Soil nitrogen forecasting from environmental variables provided by multisensor remote sensing images

TL;DR

This paper presents a machine learning framework using multisensor remote sensing data to accurately forecast soil nitrogen levels across different land cover types, enhancing environmental monitoring and agricultural management.

Contribution

It introduces a novel integration of multi-sensor remote sensing data with machine learning models, especially CatBoost, for soil nitrogen prediction across diverse land covers.

Findings

CatBoost outperforms other models in accuracy

Robustness across croplands and grasslands demonstrated

Integration of multisensor data improves prediction quality

Abstract

This study introduces a framework for forecasting soil nitrogen content, leveraging multi-modal data, including multi-sensor remote sensing images and advanced machine learning methods. We integrate the Land Use/Land Cover Area Frame Survey (LUCAS) database, which covers European and UK territory, with environmental variables from satellite sensors to create a dataset of novel features. We further test a broad range of machine learning algorithms, focusing on tree-based models such as CatBoost, LightGBM, and XGBoost. We test the proposed methods with a variety of land cover classes, including croplands and grasslands to ensure the robustness of this approach. Our results demonstrate that the CatBoost model surpasses other methods in accuracy. This research advances the field of agricultural management and environmental monitoring and demonstrates the significant potential of integrating multisensor remote sensing data with machine learning for environmental analysis.