Open Access Journal
B1
2021-2024
quadriênio
Modelagem Ambiental | Vol. 7 Issue 1 (2026)
Jack Endrick Pastrana Mojica Tássia Fraga Belloli Pamela Boelter Herrmann Deyvis Cano Camila Souza Silva
Author information
PhD candidate in Remote Sensing at the Federal University of Rio Grande do Sul (UFRGS) and holder of a Master’s degree in Geography from the Federal University of Ceará (UFC), with a primary focus on the application of geospatial technologies and remote sensing in studies of environmental degradation and conservation in the Amazon region. My scientific work is centered on the monitoring of forest ecosystems, vegetation cover dynamics, and land use and land cover change processes, with an emphasis on tropical environments. My expertise includes the implementation of machine learning and deep learning models applied to the analysis of large volumes of geospatial data, the integration of multispectral and multitemporal remote sensing imagery, and the development of predictive models to support environmental management. I develop strategies that combine spatial analysis, artificial intelligence, and environmental modeling, aiming to promote sustainability, forest conservation, and ecosystem preservation.
Author information
Geographer graduated from the Federal University of Rio Grande do Sul (2017), with a Master’s degree (2019) and PhD (2025) in Remote Sensing and Geoprocessing from the Graduate Program in Remote Sensing (PPGSR-UFRGS). I have over 10 years of experience in the fields of Geosciences and Geoecology, with emphasis on the following topics: remote sensing applied to water resources with a focus on wetlands, Geographic Information Systems (GIS), digital image processing, environmental analysis (impact assessment, restoration, diagnosis, and technical reporting), mapping and classification, soil characterization in wetlands and floodplains, ecosystem services, and the estimation and improvement of vegetation biomass modeling and carbon storage in wetlands (blue carbon).
I am currently a postdoctoral researcher at the Laboratory of Geoprocessing and Environmental Analysis (LAGAM/UFRGS). I am developing an R&D&I project aimed at mapping and designing conservation strategies for wetlands to enhance mitigation and resilience to climate-related disasters in the Metropolitan Region of Porto Alegre, funded by the Research Support Foundation of the State of Rio Grande do Sul (FAPERGS).
Author information
I hold a Master’s degree and am currently a PhD candidate in Remote Sensing at the Federal University of Rio Grande do Sul (UFRGS). I have a specialization in Georeferenced Spatial Information, as well as academic training in Environmental Management (Bachelor’s degree) and Environmental Engineering. I work as an Environmental Analyst, with academic and professional experience in the areas of geoprocessing, remote sensing, UAV applications, environmental monitoring and licensing, environmental modeling, machine learning, and spatial analysis.
Author information
Specialist in Remote Sensing and Geographic Information Systems applied to the study of natural resources and agricultural production from the University of Buenos Aires, Argentina. Agricultural Engineer (Zootechnics) by profession from the National University of the Center of Peru. Master’s degree in Environmental Management and Planning from the University of Chile. PhD candidate in Remote Sensing at the Federal University of Rio Grande do Sul (UFRGS), Brazil. Research professor in the Environmental Engineering program at the University of Huánuco. Research project coordinator. Experience in publishing scientific articles in journals indexed in Scopus and Web of Science.
Author information
I am a Forest Engineer graduated from the University of Brasília, with a sandwich exchange period at Colorado State University through the Science without Borders program. During this period, I realized my affinity with the fields of geoprocessing and fire management by engaging in studies conducted in native forests in northern Colorado, USA. In addition, I was able to improve my English proficiency and develop skills such as time management, public speaking, and note-taking.
I have five years of experience in Integrated Fire Management (IFM) in Federal Protected Areas (PAs) of the Chico Mendes Institute for Biodiversity Conservation (ICMBio). I provide support in the management and planning of IFM actions in protected areas and in data systematization to assist decision-making by the coordination team.
Published in March 11, 2026
This study seeks to investigate the different uses of fire in territorial management by analyzing prescribed, controlled, and suppression burns, combined with data from the Fire Panel of the Amazon Protection System Operational and Management Center (CENSIPAM) for the year 2023. The research was carried out in the Brazilian Legal Amazon, following the official administrative boundaries, covering the states of Acre, Amapá, Amazonas, Pará, Rondônia, Roraima, Tocantins, Mato Grosso, and part of Maranhão. Fire events recorded in 2023 were retrieved from the Fire Panel platform, which compiles a database of environmental and socio-spatial variables, thereby enabling a more comprehensive characterization of fire occurrences. These data were integrated with records of prescribed, controlled, and suppression burns conducted by ICMBio brigades during the same period. The methodological framework was based on machine learning techniques to generate predictive models and provide insights into the impacts of fire use across the Brazilian Federative Units (states). The Random Forest model achieved the highest overall accuracy (76%). Suppression and prescribed burns showed the highest precision values (0.90 and 0.69, respectively), while the ROC curves and AUC scores demonstrated good generalization performance for these classes (0.84 and 0.79). Conversely, controlled burns exhibited lower predictive performance. SHAP (Shapley Additive Explanations) analyses revealed that variables such as biomass and unmonitored areas play a key role in modeling the classification of fire occurrences.

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Jack Endrick Pastrana Mojica, Tássia Fraga Belloli , Pamela Boelter Herrmann, Deyvis Cano , Camila Souza Silva