We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Monitoring Digestate Application on Agricultural Crops Using Sentinel-2 Satellite Imagery
AI summary Read the abstract
Researchers used Sentinel-2 satellite imagery and machine learning (Random Forest, k-NN, Gradient Boosting, neural network) to detect digestate application on agricultural soils in Greece. Models achieved F1-scores up to the mid-80s%, offering a scalable approach to monitor organic fertilizer use and associated microplastic contamination risks.
The widespread use of Exogenous Organic Matter in agriculture necessitates monitoring to assess its effects on soil and crop health. This study evaluates optical Sentinel-2 satellite imagery for detecting digestate application, a practice that enhances soil fertility but poses environmental risks like microplastic contamination and nitrogen losses. In the first instance, Sentinel-2 satellite image time series (SITS) analysis of specific indices (EOMI, NDVI, EVI) was used to characterize EOM’s spectral behavior after application on the soils of four different crop types in Thessaly, Greece. Furthermore, Machine Learning (ML) models (namely Random Forest, k-NN, Gradient Boosting and a Feed-Forward Neural Network), were used to investigate digestate presence detection, achieving F1-scores up to 0.85. The findings highlight the potential of combining remote sensing and ML for scalable and cost-effective monitoring of EOM applications, supporting precision agriculture and sustainability.
More Papers Like This
Remote sensing detection of plastic-mulched farmland using a temporal approach in machine learning: case study in tomato crops
AI summary Read the abstract
Researchers tested machine learning classifiers on Sentinel-2 satellite time-series images to map plastic-mulched farmlands, achieving 99.7% accuracy using a multilayer perceptron model and demonstrating that a 3-image composite series reduces confusion with background vegetation — producing the first plastic mulch map for Latin America.
Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation data
AI summary Read the abstract
This study developed a machine learning classifier using free Copernicus Sentinel-1 and Sentinel-2 satellite data to detect waste plastics in both marine and terrestrial environments. A training dataset was manually digitized covering land cover classes including greenhouses, general plastic waste, tires, and waste sites, and the classifier combined an artificial neural network with a post-processing decision tree. Validation across five locations demonstrated high accuracy, showing the potential for large-scale, low-cost plastic waste mapping using open satellite data.
Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation data
AI summary Read the abstract
Researchers used free Copernicus Earth observation satellite data and machine learning to detect waste plastic in marine and terrestrial environments at a large scale. The classifier was trained on Sentinel-1 and Sentinel-2 data and performed well for detecting larger plastic accumulations. Satellite-based detection could enable continuous, wide-area monitoring of plastic pollution at a fraction of the cost of ground surveys.
Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation Data
AI summary Read the abstract
Researchers developed a machine learning classifier using free Copernicus satellite data to detect plastic waste — including greenhouses, tyres, and waste sites — in both aquatic and terrestrial environments, achieving high accuracy and enabling low-cost large-scale plastic pollution mapping.
Time Series approach to map areas of Agricultural Plastic Waste generation
AI summary Read the abstract
Researchers applied a time-series remote sensing approach to map the spatial distribution of agricultural plastic waste generation across extensive agricultural landscapes, using satellite imagery to detect plastic-mulched farmlands and other agri-plastics to address the lack of comprehensive plasticulture data needed for effective waste management and land-use policy.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.