Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

Journal Browser

Remote Sensing in the Amazon Biome

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Forest Remote Sensing".

Deadline for manuscript submissions: closed (30 July 2022) | Viewed by 32433

Share This Special Issue

Special Issue Editors

Dr. Osmar Abílio De Carvalho Júnior

E-Mail Website
Guest Editor

Department of Geography, University of Brasilia, Brasilia 70910-900, Brazil
Interests: deep learning; digital image processing; change detection; crop mapping
Special Issues, Collections and Topics in MDPI journals

Dr. Yosio Edemir Shimabukuro

E-Mail Website
Guest Editor

Remote Sensing Department, Instituto Nacional de Pesquisas Espaciais, São José dos Campos, São Paulo 2337-010, Brazil
Interests: tropical ecosystems and environmental sciences; forest resources; LIDAR; optical sensors of moderate spatial resolution
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Alfredo Huete

E-Mail Website
Guest Editor

School of Life Sciences, University of Technology Sydney, Ultimo, NSW 2007, Australia
Interests: biophysical remote sensing; terrestrial ecohydrology; land surface phenology; carbon and water fluxes; geostationary and low earth observations; time series analyses; climate change impacts; vegetation health and ecosystem resilience; ecological forecasting
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Gilberto Camara

E-Mail Website
Guest Editor

National Institute for Space Research (INPE), Avenida dos Astronautas, 1758, Sao Jose dos Campos 12227-010, SP, Brazil
Interests: geoinformatics; land-use change; spatial data analysis; GIScience
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleague,

The Amazon biome covers 6,700,000 square kilometers, being present in 9 countries (Brazil, Bolivia, Peru, Ecuador, Colombia, Venezuela, Guyana, Suriname, and French Guiana). The biome has the most significant biodiversity (formed by 53 large ecosystems) and water potentials (with the Amazon River being the most voluminous in the world). The region's size and high environmental diversity make remote sensing a viable and fundamental tool for its study. Remote sensing techniques offer a high capacity to help deal with the high environmental complexity and the wide range of problems faced from deforestation, illegal logging, fires, illegal mining, invasion of conservation units, and indigenous reserves. Besides, remote sensing is an essential governmental tool for monitoring and decision-making. Therefore, a wide range of polar-orbiting and geostationary satellites and airborne and in situ sensors have been used across the Amazon to better understand its health, functioning, degradation, and carbon and water cycling. Instruments include airborne LiDAR; VIS, NIR, SWIR, Thermal; Solar Chlorophyll Induced Fluorescence, SIF; GRACE; Microwave, VOD; and atmosphere CO₂ inversions from GOSAT, OCO-2.

This Special Issue, entitled "Remote Sensing in the Amazon Biome", seeks to highlight the research currently carried out in the Amazon region based on data from remote sensing. Therefore, manuscripts can include different studies such as plant communities, wetlands, fluvial dynamics, lakes, deforestation, illegal logging, agricultural expansion, pasture, climate change, sustainable development goals, disturbance events, recovery, and resilience. The collection of articles on the Amazon biome allows the scientific community to review knowledge and deepen discussions on this immense region, which is crucial to the world.

Dr. Osmar Abílio De Carvalho Júnior
Dr. Yosio Edemir Shimabukuro
Prof. Dr. Alfredo Huete
Prof. Dr. Gilberto Camara
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Forest Resources
Deforestation
Burned Area
Land Use Dynamics
Floodplain
Wetlands
Carbon Stock
Climate Change

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (8 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

27 pages, 7803 KiB

Open AccessArticle

Bringing to Light the Potential of Angular Nighttime Composites for Monitoring Human Activities in the Brazilian Legal Amazon

by Gabriel da Rocha Bragion, Ana Paula Dal’Asta and Silvana Amaral

Remote Sens. 2023, 15(14), 3515; https://doi.org/10.3390/rs15143515 - 12 Jul 2023

Viewed by 1547

Abstract

The Brazilian Legal Amazon (BLA) is the largest administrative unit in Brazil. The region has undergone a series of territorial policies that have led to specific conditions of occupation of the land and particular urban environments. This plurality expresses specific physical relations with the environment and infrastructure, which require innovative methods for detecting and profiling human settlements in this region. The aim of this work is to demonstrate how angular composites of nighttime lights can be associated with specific profiles of urban infrastructure, sociodemographic parameters, and mining sites present in the BLA. We make use of sets of yearly VNP46A4 angular composites specifically associated with the narrowest ranges of observations across the year, i.e., observations right below the sensor’s pathway (near-nadir range) and observations in between the oblique range (off-nadir), to identify urban typologies that expose the presence of structures such as vertical buildings, industrial sites, and areas with different income levels. Through a non-parametric evaluation of the simple difference in radiance values ranging from 2012 to 2021, followed by an ordinary least squares regression (OLS), we find that off-nadir values are persistently higher than near-nadir values except in areas where obstructing structures and particular anisotropic characteristics are present, generally changing trends of the so-called angular effect. We advocate that relational metrics can be extracted from the angular annual composites to provide additional information on the current urban structural state. By calculating the simple difference (DIF), the relative difference (REL), and the residual values of the linear regression formula estimated for the off-nadir and near-nadir composites (RES), it is possible to differentiate urban environments by their physical aspects, such as high-mid income areas, low-income settlements with different levels of density, industrial sites, and verticalized areas. Moreover, pixels that were exclusively found in one of the angular composites could be spatially associated with phenomena such as the overglow effect for the exclusive off-nadir samples and with the wetlands of the northwest portion of the Amazon Forest for the near-nadir samples. This work deepens our current understanding of how to optimize the use of the VNP46A4 angular series for monitoring human activities in the Amazon biome and provides further directions on research possibilities concerning nighttime light angular composites. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Graphical abstract

26 pages, 27178 KiB

Open AccessArticle

Comparing Machine and Deep Learning Methods for the Phenology-Based Classification of Land Cover Types in the Amazon Biome Using Sentinel-1 Time Series

by Ivo Augusto Lopes Magalhães, Osmar Abílio de Carvalho Júnior, Osmar Luiz Ferreira de Carvalho, Anesmar Olino de Albuquerque, Potira Meirelles Hermuche, Éder Renato Merino, Roberto Arnaldo Trancoso Gomes and Renato Fontes Guimarães

Remote Sens. 2022, 14(19), 4858; https://doi.org/10.3390/rs14194858 - 29 Sep 2022

Cited by 17 | Viewed by 2983

Abstract

The state of Amapá within the Amazon biome has a high complexity of ecosystems formed by forests, savannas, seasonally flooded vegetation, mangroves, and different land uses. The present research aimed to map the vegetation from the phenological behavior of the Sentinel-1 time series, which has the advantage of not having atmospheric interference and cloud cover. Furthermore, the study compared three different sets of images (vertical–vertical co-polarization (VV) only, vertical–horizontal cross-polarization (VH) only, and both VV and VH) and different classifiers based on deep learning (long short-term memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Units (GRU), Bidirectional GRU (Bi-GRU)) and machine learning (Random Forest, Extreme Gradient Boosting (XGBoost), k-Nearest Neighbors, Support Vector Machines (SVMs), and Multilayer Perceptron). The time series englobed four years (2017–2020) with a 12-day revisit, totaling 122 images for each VV and VH polarization. The methodology presented the following steps: image pre-processing, temporal filtering using the Savitsky–Golay smoothing method, collection of samples considering 17 classes, classification using different methods and polarization datasets, and accuracy analysis. The combinations of the VV and VH pooled dataset with the Bidirectional Recurrent Neuron Networks methods led to the greatest F1 scores, Bi-GRU (93.53) and Bi-LSTM (93.29), followed by the other deep learning methods, GRU (93.30) and LSTM (93.15). Among machine learning, the two methods with the highest F1-score values were SVM (92.18) and XGBoost (91.98). Therefore, phenological variations based on long Synthetic Aperture Radar (SAR) time series allow the detailed representation of land cover/land use and water dynamics. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Figure 1

19 pages, 5713 KiB

Open AccessArticle

Deforestation Detection in the Amazon Using DeepLabv3+ Semantic Segmentation Model Variants

by Renan Bides de Andrade, Guilherme Lucio Abelha Mota and Gilson Alexandre Ostwald Pedro da Costa

Remote Sens. 2022, 14(19), 4694; https://doi.org/10.3390/rs14194694 - 20 Sep 2022

Cited by 18 | Viewed by 3669

Abstract

The Amazon rainforest spreads across nine countries and covers nearly one-third of South America, being 69% inside Brazilian borders. It represents more than half of the remaining tropical forest on Earth and covers the catchment basin of the Amazon river on which 20% of the surface fresh water on the planet flows. Such an ecosystem produces large quantities of water vapor, helping regulate rainfall regimes in most of South America, with strong economic implications: for instance, by irrigating crops and pastures, and supplying water for the main hydroelectric plants in the continent. Being the natural habitat of one-tenth of the currently known species, the Amazon also has enormous biotechnological potential. Among the major menaces to the Amazon is the extension of agricultural and cattle farming, forest fires, illegal mining and logging, all directly associated with deforestation. Preserving the Amazon is obviously essential, and it is well-known that remote sensing provides effective tools for environmental monitoring. This work presents a deforestation detection approach based on the DeepLabv3+, a fully convolutional deep learning model devised for semantic segmentation. The proposed method extends the original DeepLabv3+ model, aiming at properly dealing with a strong class imbalanced problem and improving the delineation quality of deforestation polygons. Experiments were devised to evaluate the proposed method in terms of the sensitivity to the weighted focal loss hyperparameters—through an extensive grid search—and the amount of training data, and compared its performance to previous deep learning methods proposed for deforestation detection. Landsat OLI-8 images of a specific region in the Amazon were used in such evaluation. The results indicate that the variants of the proposed method outperformed previous works in terms of the F1-score and Precision metrics. Additionally, more substantial performance gains were observed in the context of smaller volumes of training data. When the evaluated methods were trained using four image tiles, the proposed method outperformed its counterparts by approximately +10% in terms of F1-score (from 63% to 73%); when the methods were trained with only one image tile, the performance difference in terms of F1-score achieved approximately +18% (from 49% to 67%). Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Figure 1

23 pages, 14529 KiB

Open AccessArticle

Identifying Precarious Settlements and Urban Fabric Typologies Based on GEOBIA and Data Mining in Brazilian Amazon Cities

by Bruno Dias dos Santos, Carolina Moutinho Duque de Pinho, Gilberto Eidi Teramoto Oliveira, Thales Sehn Korting, Maria Isabel Sobral Escada and Silvana Amaral

Remote Sens. 2022, 14(3), 704; https://doi.org/10.3390/rs14030704 - 2 Feb 2022

Cited by 8 | Viewed by 3931

Abstract

Although 70% of the Amazon population lives in urban areas, studies on the urban Amazon are scarce. Much of the urban Amazon population lives in precarious settlements. The distinctiveness and diversity of Amazonian precarious settlements are vast and must be identified to be considered in the development of appropriate public policies. Aiming at investigating precarious settlements in Amazon, this study is guided by the following questions: For the Brazilian Amazon region, is it possible to identify areas of precarious settlements by combining geoprocessing and remote sensing techniques? Are there different typologies of precarious settlements distinguishable by their spatial arrangements? Thus, we developed a methodology for identifying precarious settlements and subsequently classifying them into urban fabric typologies (UFT), choosing the cities of Altamira, Cametá, and Marabá as study sites. Our classification model utilized geographic objects-based image analysis (GEOBIA) and data mining of spectral data from WPM sensor images from the CBERS-4A satellite, jointly with texture metrics, context metrics, biophysical index, voluntary geographical information, and neighborhood relationships. With the C5.0 decision tree algorithm we carried out variable selection and classification of these geographic objects. Our estimated models show accuracy above 90% when applied to the study sites. Additionally, we described Amazonian UFT in six types to be identified. We concluded that Amazonian precarious settlements are morphologically diverse, with an urban fabric different from those commonly found in Brazilian metropolitan areas. Identifying and characterizing distinct precarious areas is vital for the planning and development of sustainable and effective public policies for the urban Amazon. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Figure 1

20 pages, 3295 KiB

Open AccessArticle

Deforestation Detection with Fully Convolutional Networks in the Amazon Forest from Landsat-8 and Sentinel-2 Images

by Daliana Lobo Torres, Javier Noa Turnes, Pedro Juan Soto Vega, Raul Queiroz Feitosa, Daniel E. Silva, Jose Marcato Junior and Claudio Almeida

Remote Sens. 2021, 13(24), 5084; https://doi.org/10.3390/rs13245084 - 14 Dec 2021

Cited by 40 | Viewed by 7483

Abstract

The availability of remote-sensing multisource data from optical-based satellite sensors has created new opportunities and challenges for forest monitoring in the Amazon Biome. In particular, change-detection analysis has emerged in recent decades to monitor forest-change dynamics, supporting some Brazilian governmental initiatives such as PRODES and DETER projects for biodiversity preservation in threatened areas. In recent years fully convolutional network architectures have witnessed numerous proposals adapted for the change-detection task. This paper comprehensively explores state-of-the-art fully convolutional networks such as U-Net, ResU-Net, SegNet, FC-DenseNet, and two DeepLabv3+ variants on monitoring deforestation in the Brazilian Amazon. The networks’ performance is evaluated experimentally in terms of Precision, Recall,

F 1

-score, and computational load using satellite images with different spatial and spectral resolution: Landsat-8 and Sentinel-2. We also include the results of an unprecedented auditing process performed by senior specialists to visually evaluate each deforestation polygon derived from the network with the highest accuracy results for both satellites. This assessment allowed estimation of the accuracy of these networks simulating a process “in nature” and faithful to the PRODES methodology. We conclude that the high resolution of Sentinel-2 images improves the segmentation of deforestation polygons both quantitatively (in terms of

F 1

-score) and qualitatively. Moreover, the study also points to the potential of the operational use of Deep Learning (DL) mapping as products to be consumed in PRODES. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Graphical abstract

18 pages, 6872 KiB

Open AccessArticle

Change Detection of Selective Logging in the Brazilian Amazon Using X-Band SAR Data and Pre-Trained Convolutional Neural Networks

by Tahisa Neitzel Kuck, Paulo Fernando Ferreira Silva Filho, Edson Eyji Sano, Polyanna da Conceição Bispo, Elcio Hideiti Shiguemori and Ricardo Dalagnol

Remote Sens. 2021, 13(23), 4944; https://doi.org/10.3390/rs13234944 - 5 Dec 2021

Cited by 7 | Viewed by 5285

Abstract

It is estimated that, in the Brazilian Amazon, forest degradation contributes three times more than deforestation for the loss of gross above-ground biomass. Degradation, in particular those caused by selective logging, result in features whose detection is a challenge to remote sensing, due to its size, space configuration, and geographical distribution. From the available remote sensing technologies, SAR data allow monitoring even during adverse atmospheric conditions. The aim of this study was to test different pre-trained models of Convolutional Neural Networks (CNNs) for change detection associated with forest degradation in bitemporal products obtained from a pair of SAR COSMO-SkyMed images acquired before and after logging in the Jamari National Forest. This area contains areas of legal and illegal logging, and to test the influence of the speckle effect on the result of this classification by applying the classification methodology on previously filtered and unfiltered images, comparing the results. A method of cluster detections was also presented, based on density-based spatial clustering of applications with noise (DBSCAN), which would make it possible, for example, to guide inspection actions and allow the calculation of the intensity of exploitation (IEX). Although the differences between the tested models were in the order of less than 5%, the tests on the RGB composition (where R = coefficient of variation; G = minimum values; and B = gradient) presented a slightly better performance compared to the others in terms of the number of correct classifications for selective logging, in particular using the model Painters (accuracy = 92%) even in the generalization tests, which presented an overall accuracy of 87%, and in the test on RGB from the unfiltered image pair (accuracy of 90%). These results indicate that multitemporal X-band SAR data have the potential for monitoring selective logging in tropical forests, especially in combination with CNN techniques. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Figure 1

21 pages, 6414 KiB

Open AccessArticle

Three Decades after: Landscape Dynamics in Different Colonisation Models Implemented in the Brazilian Legal Amazon

by Valdir Moura, Ranieli dos Anjos de Souza, Erivelto Mercante, Jonathan Richetti and Jerry Adriani Johann

Remote Sens. 2021, 13(22), 4581; https://doi.org/10.3390/rs13224581 - 15 Nov 2021

Cited by 1 | Viewed by 2408

Abstract

Several colonisation projects were implemented in the Brazilian Legal Amazon in the 1970s and 1980s. Among these colonisation projects, the most prominent were those with the “fishbone” and “topographic” models. Within this scope, the settlements known as Anari and Machadinho stand out because they are contiguous areas with different models and structures of occupation and colonisation. The main objective of this work was to evaluate the dynamics of Land-Use and Land-Cover (LULC) in two different colonisation models, implanted in the State of Rondônia in the 1980s. The fishbone and topographic or Disorganised Multidirectional models were implemented in the Anari and Machadinho settlements, respectively. A 36-year time series of Landsat images (1984–2020) was used to evaluate the rates and trends in the LULC process in the different colonisation models. In the analysed models, a rapid loss of primary and secondary forests (anthropized areas) was observed, mainly due to the dynamics of its use, established by the Agriculture/Pasture relation with a heavy dependence on road construction. Understanding these two forms of occupation can help the future programs and guidelines of the Brazilian Legal Amazon and any tropical rainforest across the globe. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Figure 1

13 pages, 2003 KiB

Open AccessCommunication

Phytoplankton Genera Structure Revealed from the Multispectral Vertical Diffuse Attenuation Coefficient

by Cleber Nunes Kraus, Daniel Andrade Maciel, Marie Paule Bonnet and Evlyn Márcia Leão de Moraes Novo

Remote Sens. 2021, 13(20), 4114; https://doi.org/10.3390/rs13204114 - 14 Oct 2021

Cited by 1 | Viewed by 2568

Abstract

The composition of phytoplankton and the concentration of pigments in their cells make their absorption and specific absorption coefficients key parameters for bio-optical modeling. This study investigated whether the multispectral vertical diffuse attenuation coefficient of downward irradiance (K_d) gradients could be a good framework for accessing phytoplankton genera. In situ measurements of remote sensing reflectance (R_rs), obtained in an Amazon Floodplain Lake (Lago Grande do Curuai), were used to invert K_d, focusing on Sentinel-3/Ocean and Land Color Instrument (OLCI) sensor bands. After that, an analysis based on the organization of three-way tables (STATICO) was applied to evaluate the relationships between phytoplankton genera and K_d at different OLCI bands. Our results indicate that phytoplankton genera are organized according to their ability to use light intensity and different spectral ranges of visible light (400 to 700 nm). As the light availability changes seasonally, the structure of phytoplankton changes as well. Some genera, such as Microcystis, are adapted to low light intensity at 550–650 nm, therefore high values of K_d in this range would indicate the dominance of Microcysts. Other genera, such as Aulacoseira, are highly adapted to harvesting blue-green light with higher intensity and probably grow in lakes with lower concentrations of colored dissolved organic matter that highly absorbs blue light (405–498). These findings are an important step to describing phytoplankton communities using orbital data in tropical freshwater floodplains. Furthermore, this approach can be used with biodiversity indexes to access phytoplankton diversity in these environments. Full article

(This article belongs to the Special Issue Remote Sensing in the Amazon Biome)

► Show Figures

Journal Menu

Journal Browser

Remote Sensing in the Amazon Biome

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI