Xinggao Liu

Domain-Informed Graph Neural Networks for Climate Factor Forecasting to Support Sustainable Crop Management

Inspired by agronomic knowledge, DoIGNN is proposed, a Domain-Informed Graph Neural Network that injects a domain-structured graph constraint built from Agro-Climatic Homogeneous Zones (ACHZs) that improves forecasting accuracy over strong baselines while yielding more interpretable spatial dependency patterns that sup...