Physics-aware sampling critical points

The file contains code for physics-aware sampling.

If you are using this code, then do refer/cite the following papers;

1. Singh, A., Singh, V., & Gaurav, K. (2025a). Leveraging neural operator and sliding window technique for enhanced subsurface soil moisture imputation under diverse precipitation scenarios. Journal of Geophysical Research: Machine Learning and Computation, 2 (3), e2025JH000730.474
2. Singh, A., Singh, V., & Gaurav, K. (2025b). Physics-aware probabilistic modeling of subsurface soil moisture using diffusion processes across different climate settings. Geophysical Research Letters, 52 (20), e2025GL118607.
3. Singh, A., Singh, V., & Gaurav, K. (2026). Weak physics-guided multi-agent learning for surface to subsurface moisture estimation across diverse climate and soil conditions. Journal of Geophysical Research: Machine Learning and Computation, 3 (1), e2025JH001039.480
4. Singh, V., Singh, A., & Gaurav, K. (2026). How Important Are the Critical Points in Selecting the Optimal Samples for Accurate Estimation of Subsurface Soil Moisture?. Geophysical Research Letters, 53(15), e2026GL124661.
5. Singh, A., Ravikumar, M., Singh, V., More, S., Tiwari, V. M., & Gaurav, K. (2026). Transferable neural operators to estimate subsurface soil moisture. Journal of Geophysical Research: Machine Learning and Computation, 3(4), e2026JH001322.