Tag
PhyRestore introduces a physics-structured framework for restoring corrupted physical factors in soil-loss estimation, improving the recovery of temporal changes through known physical relationships.
This paper proposes the Knowledge-enhanced Agriculture-informed Neural Network (KAINN) framework, which integrates domain knowledge into deep learning models to improve the accuracy and interpretability of nitrous oxide emissions predictions in agricultural systems.
This paper proposes MVG-KAN, a multi-view model integrating periodic-residual decomposition, a Geo-Wind Graph for wind-aware spatial dependencies, and a temporal KAN head for PM2.5 forecasting, achieving MAE 14.09 on Beijing data.