Pedro Henrique Batista de Barros , Filipe Gomes Dias , José Alberto Quintanilha , Carlos Henrique Grohmann
{"title":"Mapping oil palm expansion in the Eastern Amazon using optical and radar imagery","authors":"Pedro Henrique Batista de Barros , Filipe Gomes Dias , José Alberto Quintanilha , Carlos Henrique Grohmann","doi":"10.1016/j.rsase.2025.101506","DOIUrl":null,"url":null,"abstract":"<div><div>Palm oil, the world’s most widely consumed vegetable oil, plays a pivotal role in the food, biodiesel, and pharmaceutical industries. However, its rapid expansion in tropical regions has led to critical environmental challenges, including deforestation and biodiversity loss. This study maps oil palm plantations in the Eastern Amazon, Brazil’s largest producer, for 2014, 2017, and 2020, employing machine learning algorithms such as K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Decision Trees (DT), Support Vector Machines (SVM), and Random Forests (RF). This study integrate Landsat-8 optical spectral bands (blue, green, red, and near-infrared) with Sentinel-1 radar backscatter values (VV and VH polarizations) to map the expansion of oil palm in the Brazilian Amazon, a combination that has not been previously implemented in this region. Vegetation indices, including NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), SAVI (Soil-Adjusted Vegetation Index), DVI (Difference Vegetation Index), RVI (Ratio Vegetation Index), GI (Green Index), and texture indices derived from the gray-level co-occurrence matrix (GLCM), such as contrast, angular second moment (ASM), correlation, and entropy, were used to improve classification accuracy. A linear spectral mixing model was also applied to distinguish the spectral signatures, with the resulting end members subsequently incorporated. The RF achieved the highest classification accuracy, with overall accuracies of 94.53%, 94.28%, and 95.53% for 2014, 2017, and 2020, respectively. A land use and land cover (LULC) transition analysis revealed a substantial expansion of 72.16%, with the area growing from 1,074 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> in 2014 to 1,849 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> in 2020. Notably, 156.88 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> (20.24%) of this expansion occurred directly at the expense of vegetation cover, underscoring areas of significant environmental concern. This study offers valuable insights to guide the development of public and market-driven policies aimed at promoting sustainable and environmentally responsible oil palm expansion.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101506"},"PeriodicalIF":3.8000,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Remote Sensing Applications-Society and Environment","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S235293852500059X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Palm oil, the world’s most widely consumed vegetable oil, plays a pivotal role in the food, biodiesel, and pharmaceutical industries. However, its rapid expansion in tropical regions has led to critical environmental challenges, including deforestation and biodiversity loss. This study maps oil palm plantations in the Eastern Amazon, Brazil’s largest producer, for 2014, 2017, and 2020, employing machine learning algorithms such as K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Decision Trees (DT), Support Vector Machines (SVM), and Random Forests (RF). This study integrate Landsat-8 optical spectral bands (blue, green, red, and near-infrared) with Sentinel-1 radar backscatter values (VV and VH polarizations) to map the expansion of oil palm in the Brazilian Amazon, a combination that has not been previously implemented in this region. Vegetation indices, including NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), SAVI (Soil-Adjusted Vegetation Index), DVI (Difference Vegetation Index), RVI (Ratio Vegetation Index), GI (Green Index), and texture indices derived from the gray-level co-occurrence matrix (GLCM), such as contrast, angular second moment (ASM), correlation, and entropy, were used to improve classification accuracy. A linear spectral mixing model was also applied to distinguish the spectral signatures, with the resulting end members subsequently incorporated. The RF achieved the highest classification accuracy, with overall accuracies of 94.53%, 94.28%, and 95.53% for 2014, 2017, and 2020, respectively. A land use and land cover (LULC) transition analysis revealed a substantial expansion of 72.16%, with the area growing from 1,074 km in 2014 to 1,849 km in 2020. Notably, 156.88 km (20.24%) of this expansion occurred directly at the expense of vegetation cover, underscoring areas of significant environmental concern. This study offers valuable insights to guide the development of public and market-driven policies aimed at promoting sustainable and environmentally responsible oil palm expansion.
期刊介绍:
The journal ''Remote Sensing Applications: Society and Environment'' (RSASE) focuses on remote sensing studies that address specific topics with an emphasis on environmental and societal issues - regional / local studies with global significance. Subjects are encouraged to have an interdisciplinary approach and include, but are not limited by: " -Global and climate change studies addressing the impact of increasing concentrations of greenhouse gases, CO2 emission, carbon balance and carbon mitigation, energy system on social and environmental systems -Ecological and environmental issues including biodiversity, ecosystem dynamics, land degradation, atmospheric and water pollution, urban footprint, ecosystem management and natural hazards (e.g. earthquakes, typhoons, floods, landslides) -Natural resource studies including land-use in general, biomass estimation, forests, agricultural land, plantation, soils, coral reefs, wetland and water resources -Agriculture, food production systems and food security outcomes -Socio-economic issues including urban systems, urban growth, public health, epidemics, land-use transition and land use conflicts -Oceanography and coastal zone studies, including sea level rise projections, coastlines changes and the ocean-land interface -Regional challenges for remote sensing application techniques, monitoring and analysis, such as cloud screening and atmospheric correction for tropical regions -Interdisciplinary studies combining remote sensing, household survey data, field measurements and models to address environmental, societal and sustainability issues -Quantitative and qualitative analysis that documents the impact of using remote sensing studies in social, political, environmental or economic systems