AI-Based Profile Soil Moisture


Soil moisture profile for a year at a forest site in Germany (Werban et al., UFZ) with vertical coverages of an L-band remote sensor and a cosmic-ray neutron sensor. The wilting point is deceeded depending on the vertical coverage of the sensors.

Recent soil moisture products have not yet targeted profile soil moisture estimates derived from cosmic-ray neutron sensors (CRNS) despite their unique footprint. CRNS have a capability to integrate measurements over a volume of ~300 m in radius and ~30 cm in depth, surpassing other in-situ techniques. This extraordinary coverage presents a distinct advantage for gauging plant water availability, which provides valuable information for managing water resources, particularly in farming and land-use planning. To extend the sensor’s benefits from station to raster scale, the combination of high-resolution remote sensing data with artificial intelligence models is being pursued. This can offer significant advantages in improving the vertical accuracy of satellite-based soil moisture products.

Related literature

Schrön, Martin, et al. "Improving calibration and validation of cosmic-ray neutron sensors in the light of spatial sensitivity." Hydrology and Earth System Sciences 21.10 (2017): 5009–5030. → Vertically weighting point-based in-situ soil moisture data

Wagner, Wolfgang, Guido Lemoine, and Helmut Rott. "A method for estimating soil moisture from ERS scatterometer and soil data." Remote sensing of environment 70.2 (1999): 191–207. → Exponentially filtering surface soil moisture data

Zreda, Marek, et al. "Measuring soil moisture content non‐invasively at intermediate spatial scale using cosmic‐ray neutrons." Geophysical research letters 35.21 (2008). → Introduction to using CRNS in environmental sciences

Share



Follow this website


You need to create an Owlstown account to follow this website.


Sign up

Already an Owlstown member?

Log in