Soltan Galano Duverger

Mr. Soltan Galano Duverger

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 May 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Ane AlencarAne Alencar
Ane Alencar
VAVera Laísa da Silva Arruda
Vera Laísa da Silva Arruda
WSWallace Vieira da Silva
Wallace Vieira da Silva
Dhemerson E. ConcianiDhemerson E. Conciani
Dhemerson E. Conciani
DCDiego Pereira Costa
Diego Pereira Costa
EMEduardo Vélez Martin
Eduardo Vélez Martin
Fire is a significant agent of landscape transformation on Earth, and a dynamic and ephemeral process that is challenging to map. Difficulties include the seasonality of native vegetation in areas affected by fire, the high levels of spectral heterogeneity due to the spatial and temporal variability of the burned areas, distinct persistence of the fire signal, increase in cloud and smoke cover surrounding burned areas, and difficulty in detecting understory fire signals. To produce a large-scale time-series of burned area, a robust number of observations and a more efficient sampling strategy is needed. In order to overcome these challenges, we used a novel strategy based on a machine-learning algorithm to map monthly burned areas from 1985 to 2020 using Landsat-based annual quality mosaics retrieved from minimum NBR values. The annual mosaics integrated year-round observations of burned and unburned spectral data (i.e., RED, NIR, SWIR-1, and SWIR-2), and used them to train a Deep Neural Network model, which resulted in annual maps of areas burned by land use type for all six Brazilian biomes. The annual dataset was used to retrieve the frequency of the burned area, while the date on which the minimum NBR was captured in a year, was used to reconstruct 36 years of monthly burned area. Results of this effort indicated that 19.6% (1.6 million km2) of the Brazilian territory was burned from 1985 to 2020, with 61% of this area burned at least once. Most of the burning (83%) occurred between July and October. The Amazon and Cerrado, together, accounted for 85% of the area burned at least once in Brazil. Native vegetation was the land cover most affected by fire, representing 65% of the burned area, while the remaining 35% burned in areas dominated by anthropogenic land uses, mainly pasture. This novel dataset is crucial for understanding the spatial and long-term temporal dynamics of fire regimes that are fundamental for designing appropriate public policies for reducing and controlling fires in Brazil.

17 October 2024 in Land
Verified
Journal Article
Open access
PDF file
RVRodrigo Nogueira Vasconcelos
Rodrigo Nogueira Vasconcelos
Washington Franca-RochaWashington Franca-Rocha
Washington Franca-Rocha
DCDiego Pereira Costa
Diego Pereira Costa
Soltan Galano DuvergerSoltan Galano Duverger
Soltan Galano Duverger
MSMARIANA Martins Medeiros Santana
MARIANA Martins Medeiros Santana
CCCARLOS Leandro Oliveira CORDEIRO
CARLOS Leandro Oliveira CORDEIRO
Wildfires are a critical driver of landscape transformation on Earth, representing a dynamic and ephemeral process that poses challenges for accurate early detection. To address this challenge, researchers have increasingly turned to deep learning techniques, which have demonstrated remarkable potential in enhancing the performance of wildfire detection systems. This paper provides a comprehensive review of fire detection using deep learning, spanning from 1990 to 2023. This study employed a comprehensive approach, combining bibliometric analysis, qualitative and quantitative methods, and systematic review techniques to examine the advancements in fire detection using deep learning in remote sensing. It unveils key trends in publication patterns, author collaborations, and thematic focuses, emphasizing the remarkable growth in fire detection using deep learning in remote sensing (FDDL) research, especially from the 2010s onward, fueled by advancements in computational power and remote sensing technologies. The review identifies “Remote Sensing” as the primary platform for FDDL research dissemination and highlights the field’s collaborative nature, with an average of 5.02 authors per paper. The co-occurrence network analysis reveals diverse research themes, spanning technical approaches and practical applications, with significant contributions from China, the United States, South Korea, Brazil, and Australia. Highly cited papers are explored, revealing their substantial influence on the field’s research focus. The analysis underscores the practical implications of integrating high-quality input data and advanced deep-learning techniques with remote sensing for effective fire detection. It provides actionable recommendations for future research, emphasizing interdisciplinary and international collaboration to propel FDDL technologies and applications. The study’s conclusions highlight the growing significance of FDDL technologies and the necessity for ongoing advancements in computational and remote sensing methodologies. The practical takeaway is clear: future research should prioritize enhancing the synergy between deep learning techniques and remote sensing technologies to develop more efficient and accurate fire detection systems, ultimately fostering groundbreaking innovations.

9 August 2024 in Land
Verified
Journal Article
Open access
PDF file
Washington Franca-RochaWashington Franca-Rocha
Washington Franca-Rocha
RVRodrigo Nogueira Vasconcelos
Rodrigo Nogueira Vasconcelos
DCDiego Pereira Costa
Diego Pereira Costa
Soltan Galano DuvergerSoltan Galano Duverger
Soltan Galano Duverger
JLJocimara S. B. Lobão
Jocimara S. B. Lobão
WAWILLIAN MOURA AGUIAR
WILLIAN MOURA AGUIAR
Dryland regions around the world are facing intricate challenges due to climate change and human activities. The Caatinga biome in Brazil, an exceptional dryland ecosystem covering approximately 86.3 million hectares, is particularly impacted by human influence. We conducted an extensive study analyzing changes in land use and land cover within the Caatinga region over a span of 35 years, from 1985 to 2019. This study leverages collective knowledge and collaborative effort with the MapBiomas project to provide valuable insights into the biome’s landscape. It maps eight principal land cover classes using Landsat Collection 1 Tier 1 data normalized to top-of-atmosphere reflectance. All data processing was carried out within the Google Earth Engine platform, and the graphics were generate using R version 3.6.2. This study achieved an impressive 80% global accuracy in the time series of Caatinga land use and land cover (LULC) changes, with allocation and area discrepancies of 11.6% and 8.5%, respectively. The extensive 35-year LULC dataset reveals a substantial 11% reduction in natural vegetation in the Caatinga biome, translating to a loss of 6.57 million hectares. This decline is primarily attributed to the expansion of cattle ranching and agriculture; all types of natural vegetation have experienced decreases, with Savanna Formation (SF) areas declining by 11% and Forest Formation (FF) areas declining by 8%. In contrast, pasturelands expanded by 62% and agricultural land expanded by 284% during this period. With their urgent and significant real-world for informing social, economic, and environmental policy decisions within the Caatinga and other dryland regions globally, these findings underscore the importance and immediacy of our research.

Verified
Journal Article
Open access
PDF file
RVRodrigo Nogueira Vasconcelos
Rodrigo Nogueira Vasconcelos
Andre LimaAndre Lima
Andre Lima
CARLOS ALESSANDRE DOMINGOS LENTINICARLOS ALESSANDRE DOMINGOS LENTINI
CARLOS ALESSANDRE DOMINGOS LENTINI
JMJose Garcia Vivas Miranda
Jose Garcia Vivas Miranda
Luis Felipe Ferreira de MendonçaLuis Felipe Ferreira de Mendonça
Luis Felipe Ferreira de Mendonça
Washington Franca-RochaWashington Franca-Rocha
Washington Franca-Rocha
Oil spill detection and mapping using deep learning (OSDMDL) is crucial for assessing its impact on coastal and marine ecosystems. A novel approach was employed in this study to evaluate the scientific literature in this field through bibliometric analysis and literature review. The Scopus database was used to evaluate the relevant scientific literature in this field, followed by a bibliometric analysis to extract additional information, such as architecture type, country collaboration, and most cited papers. The findings highlight significant advancements in oil detection at sea, with a strong correlation between technological evolution in detection methods and improved remote sensing data acquisition. Multilayer perceptrons (MLP) emerged as the most prominent neural network architecture in 11 studies, followed by a convolutional neural network (CNN) in 5 studies. U-Net, DeepLabv3+, and fully convolutional network (FCN) were each used in three studies, demonstrating their relative significance too. The analysis provides insights into collaboration, interdisciplinarity, and research methodology and contributes to the development of more effective policies, strategies, and technologies for mitigating the environmental impact of oil spills in OSDMDL.

Verified
Journal Article
Open access
PDF file
LMLucrêncio Silvestre Macarringue
Lucrêncio Silvestre Macarringue
Édson Luis BolfeÉdson Luis Bolfe
Édson Luis Bolfe
Soltan Galano DuvergerSoltan Galano Duverger
Soltan Galano Duverger
ESEDSON SANO
EDSON SANO
Marcellus CaldasMarcellus Caldas
Marcellus Caldas
LMLindon Fonseca Matias
Lindon Fonseca Matias
Accurate land use and land cover (LULC) mapping is essential for scientific and decision-making purposes. The objective of this paper was to map LULC classes in the northern region of Mozambique between 2011 and 2020 based on Landsat time series processed by the Random Forest classifier in the Google Earth Engine platform. The feature selection method was used to reduce redundant data. The final maps comprised five LULC classes (non-vegetated areas, built-up areas, croplands, open evergreen and deciduous forests, and dense vegetation) with an overall accuracy ranging from 80.5% to 88.7%. LULC change detection between 2011 and 2020 revealed that non-vegetated areas had increased by 0.7%, built-up by 2.0%, and dense vegetation by 1.3%. On the other hand, open evergreen and deciduous forests had decreased by 4.1% and croplands by 0.01%. The approach used in this paper improves the current systematic mapping approach in Mozambique by minimizing the methodological gaps and reducing the temporal amplitude, thus supporting regional territorial development policies.

24 January 2023 in Fire
Verified
Journal Article
Open access
PDF file
Sarah Moura Batista dos SantosSarah Moura Batista dos Santos
Sarah Moura Batista dos Santos
Soltan Galano DuvergerSoltan Galano Duverger
Soltan Galano Duverger
António Bento-GonçalvesAntónio Bento-Gonçalves
António Bento-Gonçalves
Washington Franca-RochaWashington Franca-Rocha
Washington Franca-Rocha
António VieiraAntónio Vieira
António Vieira
GTGeorgia Teixeira
Georgia Teixeira
Mapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for this type of analysis. The main aim of this article is to develop a methodology for mapping LW in northwestern Portugal using a machine learning algorithm and time series from Landsat images. For the burnt area classification, we initially used the Fourier harmonic model to define outliers in the time series that represented pixels of possible burnt areas and, then, we applied the random forest classifier for the LW classification. The results indicate that the harmonic analysis provided estimates with the actual observed values of the NBR index; thus, the pixels classified by random forest were only those that were masked, collaborated in the processing, and reduced possible spectral confusion between targets with similar behaviour. The burnt area maps revealed that ~23.5% of the territory was burnt at least once from 2001 to 2020. The temporal variability of the burnt area indicated that, on average, 6.504 hectares were affected by LW within the 20 years. The annual burnt area varied over the years, with the minimum annual area detected in 2014 (679.5 hectares) and the maximum mapped area detected in 2005 (73,025.1 hectares). We concluded that the process of defining the mask with the outliers considerably reduced the universe of pixels to be classified within each image, which leaves the training of the classifier focused on separating the set of pixels into two groups with very similar spectral characteristics, thus contributing so that the separation of groups with similar spectral behaviour was performed automatically and without great sampling effort. The method showed satisfactory accuracy results with little omission for burnt areas.