Short project description

Soil moisture is crucial in regulating agricultural productivity and greenhouse gas emissions from croplands. Understanding its spatial and temporal variations in croplands is essential for optimizing water resources management. However, obtaining accurate and high-resolution soil moisture data remains a challenge due to the limitations of traditional point-scale measurements.

This master thesis project is a part of the SMART FIELD project (https://land-craft.dk/research/publications/projects-we-are-participating-in/smartfield) and the Digital Twin for Climate Smart Agriculture project (https://villumfonden.dk/en/projekt/digital-twin-climate-smart-agriculture-unraveling-environment-and-management-effects-field). We will use the cosmic-ray neutron sensor (CRNS) to acquire soil moisture at high spatial resolution for croplands in Denmark. Furthermore, we will develop a machine-learning method for soil moisture estimation by using multi-source remote sensing data. Ultimately, this project will provide a novel approach for high-resolution soil moisture mapping in croplands, improving our understanding of soil moisture dynamics and supporting precision agriculture management.