January 2025
-
Montzka et al. (2025) AI in soil moisture remote sensing
This paper provides the first structured overview of artificial intelligence (AI) applications for soil moisture retrieval from remote sensing data. It highlights how AI overcomes the limitations of traditional physical models by learning complex non-linear relationships and improving data continuity and resolution.
-
Moucha et al. (2025) Projection of irrigation water requirement in the south Mediterranean area using an explicit representation of irrigation processes into a land surface model: Case of the Tensift catchment (Morocco)
This study evaluates a new irrigation module in the ISBA land surface model using data from the semi-arid Tensift catchment (Morocco) and projects future agricultural water requirements, finding that water use could nearly double by 2050, primarily driven by land use change (conversion to water-intensive tree crops) rather than climate change alone.
-
Collignan et al. (2025) Identifying and Quantifying the Impact of Climatic and Non‐Climatic Drivers on River Discharge in Europe
This study proposes a novel methodology utilizing a common parsimonious modeling framework to decompose observed river discharge trends into components driven by climate change and those driven by non-climatic (human) factors across Europe, concluding that non-climatic factors dominate discharge changes, particularly in Southern Europe.
-
He et al. (2025) SMPD-MERG: A Hybrid Downscaling Model for High-Resolution Daily Precipitation Estimation via Merging Surface Soil Moisture and Multisource Precipitation Data
The study introduces SMPD-MERG, a novel hybrid downscaling model designed to merge surface soil moisture data with multisource precipitation products to generate high-resolution, accurate daily precipitation estimates.
-
Lamichhane et al. (2025) Multi‐layer root zone soil moisture estimation using field and remote sensing data fusion with machine learning in semi‐arid croplands
This study developed an Extreme Gradient Boosting model integrating PlanetScope optical data, climate variables, and soil properties to estimate multi-layer soil moisture (SM) down to 1.8 m at 3 m spatial resolution, achieving high accuracy ($R^2$ up to 0.89) and demonstrating that incorporating SM from the adjacent upper layer significantly improves deep SM prediction.