A5080492884- Geographic Information Systems Studies
- Geological Modeling and Analysis
- Genetic and phenotypic traits in livestock
- Authorship Attribution and Profiling
- X-ray Diffraction in Crystallography
- 3D Modeling in Geospatial Applications
- Machine Learning in Materials Science
- Atmospheric and Environmental Gas Dynamics
- Computational and Text Analysis Methods
- Surface and Thin Film Phenomena
- Meteorological Phenomena and Simulations
California Institute of Technology
2022-2025
Land surface models (LSMs) play a pivotal role in Earth System Models by simulating energy, water, and carbon fluxes between the land atmosphere. However, existing LSMs face challenges with computational efficiency calibration of uncertain parameterizations, particularly for key water fluxes. To address these limitations, we introduce ClimaLand, GPU-native LSM designed to integrate machine learning (ML)  parameterizations frameworks physical models. ClimaLand's modular architecture...
In the field of Artificial Intelligence (AI) and Machine Learning (ML), a common objective is approximation unknown target functions y=f(x) using limited instances S=(x(i),y(i)), where x(i)∈D D represents domain interest. We refer to S as training set aim identify low-complexity mathematical model that can effectively approximate this function for new x. Consequently, model’s generalization ability evaluated on separate T={x(j)}⊂D, T≠S, frequently with T∩S=∅, assess its performance beyond...