African forest are increasingly in decline as a result of land-use conversion due to human activities. However, a consistent and detailed characterization and mapping of land-use change that results in forest loss is not available at the spatial-temporal resolution and thematic levels suitable for decision-making at the local and regional scales; so far they have only been provided on coarser scales and restricted to humid forests. Here we present the first high-resolution (5 m) and continental-scale mapping of land use following deforestation in Africa, which covers an estimated 13.85% of the global forest area, including humid and dry forests. We use reference data for 15 different land-use types from 30 countries and implement an active learning framework to train a deep learning model for predicting land-use following deforestation with an F1-score of $$84\pm 0.7$$84 ± 0.7 for the whole of Africa. Our results show that the causes of forest loss vary by region. In general, small-scale cropland is the dominant driver of forest loss in Africa, with hotspots in Madagascar and DRC. In addition, commodity crops such as cacao, oil palm, and rubber are the dominant drivers of forest loss in the humid forests of western and central Africa, forming an “arc of commodity crops” in that region. At the same time, the hotspots for cashew are found to increasingly dominate in the dry forests of both western and south-eastern Africa, while larger hotspots for large-scale croplands were found in Nigeria and Zambia. The increased expansion of cacao, cashew, oil palm, rubber, and large-scale croplands observed in humid and dry forests of western and south-eastern Africa suggests they are vulnerable to future land-use changes by commodity crops, thus creating challenges for achieving the zero deforestation supply chains, support REDD+ initiatives, and towards sustainable development goals.

National-scale assessments of post-deforestation land-use are crucial for decreasing deforestation and forest degradation-related emissions. In this research, we assess the potential of different satellite data modalities (single-date, multi-date, multi-resolution, and an ensemble of multi-sensor images) for classifying land-use following deforestation in Ethiopia using the U-Net deep neural network architecture enhanced with attention. We performed the analysis on satellite image data retrieved across Ethiopia from freely available Landsat-8, Sentinel-2 and Planet-NICFI satellite data. The experiments aimed at an analysis of (a) single-date images from individual sensors to account for the differences in spatial resolution between image sensors in detecting land-uses, (b) ensembles of multiple images from different sensors (Planet-NICFI/Sentinel-2/Landsat-8) with different spatial resolutions, (c) the use of multi-date data to account for the contribution of temporal information in detecting land-uses, and, finally, (d) the identification of regional differences in terms of land-use following deforestation in Ethiopia. We hypothesize that choosing the right satellite imagery (sensor) type is crucial for the task. Based on a comprehensive visually interpreted reference dataset of 11 types of post-deforestation land-uses, we find that either detailed spatial patterns (single-date Planet-NICFI) or detailed temporal patterns (multi-date Sentinel-2, Landsat-8) are required for identifying land-use following deforestation, while medium-resolution single-date imagery is not sufficient to achieve high classification accuracy. We also find that adding soft-attention to the standard U-Net improved the classification accuracy, especially for small-scale land-uses. The models and products presented in this work can be used as a powerful data resource for governmental and forest monitoring agencies to design and monitor deforestation mitigation measures and data-driven land-use policy.

The largest tropical peatland complex in the Cuvette Centrale is marked by persistent knowledge gaps. We assessed recent peat forest disturbances and their direct drivers from 2019 to 2021 in Cuvette Centrale, spanning the Republic of Congo (ROC) and the Democratic Republic of Congo (DRC). Utilizing peatland maps and Radar for Detecting Deforestation alert data, we analyzed spatial and temporal patterns of disturbances. Further, we examined 2267 randomly sampled peat forest disturbance events through visual interpretation of monthly Planet and Sentinel 2A data to identify direct drivers. Our findings revealed that between 2019 and 2021, about 91% of disturbances occurred in DRC, with hotspots concentrated in the northwest Sud-Ubangi district. Disturbances predominantly followed a sharp seasonal pattern, recurring during the first half of each year with temporal hotspots emerging between February and May, closely associated with smallholder agriculture activities. Smallholder agriculture accounted for over 88% of disturbances in Cuvette Centrale, representing a leading role both in ROC (∼77%) and DRC (∼89%). While small-scale logging contributed 7% to the disturbances in the region, it constituted an important driver (18%) in the ROC. Other drivers included floods, roads, and settlements. Approximately 77% of disturbances occurred outside managed forest concessions in Cuvette Centrale, with 40% extending into protected areas. About 90% of disturbances were concentrated within 1 km of peat forest edges and ∼76% of the disturbances occurred within 5 km of road or river networks. The insights underscore the crucial need for effective peat forest conservation strategies in Cuvette Centrale and can inform national policies targeting peatland protection, aligning with commitments in the Brazzaville Declaration and the Paris Agreement. Further, our findings on direct driver assessment could serve as a reference dataset for machine learning models to automate the visual interpretation and upscale the assessment across the entire region.

Species-level phenology models are essential for predicting shifts in tree species under climate change. This study quantified phenological differences among dominant miombo tree species and modeled seasonal variability using climate variables. We used TIMESAT version 3.3 software and the Savitzky–Golay filter to derive phenology metrics from bi-monthly PlanetScope Normalized Difference Vegetation Index (NDVI) data from 2017 to 2024. A repeated measures Analysis of Variance (ANOVA) assessed differences in phenology metrics between species, while a regression analysis modeled the Start of Season (SOS) and End of Season (EOS). The results show significant seasonal and species-level variations in phenology. Brachystegia spiciformis differed from other species in EOS, Length of Season (LOS), base value, and peak value. Surface solar radiation and skin temperature one month before SOS were key predictors of SOS, with an adjusted R-squared of 0.90 and a Root Mean Square Error (RMSE) of 13.47 for Brachystegia spiciformis. SOS also strongly predicted EOS, with an adjusted R-squared of 1 and an RMSE of 3.01 for Brachystegia spiciformis, indicating a shift in the growth cycle of tree species due to seasonal variability. These models provide valuable insights into potential phenological shifts in miombo species due to climate change.