This research uses drone imagery and a hybrid AI model to classify rangeland cover as green vegetation, dead vegetation, or bare soil. Combining two neural network approaches achieved 96% accuracy while requiring only simple, low-cost sensors. The method enables fast, large-scale monitoring to combat invasive shrubs and support sustainable land management.

This study modeled wild edible mushroom yields in Mediterranean forests using Planet satellite imagery, LiDAR, climate data, and field measurements. Results show that seasonal NDVI differences, precipitation, and forest structure are key predictors. Integrating high-resolution intra-annual remote sensing significantly improves yield prediction and ecological understanding.

This study analyzed long-term changes in forest composition in the Spanish Iberian Range using National Forest Inventory data and Landsat imagery. Results show a significant shift from monospecific to mixed forests, with mixed stands nearly doubling over three decades. Satellite-derived vegetation indices successfully detected these temporal dynamics.

This study examines whether burned area from forest fires in Portugal can be predicted using satellite, weather, and time-series data. Results show human-caused fires dominate over natural ones, and predictive models achieved around 95% accuracy, demonstrating strong potential for improving resource allocation and fire management strategies.

This study evaluated a PointNet++ deep learning model for binary classification of Pinus sylvestris and Quercus pyrenaica using only LiDAR 3D point clouds. A balanced dataset of 160 trees achieved 91% accuracy, showing that geometric features alone can effectively discriminate species, highlighting the potential of lightweight AI models for forest inventories.

This study evaluated multispectral and hyperspectral vegetation indices to estimate wildfire severity in the 2022 Sierra de la Culebra fire. Field Composite Burn Index data were correlated with satellite-derived indices. Results showed hyperspectral imagery provided more accurate severity estimates, particularly using Cellulose Absorption Index and Red Edge indices.

This study mapped land use changes in the Grombalia Region of Tunisia using Sentinel-2 imagery and machine learning. Three classifiers—Random Forest, SVM, and CNN—were compared. Random Forest achieved the highest accuracy. Results highlight agricultural changes over time and demonstrate the effectiveness of remote sensing for environmental monitoring.

This study explored whether satellite remote sensing can estimate black truffle mycelium biomass. Optical vegetation indices showed limited results, while Sentinel-1 radar backscatter had significant correlations, especially in spring. Findings suggest radar data capture soil moisture dynamics linked to fungal activity, offering a promising tool for sustainable truffle orchard management.

This research improves aging satellite imagery using ground-based mirror arrays that reflect sunlight to diagnose and correct image blur. By giving satellites precise calibration targets, the method sharpens observations, enabling faster disaster response, improved climate monitoring, and more accurate data for governments and scientists worldwide.

This research develops an AI-powered, multi-sensor drone system to detect butterfly landmines more safely and efficiently. By fusing sensor data into confidence-scored maps, it accelerates demining, reduces risk to operators, and supports civilian safety, land reuse, and humanitarian recovery in post-conflict regions.