We address the task of mapping deforested areas in the Brazilian Amazon. Accurate maps are an important tool for informing effective deforestation containment policies. The main existing approaches to this task are largely manual, requiring significant effort by trained experts. To reduce this effort, we propose a fully automatic approach based on spatio-temporal deep convolutional neural networks. We introduce several domain-specific components, including approaches for: image preprocessing; handling image noise, such as clouds and shadow; and constructing the training data set. We show that our preprocessing protocol reduces the impact of noise in the training data set. Furthermore, we propose two spatio-temporal variations of the U-Net architecture, which make it possible to incorporate both spatial and temporal contexts. Using a large, real-world data set, we show that our method outperforms a traditional U-Net architecture, thus achieving approximately 95% accuracy.

Cerrado is the second largest biome in Brazil, covering about 2 million km${}^2$. This biome has experienced land use and land cover changes at high rates due to agricultural expansion so that more than $50\%$ of its natural vegetation has already been removed. Therefore, it is crucial to provide technology capable of controlling and monitoring the Cerrado vegetation suppression in order to undertake the environmental conservation policies. Within this context, this work aims to develop a new methodology to detect deforestation in Cerrado through the combination of two Deep Learning (DL) architectures, Long Short-Term Memory (LSTM) and U-Net, and using Landsat and Sentinel image time series. In our proposed method, the LSTM evaluates the time series in relation to the time axis to create a deforestation probability map, which is spatially analyzed by the U-Net algorithm alongside the terrain slope to produce final deforestation maps. The method was applied in two different study areas, which better represent the main deforestation patterns present in Cerrado. The resultant deforestation maps based on cost-free Sentinel-2 images achieved high accuracy metrics, peaking at an overall accuracy of $99.81\%\pm 0.21$ and F1-Score of $0.8795\pm 0.1180$. In addition, the proposed method showed strong potential to automate the PRODES project, which provides the official Cerrado yearly deforestation maps based on visual interpretation.

In the last decades, several methodologies for estimating crop phenology based on remote sensing data have been developed and used to create different algorithms. Although many studies have been conducted to evaluate the different methodologies, a comprehensive understanding of the potential of the different current algorithms to detect changes in the growing season is still lacking, especially in large regions and with more than one crop per season. Therefore, this work aimed to evaluate different phenological metrics extraction methodologies. Using data from over 1500 fields distributed across Brazil’s central area, six algorithms, including CropPhenology, Digital Earth Australia tools package (DEA), greenbrown, phenex, phenofit, and TIMESAT, to extract soybean crop phenology were applied. To understand how robust the algorithms are to different input sources, the NDVI and EVI2 time series derived from MODIS products (MOD13Q1 and MOD09Q1) and from Sentinel-2 satellites were used to estimate the sowing date (SD) and harvest date (HD) in each field. The algorithms produced significantly different phenological date estimates, with Spearman’s R ranging between 0.26 and 0.82 when comparing sowing and harvesting dates. The best estimates were obtained using TIMESAT and phenex for SD and HD, respectively, with R greater than 0.7 and RMSE of 16–17 days. The DEA tools and greenbrown packages showed higher sensitivity when using different data sources. Double cropping is an added challenge, with no method adequately identifying it.

Cover crops play a pivotal role in mitigating climate change by bolstering carbon sequestration through biomass production and soil integration. However, current methods for quantifying cover crop biomass lack spatial precision and objectivity. Thus, our research aimed to devise a remote-sensing-based approach to estimate cover crop biomass across various species and mixtures during fallow periods in France. Leveraging Sentinel-2 optical data and machine learning algorithms, we modeled biomass across 50 fields representative of France’s diverse cropping practices and climate types. Initial tests using traditional empirical relationships between vegetation indices/spectral bands and dry biomass revealed challenges in accurately estimating biomass for mixed cover crop categories due to spectral interference from grasses and weeds, underscoring the complexity of modeling diverse agricultural conditions. To address this challenge, we compared several machine learning algorithms (Support Vector Machine, Random Forest, and eXtreme Gradient Boosting) using spectral bands and vegetation indices from the latest available image before sampling as input. Additionally, we developed an approach that incorporates dense optical time series of Sentinel-2 data, generated using a Radial Basis Function for interpolation. Our findings demonstrated that a Random Forest model trained with dense time series data during the cover crop development period yielded promising results, with an average R-squared (r²) value of 0.75 and root mean square error (RMSE) of 0.73 t·ha⁻¹, surpassing results obtained from methods using single-image snapshots (r² of 0.55). Moreover, our approach exhibited robustness in accounting for factors such as crop species diversity, varied climatic conditions, and the presence of weed vegetation—essential for approximating real-world conditions. Importantly, its applicability extends beyond France, holding potential for global scalability. The availability of data for model calibration across diverse regions and timeframes could facilitate broader application.

The increasing deforestation and fires since 2019 raises concerns about the irreversible destruction of the Brazilian Amazon. Our goal was to better understand these changes in south-west Pará across different land-tenure and farm systems and between the terms of President Rousseff, Temer, and Bolsonaro. We reconstructed deforestation and fire history using all Landsat and Sentinel-2 observations from 2014 to 2020 and assessed, using quasi-experimental methods, the average treatment effects of each presidency on deforestation and fires across land-tenure and farm types. Deforestation nearly quadrupled to 1,201 km², particularly during Bolsonaro in undesignated areas and conservation units and on medium-sized farms (p < 0.001). Burning increased to 4,805 km² and in all tenure types (p < 0.001). The increase was strongest in agrarian settlements and conservation units and on medium and large farms. Our observations show the importance of clarifying land-tenure and re-strengthening disincentives of environmental infractions, which have been weakened specifically under President Bolsonaro.