Farm-scale mapping of compost and digestate spreadings from Sentinel-2 and Sentinel-1

• Aim to simultaneously track both liquid and solid EOM from Sentinel-2 &-1. • Bootstrapping SVM over 3 periods and years on a farm scale. • Highly uncertain pixels covered < 10 % of the mapped area regardless of the year. • Best models showed accuracies higher than 93% for two years. • Need for thoroughly characterize the sequence of crop technical management. According to few recent studies, exogenous organic matters (EOM) can be detectable on either emerging vegetation or bare soil using optical and radar remote sensing techniques. Nevertheless, these image processing approaches considered one single EOM, one season and/or year only and were limited to one surface condition prior to spreading. So far no method addressed the simultaneously tracking of both liquid and solid EOM applications using satellite imagery, for different years, seasons and surface conditions. Relying on Support Vector Machine (SVM) classifier, this study aimed to track applications of both composted manure and liquid digestate over three seasons of successive years (late winter of 2019; spring of 2020 and 2021) in agricultural fields on a farm scale with distinct surface conditions (grassland, winter crop, bare soil). Within-field reference areas were delineated based on both the observed amendment practices, crops and soil map and randomly selected with replacement to train/ validate SVM with several iterations. Various feature sets composed of bands, signals and specific spectral indices from either Sentinel-2 and/or Sentinel-1 data served to compute SVM in a bootstrapping approach in order to produce a series of map results, to assess the final mode class and the uncertainty of map results. Classification performance was higher for pre- and post-application image pairs compared to post-application images alone and slightly improved when adding Sentinel-1 data. While the areal percentage of the highest uncertainty class covered less of 10% of the mapped area regardless of the year, the best models showed accuracies higher than 93% in 2020 and 2021. In 2019, the overall accuracy did not reach more than 79%, probably due to rainfall events and considerable time lags between the image pairs. This study underscores, not only the potential of Sentinel-2 and 1 for monitoring EOM applications, but also the requirement of better understanding the spectral behaviour of the EOM spreadings, in line with a thorough characterization of the sequence of crop technical management.