Sentinel-2 Recognition of Uncovered and Plastic Covered Agricultural Soil

Abstract

Medium resolution satellite data, such as Sentinel-2 of the Copernicus programme, offer great new opportunities for the agricultural sector, and provide insights on soil surface characteristics and their management. Soil monitoring requires a high-quality dataset of uncovered and plastic covered agricultural soil. We developed a methodology to identify uncovered soil pixels in agricultural parcels during seedbed preparation and considered the impacts of clouds and shadows, vegetation cover, and artificial covers, such as those of greenhouses and plastic mulch films. We preserved the spatial and temporal integrity of parcels in the process and analysed spectral anomalies and their sources. The approach is based on freely available tools, namely Google Earth Engine and R Programming packages. We tested the methodology on the northern region of Belgium, which is characterised by small, fragmented parcels. We selected a period between mid-April to end-May, when active agricultural management practices leave the soil bare in preparation for the main cropping season. The spectral angle mapper was used to identify soil covered by non-plastic greenhouses or temporary soil covers, such as plastic mulch films. The effect of underlying soil on temporary covers was considered. The retrogressive plastic greenhouse index was used for detecting plastic greenhouses. The result was a high quality dataset of potential bare uncovered agricultural soil that allows further soil surface characterisation. This offered an improved understanding of the use of artificial covers, their spatial distribution, and their corresponding crops during the considered period. Artificial covers occurred most frequently in maize parcels. The approach resulted in precision values exceeding 0.9 for the detection of temporary covers and non-plastic greenhouses and a sensitivity value exceeding 0.95 for non-plastic and plastic greenhouses.

Implementing a GIS-Based Digital Atlas of Agricultural Plastics to Reduce Their Environmental Footprint; Part I: A Deductive Approach

“…This not-high value is due both to the resolution of the satellite images (as it does not allow identification of some very small plots) and to the fact that the application of the RPGI index is not a real supervised classification of the territory, so it only provides a rough indication of the presence of plastics and needs further investigation to improve its exclusive usability. As reported by Ibrahim et al [30], the RPGI index is less sensitive than other classification methodologies because it is related to the type of crop, and if the plastic greenhouses are painted or not during their use. Moreover, greenhouse plastics have high correspondences to bare soil spectra, but still allow a preliminary detection of APSs [30].…”

“…As reported by Ibrahim et al [30], the RPGI index is less sensitive than other classification methodologies because it is related to the type of crop, and if the plastic greenhouses are painted or not during their use. Moreover, greenhouse plastics have high correspondences to bare soil spectra, but still allow a preliminary detection of APSs [30]. In addition, a 5% incidence of classification errors emerged.…”

“…Given its versatility thanks to high revisit time, spectral, and spatial resolution, and free availability of images [28], the Sentinel-2 mission can be also widely used for APS detection. For example, there are several works showing the efficiency of using these images for the detection of plastics in agriculture based on different techniques and indices [29,30]. In this work, only the B2, B3, B4, and B8 bands of the Sentinel-2A satellite were used.…”

“…The final result was combined in a single remote-sensed dataset The RPGI index provides a good detection of greenhouse plastic covers after having identified graphically the most functional threshold. This index is widely used, although limitations do not allow exclusive use [30,34]. Indeed, it provides very low or negative values when the greenhouses are colored white during the summer.…”

Remote sensing of plastic‐covered greenhouses and plastic‐mulched farmlands: Current trends and future perspectives

“…In addition to the spectral characteristics of the data used, spectral characteristics of PCGs also influence the accuracy of their mapping. For example, different plastic materials are currently used for PCGs and plastic mulching in horticulture and mapping accuracy of these materials from space using optical data depends on the spectral properties of materials used in building polymers (Ibrahim & Gobin, 2021) as well as the growth cycle of plants within the plasticulture (Yang et al, 2017).…”