribution of classes, target accuracy, ease of use, speed,
scalability and interpretability in order to achieve acceptable accuracy and ra-
tionalization of resources (Table 4).

Machine Learning Algorithms

Machine Learning (ML) are algorithms or models built to gain from information
and acts appropriately in future circumstances, being grouped in: Lazy (e.g.
k-nearest neighbour, Case-based reasoning) and eager (Decision Tree, Naive Bayes,
Artificial Neural Networks) and mainly divided into four categories: supervised
learning, unsupervised learning, semi-supervised learning, and reinforcement
learning [81] [82].
According to Galván et al. [81] most of the machine learning algorithms
(MLAs)—based on trees, rules, functions, etc.—are eager learning methods, in the
sense that the generalization is carried out beyond the training data before observ-
ing the new instance. They are a powerful tool for training Artificial Intelligence

Table 3. Advantages and disadvantages of some classification algorithms framed in distinct approaches.

Classification
Algorithm Advantages Disadvantage Reference
approach
Manage well large feature space; Needs parameters for network design;
Artificial
Indicate strength of class membership; Tends to overfit data; Black box (rules
Pixel-Based Neural [46]
Resistant to training data deficiencies- are unknown); Computationally
Networks
requires less training data than DT intense; Slow training
Clear physical meaning and being able Hard to find a proper endmember in
Sub-pixel Based Spectral Unmixing [60]
to estimate fractional distribution larger scale

Support Manages well large feature space;

Needs parameters: regularization and
Vector Insensitive to Hughes effect; Works
Object Based kernel; Poor performance with small [46]
Machines well with small training dataset and
feature space; Computationally intense
(SVM) does not overfit

Source: Authors (2021).

DOI: 10.4236/jgis.2022.141001 11 Journal of Geographic Information System

L. S. Macarringue et al.

Table 4. Distinct approaches and algorithms for handling spatial data.

Classification Software/
Method Algorithm Data/product/Place References
Approach Platform used
Sentinel-2, Cartosat-DEM,
SVM GEE, OBT [63] [64]
Multi-temporal, Vietnam India
MKNN Landsat, single date, India Not reported [65]
Supervised
Landsat, Time series, Turkey IDRISI, ArcGIS [66]
ML Landsat/sentinel, Time series, Not reported
[67] [68]
Ethiopia Vietnam Envi/ArcGIS
ISODATA IRS-P5, Single date, India ERDAS IMAGINE [69]
Landsat 8/Sentinel2/ALOS 2
Pixel Based Unsupervised Hierarchical Clustering Forestry TEP [70]
PALSAR, Multi-temporal, Finland
K-Mean Sentinel, time-series, Australia GEE [71]
ERDAS IMAGINE,
ML-ISODAT Landsat, Multi-temporal, India [72]
ENVI, ArcGIS
CA-Marcov Chain Landsat, Multi-temporal, Ghana QGIS [61]
Hybrid
ISODATA-Decision
Landsat, Multi-temporal, Iran ArcGIS [62]
Rule Based

LP-SVM (SMCF) Hyperspectral (not specified), China Matlab [57]

Landsat/MODIS/SRTM,
LSMA Not reported [60]
Time series, Brazil
SMA
Hyperspectral (APEX)/Sentinel-2,
Sub pixel MESMA LAStools [59]
Single date Belgium
Fuzzy Rule Based IRS-P6, India Erdas IMAGINE [73]
Fuzzy analysis
Fuzzy C-Mean (FCM) IKONOS, single date, Netherlands Not reported [74]
Landsat/IRS/ASTER-GDEM,
Decision Rule eCognition developer [75]
Multi-temporal, India
Nearest Neighbor Landsat, Malawi Not reported [76]
OBIA
Landsat/MODIS/Google Earth, Trimble eCognition
[77]
Object Based RF Time Series, USA Developer
Landsat, Time Series, Brazil GEE [78]
Gaofen (GF-1)/Ziyuan
Knowledge Expert rule Not reported [79]
(ZY-3)/ASTER-GDEM, China
Based
Expert-Knowledge WorldView-2, Multitemporal. Italy Not reported [80]

ML-Maximum Likelihood; MKNN-Modified k-nearest Neighbors; TEP-Thematic Exploitation Platform; SMCF-Superpixel and
Multi-Classifier Fusion; MESMA-Multiple Endmember Spectral Mixture Analysis; APEX-Airborne Prism Experiment; LSMA-
Linear Spectral Mixture Analysis; NN-Nearest Neighbor; GEE-Google Earth Engine. Source: Authors (2021).

(AI) models that can help increase automation or optimize the operational effi-
ciency of sophisticated systems such as robotics, autonomous driving tasks, man-
ufacturing and supply chain logistics [82].
Classification methods in ML can be Binary, which refers to the classification

DOI: 10.4236/jgis.2022.141001 12 Journal of Geographic Information System

 L. S. Macarringue et al.

tasks having two class labels such as “true or yes and false or no”; multiclass—
which refers to those classification tasks having more than two class labels; and
multi-label—which represent the generalization of multiclass classification, where
the classes involved in the problem are hierarchically structured, and each ex-
ample may simultaneously belong to more than one class in each hierarchical
level [82] [83].
Several works on land use and land cover mapping using machine learning
classifiers have been carried out [3] [6] [21] [56] [84]—Classification and Re-
gression Trees (CART), Random Forest (RF), kNearest Neighbor (k-NN), Sup-
port Vector Machine (SVM), Artificial Neural Network (ANN), Multinomial Lo-
gistic Regression (MLR), C5.0, J48 (Decision Tree) have shown more efficient
compared to conventional ones.
According to Shetty [21], while some of these classifiers such as SVM find a
subset of training data as support vectors by fitting a hyperplane that separates
twos classes in the best possible way, CART build simple decision tree from the
given training data, ANN follow a neural network pattern and build multiple
layer of nodes to passes input observations back and forth during the learning
process (Multi-Layer Perceptron) until it reaches a termination condition, RF
uses random subset of training data to construct multiple decision trees. Figure
4 and Figure 5 illustrate respectively some Machine Learning Methods hig-
hlighting supervised learning and machine learning workflow.

Machine Learning
Methods

Reinforcement Semi-supervised Unsupervised Supervised

Learning Learning Learning Learning

Negative Positive Unlabeled and Unlabeled

(Penalty) (reward) Labeled Data Data Target Var. Target var.
(Continuous) (Discrete)

Classification Clustering
Regression Classification

Clustering

Logic Statistical Perceptron Instant SVM

Association Based Based Based

Learning Set
Naïve Bayes Bayesian K-Nearest
of rules
Classifier Network Neighbor (KNN)
(Penalty)

Decision
Single Layer
Tree

Multi-Layer

RBF Network

Figure 4. Machine learning methods highlighting some supervised learning techniques in gray. Source: Authors (2021).

DOI: 10.4236/jgis.2022.141001 13 Journal of Geographic Information System

L. S. Macarringue et al.

Figure 5. A machine learning workflow. Source: Authors (2022) created in

[Link]

They register improvements of 10% to 20% higher accuracy when confronted

with complex data related to large areas [46]. The success of the classifiers for
the theme is due to their unlimited assumptions of parametric statistics, and
therefore, more suitable for: 1) analyzing multimodal, noisy and/or absent data;
2) analyze combinations of categorical and continuous auxiliary data; 3) reduc-
tion of pre-processing steps required in traditional approaches; 4) performance
in cloud computing environments, such as Google Earth Engine (GEE).
GEE is a cloud-based platform with multiple petabytes which provides parallel
computing and data catalog services for geospatial analysis on a planetary scale
[5] [85]. The calculations are automatically parallelized, and data sets ready for
public use. The calculations come from several geospatial data development
agencies, such as the United States Geological Survey (USGS) and the European
Space Agency (ESA), reflection data sets from Landsat surface to Sentinel data
sets, various global land cover data, climate data sets, among others. It provides
several integrated methods that support pre-processing images, in addition to
having a repository of vast functions, such as masks, logical operators, sampling
data, etc., and they perform various operations on images and vectors [21].
An example of machine learning applications can be found in Li et al. [86], ar-
ticle published in Remote Sensing Journal. In this article, it’s proposed to gener-
ate a land cover map of the whole African continent at 10 m resolution utilizing
machine learning algorithms, and multi-source data in the GEE platform. A
workflow designed for on it is shown in Figure 6 where it’s highlighted the 5
steps of machine learning workflow.

DOI: 10.4236/jgis.2022.141001 14 Journal of Geographic Information System

 L. S. Macarringue et al.

Figure 6. Flowchart of the proposed framework highlighting the machine learning workflow steps. Source: Li et al.
[86]. Edited by authors.

DOI: 10.4236/jgis.2022.141001 15 Journal of Geographic Information System

L. S. Macarringue et al.

Through this study it was possible to generate a map of land cover of all Afri-
ca, obtaining an accuracy of 81% for 5 classes, which is relatively superior to the
existing 10 m land cover product (e.g., FROM-GLC10) in detecting urban class
in city areas and identifying the boundaries between trees and low plants in rural
areas. Part of the results of this study are shown in Figure 7 (more details can be
found in the original article).

3.3. Time Series/Multi-Temporal, Multi-Scale/Multi-Source

Time series of medium spatial resolution optical data present significant results
compared to a single scene. It presents high capacity to characterize environ-
mental phenomena describing trends, as well as discrete events of change in cha-
racterization and identification of nature changes in land use and land cover [51]
[87] [88].

DOI: 10.4236/jgis.2022.141001 16 Journal of Geographic Information System

 L. S. Macarringue et al.

Figure 7. Visual results of experiments of “city-wise holdout cross validation” in A and

Visual mapping results of the whole continent of Africa in B. Source: Li et al. [86]. Edited
in [Link]

Landsat data is considered the appropriate/standard to classify land use and

land cover changes [55], due to its spatial resolution (30 m), temporal (16/8
days), covered area (185 × 185 km), rigorous calibration, and consistency in the
radiometry of sensors (TM/ETM+/OLI).
For Chi et al. [20] traditionally, data fusion can be carried out in terms of pix-
el-level fusion, feature-level fusion, and decision-level fusion. However, big data
in remote sensing usually comprise different scales and/or formats.
According to Huang and Wang [11] Big Spatial Data (BSD) can integrate data
from various sources, providing a more comprehensive picture and when doing
so, a huge amount of data is pulled from different formats, devices or systems
and given a geographic context to facilitate building a complete picture or analy-
sis, but it’s important to wonder how to integrate the data from various sources,
where data features are significantly different (e.g., spectral signatures in optical
remote sensing data, electromagnetic radiation in microwave data, structural fea-
tures of texts, unstructured features of images by a digital camera, etc.).
The use of multi-source data, also provides land use and land cover mapping,
and improve classification accuracy [6] [23] [54] [86] by collecting samples with
high resolution sensors and fusing different sensor products (optical/optical or
optical/radar) allowing clear target differentiation.
In this regard, Häme et al. [70] used the Hierarchical Clustering method to

DOI: 10.4236/jgis.2022.141001 17 Journal of Geographic Information System

L. S. Macarringue et al.

detect and identify changes in land cover using paired data Sentinel-2/Sentinel-2,
Landsat-8/Sentinel-2, and Sentinel-2/ALOS 2 PALSAR in an area of 12,372 km2
in Finland. Joshi et al. [89] reviewed 112 studies on fusing optical and radar data,
which offer unique spectral and structural information, for land cover and use
assessments were they assessed advantages of fusion for land use analysis in 32
studies, and a large majority (28 studies) concluded that fusion improved results
compared to using single data sources. MateoGarcia et al. [90] proposed and
implemented a methodology to mask clouds (Cloud Mask) using GEE to map a
type of biome based on data from OLI/Landsat-8. The algorithms used (FMask
and ACCA), showed relevant quantitative performance, improving from 4% to
5% in classification accuracy, and 3% to 10% in commission errors. Adamo et al.
[80], Samal and Gedam [75] present others applications.

3.4. Validation and Accuracy Assessment

Monitoring and managing the territory requires accurate information on land
cover. Attempts to obtain accurate land use and land cover maps will always ac-
company professionals in the area [21]. The validation of land cover products is
essential to show the quality of remote sensing products for decision making.
Evaluating and reporting with appropriate information metrics is essential for
the community of users [46]. Thus, factors such as size and quality of training
samples, thematic accuracy, choice of classifier, and the size of study area affect
the accuracy of classified maps [13] [14] [21] [91].
Comprehending these factors aids to find the appropriate accuracy classifica-
tion for a given problem studied [21]. Selecting samples must comply with sta-
tistical criteria, such as the type and method of sampling. Mastella and Vieira
[56], Shetty [21] states that in remote sensing, simple and stratified random sam-
pling are largely used, with most validation indexes based on simple random.
However, authors who employ and recommend systematic sampling methods to
study land use and land cover, due to their accurate results, despite the absence
of an unbiased estimate of the variance [21].
Accuracy assessment is the key component to have maps with remote sensing
data, as it supports evaluating the performance of various classifiers and the ef-
fect of sampling [6]. The literature recommends the inclusion of an error or con-
fusion matrix [13] [14] to assist the identification of confusion between classes, as
well as potential sources of error [21] [46] [56]. Furthermore, quantitative me-
trics derived from confusion matrix provide significant support, such as global
accuracy, which expresses how close the classified map is to the original, as well
as weighted metrics (producer accuracy and user accuracy, Kappa index, Tau,
statistical Z, among others) by area and confidence intervals.

4. Future Perspectives and Challenges

The world has experienced a remarkable and rapid advance in the field of re-
mote sensing, acquisition of geospatial information and mapping. Cloud archi-

DOI: 10.4236/jgis.2022.141001 18 Journal of Geographic Information System

 L. S. Macarringue et al.

tectures, open-source software, creative image processing developers, and a mar-

ket eager to integrate data sets based on Earth observation and location to verify
assumptions and predict trends continue to drive the industry.
In 2005, The Global Earth Observation System of Systems (GEOSS) was created,
and a new era started for the geotechnologies and remote sensing. The new tech-
nological advances have been characterized by the flow of information, interna-
tional cooperation, interconnection between current and future observation sys-
tems with impacts on cost reduction in the generation of remote sensing and
geoprocessing products. It has revolutionized the ability to study and manage
our planet [92].
The reuse of rockets, the launch of multiple satellites from a mission, the use
of low orbits in the constellations of the satellites [15] are successful examples
that have revolutionized the space sciences.
NASA and ESA developed the Landsat-8 and Sentinel2 (HLS) data harmoni-
zation project, whose objective was to provide a single data from the 2 satellites
with a temporal resolution of 3 to 5 days depending on latitude.
According to Aubrecht [93], the efforts presented here, associated with the
improved combined use of new types of space-based data with data from dy-
namic networks of sensors in situ, and the policies of free data distribution high-
lights an inevitable path towards to dynamic (almost) real-time monitoring, es-
pecially in application domains involving social and population activities. In ad-
ditional, states that the benefits of the new trend are obtaining a substantially
high spatio-temporal resolution capable of monitoring living species. Table 5
summarizes some progress achieved in the scope of production and processing
spatial data for distinct purposes.
Although all this scenario seen above, the challenges of remote sensing persist,
some of them are rolled below:
1) Allocate sensors with every high resolution, in a single platform since the
LULC characteristics occur at finer spatial scales compared to the resolution of
primary remote sensing satellites.
2) Improve MLAs based on the sub-pixel in order to attenuate the spectral
mixtures of the LULC-related targets, especially in regions with very fragmented
uses and coverage.
3) Definition of the number of samples: according to the Shetty [21], due to
the small number of training samples and the diversity of the spatial and spectral
distributions of land covers, the existing spectral classification methods and spec-
tral-spatial classification methods usually perform better for certain land cover
types and relatively worse for others.
4) Understaffed qualified personnel associated with the financial, political and
economic constraints can be considered as a challenge in the developing coun-
tries. According to Cerbaro et al. [94], these could limit the capacity of institu-
tions to develop the qualified personnel and infrastructure to benefit from the
acknowledged gains that EO data and information can bring to their environ-
mental and sustainability management roles.

DOI: 10.4236/jgis.2022.141001 19 Journal of Geographic Information System

L. S. Macarringue et al.

Table 5. Some progress achieved in the scope of production and processing spatial data.

Time series Initiatives Events

Interconnecting existing and future Earth observation systems.
2005 GEOSS initiative Reduces costs, promotes international cooperation and serves the public good.
One user may require many data sets, while one data set may serve many users.
INPE becomes a pioneer by making CBERS-2 images available free of charge from 2004.

EO Open-data In 2008, the USGS adopted a free and open Landsat data policy which led to a
2004-2013 initiatives substantial increase in the use of Landsat data.
(INPE/NASA/ESA)
ESA’s Sentinel-2 data product become publicly available at no cost through accessible
web portals.

Planet Labs Inc. operates a constellation of more than 100 cubes (doves) to capture daily
Commercial high-resolution images (3 - 5 m).
microsatellite
constellations The TripleSat/DMC3 Constellation successfully launched in 2015 which makes it
possible to target anywhere on earth once per day.
Launching multiple satellites from one mission, and the use of low orbit in the
constellations of the satellites.
Rockets Reuse
Rocket reuse by Space X in 2017, with the possibility of simultaneously launching many
satellites.
Last decade (2nd
millennium) Functionalities for big EO data management, storage and access.
Spatial Data
Provide a more complete solution for big EO data management and analysis by
Infrastructure (SDI)
integrating different kinds of technologies.
Developments.
Application Programming Interfaces (API) and web services.
Global observations of the land every 2-3 days at moderate (<30 m) spatial resolution.
Harmonized
Landsat 8 and Uses a set of algorithms to obtain seamless products from OLI and MSI: atmospheric
Sentinel-2 (HLS) correction, cloud and cloud-shadow masking, spatial co-registration and common
gridding, illumination and view angle normalization and spectral band pass adjustment.

Source: Authors (2021).

In general, the possibility of using all the data simultaneously, combine all
available information about the areas studied regardless of their media and take
advantage of complementarity of heterogeneous methods; opportunity of new
kinds of analysis and incremental new methods; need to strengthen the links
between geographer and computer scientists; use of unsupervised (or guided)
approaches and rethink the algorithms; define algorithm and method able to
take into account error/inaccuracies in data and so does in knowledge; remain
the remote sensing challenges. More details, on a systematized way of these and
other challenges can be found in Nedd et al. [48].

5. Conclusions
The present study aimed to address the advances achieved in the field of acquisi-
tion and processing of remotely sensed data for the purpose of land use and land
cover mapping. Advances in data acquisition techniques were presented, such as

DOI: 10.4236/jgis.2022.141001 20 Journal of Geographic Information System

 L. S. Macarringue et al.

reusing satellite and rocket launch bases; software and algorithms to treat spatial
data, as well as approaches for processing such data. Several approaches were
developed due to the limitations presented by each one, as well as the algo-
rithms. Thus, it has been proposed to use sub-pixel learning algorithms to solve
problems with mixed pixels found in the pixel-based approach, since they disin-
tegrate the pixel spectrum into its constituent spectra.
Relatively to Big Data, cloud processing using platforms, such as GEE is pro-
posed and recommended. However, since it is not possible to find a universal
approach for data processing on land use and cover, due to, the classification
systems which, for example, incorporate remotely sensed data and land observa-
tions as an essential function for analysis and assessment of land use and land
cover maps, several studies point to hybrid or improved approaches, because
there are certain classes, little highlighted using a certain technique.
The world is interconnected, joining synergies in order to find solutions to the
challenges proposed, such as the combined improved use of new types of space-
based data from dynamic sensor networks in situ, making essential updates.
Nevertheless, issues related to multisource, multi-temporal and multilevel analy-
sis, robustness and quality, scalability, remain challenging the remote sensing.

Acknowledgements
This research was funded by “National Council for Scientific and Technological
Development—CNPq, grant number 190158/2017-4” and for the research fel-
lowship for the second author, and by the “Coordenação de Aperfeiçoamento de
Pessoal de Nível Superior—Brasil (CAPES) Finance Code 001”.

Conflicts of Interest
The authors declare that there is no conflict of interests regarding the publica-
tion of this article.

References
[1] Barbosa, C.C.F., Novo, E.M.L.M. and Martins, V.S. (2019) Introdução ao Sensoriamento
Remoto de sistemas aquáticos: Princípios e aplicações. 1a edição, Instituto Nacional de
Pesquisas Espaciais, São José dos Campos. [Link]
[2] Burton, C. (2016) Earth Observation and Big Data: Creatively Collecting, Processing
and Applying Global Information. Earth Imaging Journal.
[Link]
ing-processing-and-applying-global-information
[3] Sidhu, N., Pebesma, E. and Câmara, G. (2018) Using Google Earth Engine to Detect
Land Cover Change: Singapore as a Use Case. European Journal of Remote Sensing,
51, 486-500. [Link]
[4] Probst, L., Pedersen, B. and Dakkak-Arnoux, L. (2017) Big Data in Earth Observa-
tion.
[Link]
Big%20Data%20in%20Earth%20Observation%[Link]
[5] Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D. and Moore, R.

DOI: 10.4236/jgis.2022.141001 21 Journal of Geographic Information System

L. S. Macarringue et al.

(2017) Google Earth Engine: Planetary-Scale Geospatial Analysis for Everyone. Re-
mote Sensing of Environment, 202, 18-27. [Link]
[6] Teluguntla, P., Thenkabail, P., Oliphant, A., Xiong, J., Gumma, M.K., Congalton,
R.G., Yadav, K. and Huete, A. (2018) A 30-m Landsat-Derived Cropland Extent Prod-
uct of Australia and China Using Random Forest Machine Learning Algorithm on
Google Earth Engine Cloud Computing Platform. ISPRS Journal of Photogramme-
try and Remote Sensing, 144, 325-340.
[Link]
[7] Mutanga, O. and Kumar, L. (2019) Google Earth Engine Aplications. Remote Sens-
ing, 11, Article No. 591. [Link]
[8] Liu, L., Zhang, X., Gao, Y., Chen, X., Shuai, X. and Mi, J. (2021) Finer-Resolution
Mapping of Global Land Cover: Recent Developments, Consistency Analysis, and
Prospects. Journal of Remote Sensing, 2021, 1-38.
[Link]
[9] Jha, M.K. and Chowdary, V.M. (2007) Challenges of Using Remote Sensing and GIS
in Developing Nations. Hydrogeology Journal, 15, 197-200.
[Link]
[10] Gomes, V.C.F., Queiroz, G.R. and Ferreira, K.R. (2020) An Overview of Platforms
for Big Earth Observation Data Management and Analysis. Remote Sensing, 12, Ar-
ticle No. 1253. [Link]
[11] Huang, B. and Wang, J. (2020) Big Spatial Data for Urban and Environmental Sus-
tainability. Geo-Spatial Information Science, 23, 125-140.
[Link]
[12] Reeves, M.C., Washington-Allen, R.A., Angerer, J., Hunt, E.R., Kulawardhana,
R.W., Kumar, L., Loboda, T., Loveland, T., Metternicht, G. and Ramsey, R.D. (2016)
Land Resources Monitoring, Modeling, and Mapping with Remote Sensing. In: Pra-
sad, S.T., Ed., Land Resources Monitoring, Modeling, and Mapping with Remote
Sensing, CRC Press, Boca Raton, 237-275.
[13] Congalton, R.G. and Green, K. (2009) Assessing the Accuracy of Remotely Sensed
Data: Principles and Practices. 2nd Edition, CRC Press, Boca Raton.
[Link]
[14] Food and Agriculture Organization of the United Nations (2016) Map Accuracy
Assessment and Area Estimation: A Practical Guide. National forest Monitoring As-
sessment Working Paper, No. 46, Food and Agriculture Organization of the United
Nations, Rome. [Link]
[15] Zhu, L., Suomalainen, J., Liu, J., Hyyppä, J., Kaartinen, H. and Haggren, H. (2018) A
Review: Remote Sensing Sensors. In: Rustamov, R., Hasanova, S. and Zeynalova, M.,
Eds., Multi-Purposeful Application of Geospatial Data, IntechOpen, London, 19-42.
[Link]
[16] Zwinkels, J.C. (2016) Light, Electromagnetic Spectrum. In: Luo, R., Ed., Encyclope-
dia of Color Science and Technology, Springer Science + Business Media, New York,
2-8. [Link]
[17] Butcher, G. (2016) Tour of the Electromagnetic Spectrum. 3rd Edition, National
Aeronautics and Space Administration, Washington DC.
[18] Bowker, D.E., Davis, R.E., Myrick, D.L., Stacy, K. and Jones, W.T. (1985) Spectral
Reflectances of Natural Targets for Use in Remote Sensing Studies. National Aero-
nautics and Space Administration, Washington DC.
[19] Coetzee, S., Ivánová, I., Mitasova, H. and Brovelli, M.A. (2020) Open Geospatial

DOI: 10.4236/jgis.2022.141001 22 Journal of Geographic Information System

 L. S. Macarringue et al.

Software and Data: A Review of the Current State and A Perspective into the Fu-
ture. ISPRS International Journal of Geo-Information, 9, Article No. 90.
[Link]
[20] Chi, M., Plaza, A., Benediktsson, J.A., Sun, Z., Shen, J. and Zhu, Y. (2016) Big Data
for Remote Sensing: Challenges and Opportunities. Proceeding of the IEEE, 104,
2207-2219. [Link]
[21] Shetty, S. (2019) Analysis of Machine Learning Classifiers for LULC Classification
on Google Earth Engine. MSc. Thesis, University of Twente, Enschede.
[22] Sajjad, H. and Kumar, P. (2019) Future Challenges and Perspective of Remote Sens-
ing Technology. In: Kumar, P., Rani, M., Chandra Pandey, P., Sajjad, H. and Chaud-
hary, B.S., Eds., Applications and Challenges of Geospatial Technology, Springer In-
ternational Publishing, Cham, 275-277.
[Link]
[23] Xu, Y. and Huang, B. (2014) Spatial and Temporal Classification of Synthetic Satel-
lite Imagery: Land Cover Mapping and Accuracy Validation. Geo-Spatial Informa-
tion Science, 17, 1-7. [Link]
[24] Maurya, S.P., Ohri, A. and Mishra, S. (2015) Open Source GIS: A Review. National
Conference on Open Source GIS: Opportunities and Challenges, Varanasi, 9-10 Oc-
tober 2015, 150-155. [Link]
[25] GIS Technical Advisory Committee (2017) Open Source GIS Software: A Guide for
Understanding Current GIS Software Solutions. North Carolina Geographic Infor-
mation Coordinating Council, Raleigh.
[Link]
[26] Steiniger, S. and Hay, G.J. (2009) Free and Open Source Geographic Information
Tools for Landscape Ecology. Ecological Informatics, 4, 183-195.
[Link]
[27] Teodoro, A.C., Ferreira, D. and Sillero, N. (2012). Performance of Commercial and
Open Source Remote Sensing/Image Processing Software for land Cover/Use Pur-
poses. Earth Resources and Environmental Remote Sensing/GIS Applications III,
8538, Article ID: 85381K. [Link]
[28] Correia, R., Duarte, L., Teodoro, A.C. and Monteiro, A. (2018) Processing Image to
Geographical Information Systems (PI2GIS)—A Learning Tool for QGIS. Educa-
tion Sciences, 8, Article No. 83. [Link]
[29] Anand, A., Krishna, A., Tiwari, R. and Sharma, R. (2018) Comparative Analysis be-
tween Proprietary Software vs. Open-Source Software vs. Free Software. 5th IEEE In-
ternational Conference on Parallel, Distributed and Grid Computing (PDGC-2018),
Solan, 20-22 December 2018, 144-147. [Link]
[30] Mota, C. and Seruca, I. (2015) Open Source Software vs. Proprietary Software in
Education. 10th Iberian Conference on Information Systems and Technologies, (CISTI),
Aveiro, 17-20 Jun 2015, 1-6. [Link]
[31] Miller, A. (2011) Open Source vs. Proprietary Software in Developing Countries.
[Link]
[32] Tesoriere, A. and Balletta, L. (2017) A Dynamic Model of Open Source vs. Proprie-
tary R & D. European Economic Review, 94, 221-239.
[Link]
[33] Neteler, M., Beaudette, D.E., Cavallini, P., Lami, L. and Cepicky, J. (2008) GRASS
GIS. In: Hall, G.B. and Leahy, M.G., Eds., Open Source Approaches in Spatial Data
Handling, Vol. 2, Issue October 2014, Springer, Berlin, Heidelberg, 171-199.
[Link]

DOI: 10.4236/jgis.2022.141001 23 Journal of Geographic Information System

L. S. Macarringue et al.

[34] Montesinos, S. and Fernández, L. (2012) Introduction to ILWIS GIS Tool. In: Erena,
M., López-Francos, A., Montesinos, S. and Berthoumieu, J-.P., Eds., Otions Méditer-
ranéennes, No. 67, 47-52.
[Link]
[35] Câmara, G., Vinhas, L., Ferreira, K.R., de Queiroz, G.R., de Souza, R.C.M., Monteiro,
A.M.V., de Carvalho, M.T., Casanova, M.A. and de Freitas, U.M. (2008) TerraLib:
An Open Source GIS Library for Large-scale Environmental and Socio-economic
Applications. In: Hall G.B., Ed., Open Source Approaches to Spatial Data Handling,
Vol. 2, Springer, Berlin, Heidelberg, 247-270.
[Link]
[36] Olaya, V. (2004) A Gentle Introduction to SAGA GIS. 1.1 Edition, Olaya Victor and
Pineda Javier Editors., Madrid, Spain.
[37] Nanni, A., Descovi Filho, L., Virtuoso, M.A., Montenegro, D., Willrich, G., Machado,
P.H., Sperb, R., Dantas, G.S. and Calazans, Y. (2012) Quantum GIS Guia do Usuário,
Versão 1.7.4 ‘Wroclaw’ (Avalable i). [Link]
[38] Moutahir, H. and Agazzi, V. (2012). The gvSIG Project. International Conference of
GIS Users, Taza, 23-24 May 2012, 1-6.
[39] dos Santos, A.R., Machado, T. and Saito, N.S. (2010) Spring 5.1.2 passo a passo:
Aplicações práticas. CAUFES, Alegre.
[Link]
%20as/[Link]
[40] Eastman, J.R. (2003) IDRISI Kilimanjaro Guide to GIS and Image Processing. Clark
Labs Editor, Worcester, MA.
[Link]
ge_Processing
[41] Hexagon (2020) ERDAS IMAGINE 2020 Update 1. Hexagon, Stockholm.
[Link]
_IMAGINE_2020_Release_Guide.pdf
[42] Exelis Visual Information Solutions (2009) Getting Started in ENVI. Boulder, Col-
orado: Exelis Visual Information Solutions.
[43] Earth Resource Mapping (1998, November) Costumizing ER Mapper. ed. E.R.P.L.
Mapping.
[44] Hoja, D., Schneider, M., Müller, R., Lehner, M. and Reinartz, P. (2008) Comparison
of Orthorectification Methods Suitable for Rapid Mapping Using Direct Georefe-
rencing and RPC for Optical Satellite Data. The International Archives of the Pho-
togrammetry, Remote Sensing and Spatial Information Sciences, 37, 1617-1624.
[45] Esri (2004) What Is ArcGIS? Esri, Redlands.
[46] Gómez, C., White, J.C. and Wulder, M.A. (2016) Optical Remotely Sensed Time Se-
ries Data for Land Cover Classification: A Review. ISPRS Journal of Photogramme-
try and Remote Sensing, 116, 55-72. [Link]
[47] Briassoulis, H. (2007) Land-Use Policy and Planning, Theorizing, and Modeling :
Lost in Translation, Found in Complexity ? Environment and Planning B: Urban
Analytics and City Science, 35, 16-33. [Link]
[48] Nedd, R., Light, K., Owens, M., James, N., Johnson, E. and Anandhi, A. (2021) A
Synthesis of Land Use/Land Cover Studies: Definitions, Classification Systems, Me-
ta-Studies, Challenges and Knowledge Gaps on a Global Landscape. Land, 10, Ar-
ticle No. 994. [Link]
[49] Rogan, J. and Chen, D.M. (2004) Remote Sensing Technology for Mapping and Mon-

DOI: 10.4236/jgis.2022.141001 24 Journal of Geographic Information System

 L. S. Macarringue et al.

itoring Land-Cover and Land-Use Change. Progress in Planning, 61, 301-325.

[Link]
[50] Duverger, S. (2015) Metodologia para a criação de mapas temáticos de super-resolução
com base em informações subpixel: Um estudo de caso na APA do [Link].
Dissertation, Universidade Estadual de Feira de Santana, Feira de Santana.
[Link]
[51] Du, P., Liu, S., Liu, P., Tan, K. and Cheng, L. (2014) Sub-Pixel Change Detection for
Urban Land-Cover Analysis via Multi-Temporal Remote Sensing Images. Geo-Spatial
Information Science, 17, 26-38. [Link]
[52] Farda, N.M. (2017) Multi-Temporal Land Use Mapping of Coastal Wetlands Area
using Machine Learning in Google Earth Engine. IOP Conference Series: Earth and
Environmental Science, 98, Article ID: 012042.
[Link]
[53] Zanotta, D.C., Ferreira, M.P. and Zortea, M. (2019) Processamento de imagens de
satélite. 1st Edition, O. de Textos, São Paulo.
[54] Peña, J.M., Gutiérrez, P.A., Hervás-Martínez, C., Six, J., Plant, R.E. and López-Gra-
nados, F. (2014) Object-Based Image Classification of Summer Crops with Machine
Learning Methods. Remote Sensing, 6, 5019-5041.
[Link]
[55] Phiri, D. and Morgenroth, J. (2017) Developments in Landsat Land Cover Classifi-
cation Methods: A Review. Remote Sensing, 9, Article No. 967.
[Link]
[56] Mastella, A.F. and Vieira, C.A. (2018) Acurácia temática para classificação de imagens
utilizando abordagens por pixel e por objetos. Revista Brasileira de Cartografia, 70,
1618-1643. [Link]
[57] Cui, B., Cui, J., Hao, S., Guo, N. and Lu, Y. (2020) Spectral-Spatial Hyperspectral
Image Classification Based on Superpixel and Multi-Classifier Fusion. International
Journal of Remote Sensing, 41, 6157-6182.
[Link]
[58] Xiong, J., Thenkabail, P.S., Tilton, J.C., Gumma, M.K., Teluguntla, P., Oliphant, A.,
Congalton, R.G., Yadav, K. and Gorelick, N. (2017) Nominal 30-m Cropland Extent
Map of Continental Africa by Integrating Pixel-Based and Object-Based Algorithms
Using Sentinel-2 and Landsat-8 Data on Google Earth Engine. Remote Sensing, 9,
Article No. 1065. [Link]
[59] Degerickx, J., Roberts, D.A. and Somers, B. (2019) Remote Sensing of Environment
Enhancing the Performance of Multiple Endmember Spectral Mixture Analysis
( MESMA ) for Urban Land Cover Mapping Using Airborne Lidar Data and Band
Selection. Remote Sensing of Environment, 221, 260-273.
[Link]
[60] Zhu, C., Zhang, X. and Huang, Q. (2019) Mapping Fractional Cropland Covers in
Brazil through Integrating LSMA and SDI Techniques Applied to MODIS Imagery.
International Journal of Agricultural and Biological Engineering, 12, 192-200.
[Link]
[61] Ackom, E.K., Amaning, K., Samuel, A. and Odai, N. (2020) Monitoring Land-Use
and Land-Cover Changes Due to Extensive Urbanization in the Odaw River Basin
of Accra, Ghana, 1991-2030. Modeling Earth Systems and Environment, 6, 1131-1143.
[Link]
[62] Mohammady, M., Moradi, H.R., Zeinivand, H. and Temme, A.J.A.M. (2015) A
Comparison of Supervised, Unsupervised and Synthetic Land Use Classification

DOI: 10.4236/jgis.2022.141001 25 Journal of Geographic Information System

L. S. Macarringue et al.

Methods in the North of Iran. International Journal of Environmental Science and

Technology 12, 1515-1526. [Link]
[63] Nguyen, H.T.T., Doan, T.M., Tomppo, E. and McRoberts, R.E. (2020) Land Use/Land
Cover Mapping Using Multitemporal Sentinel-2 Imagery and Four Classification
Methods—A Case Study from Dak Nong, Vietnam. Remote Sensing, 12, Article No.
1367. [Link]
[64] Rana, V.K. and Suryanarayana, T.M.V. (2020) Performance Evaluation of MLE, RF
and SVM Classification Algorithms for Watershed Scale Land Use/Land Cover Map-
ping Using Sentinel 2 Bands. Remote Sensing Applications: Society and Environ-
ment, 19, Article ID: 100351. [Link]
[65] Rajalakshmi, K., Murugan, D. and Ganesh Kumar, T. (2013) Supervised Methods
for Land Use Classification. International Journal of Research in Information Tech-
nology, 1, 64-73.
[Link]
d_use_classification
[66] Kaya, I.A. and Görgün, E.K. (2020) Land Use and Land Cover Change in Tuticorin
Coast Using Remote Sensing and Geographic Information System Land Use and
Land Cover Change in Tuticorin Coast Using Remote Sensing and Geographic In-
formation System. Environmental Monitoring and Assessment, 192, Article No.430.
[Link]
[67] Gedefaw, A.A., Atzberger, C., Bauer, T., Agegnehu, S.K. and Mansberger, R. (2020)
Analysis of Land Cover Change Detection in Gozamin District, Ethiopia: From
Remote Sensing and DPSIR Perspectives. Sustainability, 12, Article No.4534.
[Link]
[68] Kovyazin, V.F., Demidova, P.M., Lan Anh, D.T., Hung, D.V. and Quyet, [Link].
(2020) Monitoring of Forest Land Cover Change in Binh Chau-Phuoc Buu Nature
Reserve in Vietnam Using Remote Sensing Methods and GIS techniques. IOP Con-
ference Series: Earth and Environmental Science, 507, Article ID: 012014.
[Link]
[69] Chethan, K.S., Sinchana, G.S. and Choodarathnakara, A.L. (2020) Classification of
Homogeneous Sites Using IRS-P5 Satellite Imagery. International Conference on
Computation, Automation and Knowledge Management (ICCAKM), Dubai, 9-10
January 2020, 184-189. [Link]
[70] Häme, T., Sirro, L., Kilpi, J., Seitsonen, L., Andersson, K. and Melkas, T. (2020) A
Hierarchical Clustering Method for Land Cover Change Detection and Identifica-
tion. Remote Sensing, 12, Article No. 1751. [Link]
[71] Brinkhoff, J., Vardanega, J. and Robson, A.J. (2020) Land Cover Classification of
Nine Perennial Crops Using Sentinel-1 and -2 Data. Remote Sensing, 12, Article
No.96. [Link]
[72] Kumar, J., Biswas, B. and Walker, S. (2020) Multi-Temporal LULC Classification
Using Hybrid Approach and Monitoring Built-up Growth with Shannon’s Entropy
for a Semi-Arid Region of Rajasthan, India. Journal of the Geological Society of In-
dia, 95, 626-635. [Link]
[73] Sharma, C.S., Behera, M.D., Mishra, A. and Panda, S.N. (2011) Assessing Flood In-
duced Land-Cover Changes Using Remote Sensing and Fuzzy Approach in Eastern
Gujarat (India). Water Resources Management, 25, Article No. 3219.
[Link]
[74] Zhang, Y., Du, Y., Li, X., Fang, S. and Ling, F. (2014) Unsupervised Subpixel Map-
ping of Remotely Sensed Imagery Based on Fuzzy C-Means Clustering Approach.

DOI: 10.4236/jgis.2022.141001 26 Journal of Geographic Information System

 L. S. Macarringue et al.

IEEE Geoscience and Remote Sensing Letters, 11, 1024-1028.

[Link]
[75] Samal, D.R. and Gedam, S.S. (2015) Monitoring Land Use Changes Associated with
Urbanization: An Object Based Image Analysis Approach. European Journal of Re-
mote Sensing, 48, 85-99. [Link]
[76] Pullanikkatil, D., Palamuleni, L. and Ruhiiga, T. (2016) Assessment of Land Use
Change in Likangala River Catchment, Malawi : A Remote Sensing and DPSIR Ap-
proach. Applied Geography, 71, 9-23. [Link]
[77] Huo, L., Boschetti, L. and Sparks, A.M. (2019) Object-Based Classification of Forest
Disturbance Types in the Conterminous United States. Remote Sensing, 11, Article
No. 477. [Link]
[78] Alencar, A., Shimbo, J.Z., Lenti, F., Marques, C.B., Zimbres, B., Rosa, M., Arruda,
V., Castro, I., Ribeiro, J.P.F.M., Varela, V., Alencar, I., Piontekowski, V., Ribeiro, V.,
Bustamante, M.M.C., Sano, E.E. and Barroso, M. (2020) Mapping Three Decades of
Changes in the Brazilian Savanna Native Vegetation Using Landsat Data Processed
in the Google Earth Engine Platform. Remote Sensing, 12, Article No. 924.
[Link]
[79] Wang, Y. and Lu, D. (2017) Mapping Torreya grandis Spatial Distribution Using
High Spatial Resolution Satellite Imagery with the Expert Rules-Based Approach.
Remote Sensing, 9, Article No. 564. [Link]
[80] Adamo, M., Tomaselli, V., Tarantino, C., Vicario, S., Veronico, G., Lucas, R. and
Blonda, P. (2020) Knowledge-Based Classification of Grassland Ecosystem Based on
Multi-Temporal WorldView-2 Data and FAO-LCCS Taxonomy. Remote Sensing,
12, Article No. 1447. [Link]
[81] Galván, I.M., Valls, J.M., Garcia, M. and Isasi, P. (2011) A Lazy Learning Approach
for Building Classification Models. International Journal of Intelligent Systems, 26,
773-786. [Link]
[82] Sarker, I.H. (2021) Machine Learning: Algorithms, Real-World Applications and
Research Directions. SN Computer Science, 2, Article No. 160.
[Link]
[83] Kotsiantis, S., Zaharakis, I.D. and Pintelas, P.E. (2007) Machine Learning: A Review
of Classification and Combining Techniques. Artificial Intelligence Review, 26,
159-190. [Link]
[84] Bruce, R.W., Rajcan, I. and Sulik, J. (2021) Classification of Soybean Pubescence
from Multispectral Aerial Imagery. AAAS Plant Phenomics, 2021, Article ID: 9806201.
[Link]
[85] Kumar, L. and Mutanga, O. (2018) Google Earth Engine Applications since Incep-
tion: Usage, Trends and Potential. Remote Sensing, 10, Article No. 1509.
[Link]
[86] Li, Q., Qiu, C., Ma, L., Schmitt, M. and Zhu, X.X. (2020) Mapping the Land Cover
of Africa at 10 m Resolution from Multi-Source Remote Sensing Data with Google
Earth Engine. Remote Sensing, 12, Article No. 602.
[Link]
[87] Tulbure, M.G. and Broich, M. (2013) Spatiotemporal Dynamic of Surface Water
Bodies Using Landsat Time-Series Data from 1999 to 2011. ISPRS Journal of Pho-
togrammetry and Remote Sensing, 79, 44-52.
[Link]
[88] Zhu, Z. and Woodcock, C.E. (2014) Automated Cloud, Cloud Shadow, and Snow
Detection in Multitemporal Landsat Data: An Algorithm Designed Specifically for

DOI: 10.4236/jgis.2022.141001 27 Journal of Geographic Information System

L. S. Macarringue et al.

Monitoring Land Cover Change. Remote Sensing of Environment, 152, 217-234.

[Link]
[89] Joshi, N., Baumann, M., Ehammer, A., Fensholt, R., Grogan, K., Hostert, P., Jepsen,
M.R., Kuemmerle, T., Meyfroidt, P., Mitchard, E.T.A., Reiche, J. and Ryan, C.M.
(2016) A Review of the Application of Optical and Radar Remote Sensing Data Fu-
sion to Land Use Mapping and Monitoring. Remote Sensing, 8, Article No. 70.
[Link]
[90] Mateo-García, G., Gómez-Chova, L., Amorós-López, J., Muñoz-Marí, J. and Camps-
Valls, G. (2018) Multitemporal Cloud Masking in the Google Earth Engine. Remote
Sensing, 10, Article No.1079. [Link]
[91] Lei, G., Li, A., Bian, J., Yan, H., Zhang, L., Zhang, Z. and Nan, X. (2020) OIC-MCE:
A Practical Land Cover Mapping Approach for Limited Samples Based on Multiple
Classifier Ensemble and Iterative Classification. Remote Sensing, 12, Article No. 987.
[Link]
[92] Fritz, S. (2014) Global Earth Observation System of Systems (GEOSS). In: Njoku
E.G., Ed., Encyclopedia of Remote Sensing, Springer, New York, 257-261.
[Link]
[93] Aubrecht, C. (2018) The Remote Sensing R-Evolution: More Space for Popula-
tion-Environment Research. Cyberseminars: People and Pixels Revisited: 20 Years
of Progress and New Tools for Population-Environment Research, 20-27 February
2018, 1-4.
[Link]
mote%20sensing%[Link]
[94] Cerbaro, M., Morse, S., Murphy, R., Lynch, J. and Griffiths, G. (2020) Challenges in
Using Earth Observation (EO) Data to Support Environmental Management in
Brazil. Sustainability, 12, Article No. 10411. [Link]

DOI: 10.4236/jgis.2022.141001 28 Journal of Geographic Information System