Access to accurate and timely soil moisture information is critical for effective water resource management, ensuring food security, and advancing climate modeling; however, such information is often limited. We propose a novel transferable Fourier Neural Operator (FNO) framework designed to estimate subsurface soil moisture utilizing surface‐level data (5 cm). This framework demonstrates robust generalization capabilities for soil moisture estimates for deeper soil layers, wherein prediction tasks are inherently more complex. The model has been trained on high‐resolution temporal data from six distinct sites encompassing both arid and humid subtropical regions, as well as various soil types. It reliably predicts soil moisture at depths of 15 and 50 cm. By leveraging transfer learning, pre‐training, and fine‐tuning with only 5% of the target domain data, we achieved improved accuracy and stability. This innovative framework provides a scalable and data‐efficient solution for delivering subsurface soil moisture data to users with constrained data sets.
The rapid human-driven depletion of groundwater resources across the Indian subcontinent poses a critical threat to long-term water and food security. The Northwestern Indo-Gangetic Alluvial Plain (NIGAP) is experiencing persistent groundwater depletion due to the combined effects of intensive agricultural and industrial demands. This region, situated on the seismically active Himalayan Foreland Basin, relies heavily on its vast Quaternary alluvial aquifer system. In this study, we integrate multiple geodetic approaches to quantify the secular mass loss in this water-stressed region and partition it into changes in total water and groundwater storage (TWS and GWS).We analyze time series of TWS changes observed at 300-400 km spatial resolution by the Gravity Recovery and Climate Experiment (GRACE/GRACE-FO) missions from 2002 to 2024. These basin-scale mass estimates are compared with hydrological mass change signals inferred from high-resolution vertical land motion (VLM) derived from Interferometric Synthetic Aperture Radar (InSAR), complemented by continuous Global Positioning System (GPS) measurements. The vertical deformation field derived from InSAR and GPS data across NIGAP reveals aquifer compaction driven by pore pressure decline, enabling the quantification of GWS loss through poroelastic compaction models. However, regions outside the aquifer system exhibit elastic uplift of the Earth’s crust in response to reductions in TWS at and beneath the surface. To convert this elastic response into an equivalent TWS change, we implement an inverse elastic half-space model that incorporates observed surface deformation, along with the known elastic and hydrogeological properties of the study area.Keywords: Groundwater Depletion, Geodetic Measurements, Elastic Half-Space, Indo-Gangetic Plain.