Evaluation of multispectral data for recent manure application: A case study in northern Spain

Abstract

The use of manure in agricultural fields during the wet season can lead to environmental pollution by releasing nitrates into nearby water sources. To address this issue, authorities may impose closed periods during which manure application is prohibited. However, ensuring compliance with these regulations can be challenging, as it is difficult to monitor all fields in a country. To tackle this problem, a solution has been proposed that involves employing machine learning techniques in conjunction with satellite imagery to automatically identify freshly manured fields. This paper investigates the relationship and effectiveness of the Sentinel-2 satellite bands and 51 frequently utilized multispectral indices in the context of precision agriculture, by exploring different feature selection methods. The proposed method achieves nearly 90% F1-Score and detects all test plots of the northern Spanish region, showing its potential for large-scale use in precision agriculture and environmental monitoring. This method incorporates temporal data, resulting in an 8% improvement in the detection F1-Score. Despite their lower spatial resolution, infrared bands have proven to be more effective than visible bands, enhancing the F1-Score by 4%. Furthermore, the use of over 80 features contributes to a 12% increase in the F1-Score compared to using fewer than 10 features. For further research and future studies, a dataset of recently manured plots, verified on-site, has been developed and made publicly available.