A dataset of remote sensing observations of agricultural plastic film-covered farmland in Da’an City (2015–2023)

Plastic film mulching has been widely applied in conservation agriculture, and remote sensing provides an effective tool for monitoring the spatiotemporal dynamics of mulched farmland. However, in regions with complex natural conditions and a high risk of soil salinization, targeted datasets describing the spatial distribution and temporal variation of plastic-mulched farmland remain limited. Da’an City, located in the western part of the Songnen Plain, is characterized by low-lying terrain, pronounced salt accumulation, and poor soil fertility, making it a highly representative study area. In this study, the spatiotemporal distribution of plastic-mulched farmland in Da’an City from 2015 to 2023 was mapped and its temporal variation trends were analyzed. A Normalized Agricultural Film Index (NAFI) based on multi-temporal remote sensing data was proposed and applied to Landsat 8 OLI and Sentinel-2 MSI imagery acquired in April and May using the Google Earth Engine (GEE) platform. Spectral features and index-based features were extracted through GEE, and five feature combination schemes were designed. The optimal feature combination was selected based on classification accuracy and performance metrics. Using the optimal feature scheme, a random forest algorithm was employed to identify plastic-mulched farmland, resulting in a raster dataset representing the spatiotemporal distribution in Da’an City from 2015 to 2023. The overall classification accuracy of the random forest model ranged from 92.04% to 99.27%, with Kappa coefficients between 0.87 and 0.98. This dataset can serve as a valuable reference for regional-scale remote sensing identification and spatiotemporal analysis of plastic-mulched farmland.