We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
National-scale mapping of plastic-mulched farmlands in China based on deep semantic segmentation and Sentinel-2 imagery
AI summary Read the abstract
Scientists used AI and satellite images to create the first detailed map of where China uses plastic sheeting (called "mulch film") to help crops grow — covering about 6 million hectares of farmland, mostly in the drier western regions. This matters because these plastic films break down into microplastics that build up in soil over time, potentially entering the food we eat and the water we drink, so knowing exactly where this farming practice is most concentrated helps target cleanup and pollution-reduction efforts where they're needed most.
Plastic mulching films are widely utilized in agriculture around the globe to increase soil temperature, retain soil moisture, and prevent pests. However, its large-scale and long-term application causes several environmental issues, including soil microplastic accumulation and “white pollution”. Therefore, obtaining reliable spatial distribution data on plastic-mulched farmlands (PMFs) is essential, particularly at a large scale. This study aimed to provide the first national-scale PMFs map of China with a high resolution of 10 m. Specifically, this study proposed a hybrid framework for PMFs mapping, which employed the Vision Mamba UNet (VM-UNet) semantic segmentation model for both updating weak labels and national-scale PMFs mapping. First, a web crawler was used to gather news and academic literature related to China's PMFs, extracting temporal and spatial distribution data on plastic mulch films. Afterwards, a national 1° grid system was established for data organization, where initial weak labels were generated via Google Earth Engine and Sentinel-2 imagery. These labels were subsequently refined through an active learning strategy within a transfer learning framework. Finally, VM-UNet was adopted for the national-scale prediction of China's plastic-mulched farmland. Experimental results demonstrate that China-PMF-10 dataset achieved a user's and producer's accuracies of 85.90 ± 1.25% and 78.48 ± 5.37% for PMFs, respectively. China's total PMFs area in 2020 was estimated at approximately 6.06 ± 0.42 Mha (95% CI). Furthermore, statistical significance testing confirmed that the Hu Line emerged as a critical boundary, with more extensive PMFs and higher PMFs-to-cropland ratios to its west. This study provides a scientific basis for sustainable agricultural management and plastic pollution mitigation in China, and offers methodological insights for large-scale PMFs monitoring in other regions.
More Papers Like This
New Workflow of Plastic-Mulched Farmland Mapping using Multi-Temporal Sentinel-2 data
AI summary Read the abstract
Researchers used multi-temporal satellite imagery to map plastic-mulched farmland in China, providing a tool for monitoring the environmental risk of agricultural plastic use. Plastic mulch is a significant source of microplastic contamination in agricultural soils when film residues break down over time.
Large Scale Agricultural Plastic Mulch Detecting and Monitoring with Multi-Source Remote Sensing Data: A Case Study in Xinjiang, China
AI summary Read the abstract
Satellite imagery was used to monitor plastic mulch film coverage across large agricultural areas in China, mapping both spatial extent and temporal changes. Accurately tracking plastic mulch use is important because agricultural film residues are a major source of microplastic contamination in farmland soils.
An explainable machine learning model for accurate estimation of residual phthalate esters in Chinese agricultural soils
AI summary Read the abstract
Scientists used AI to create the first detailed map showing where harmful chemicals called phthalates (found in plastics and linked to hormone disruption) are building up in China's farmland soils, and leftover plastic film from farming turned out to be a major hidden source. This matters because these chemicals can end up in the food we eat, and the new mapping tool is far more accurate than older methods, helping identify high-risk farming regions so cleanup efforts can target them directly.
Remote estimation of plastic distribution in California agriculture using Sentinel-2 imagery: a case study
AI summary Read the abstract
Researchers used satellite images and ground-based light measurements to detect plastic mulch films used in California farm fields. Their computer classification method distinguished plastic from soil and crops with over 98% accuracy, and tracked plastic coverage across a farming region from 2023 to 2025 without needing prior knowledge of individual field practices.
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.