Explainable AI-Based Interface System for Weather Forecasting Model
This paper addresses the low decision utility and weak user trust arising from insufficient interpretability of black-box AI models in meteorological forecasting. To bridge this gap, we propose the first user-driven eXplainable AI (XAI) requirements framework tailored to meteorological decision-making. Through qualitative interviews with forecasters, we identify three core requirements: (1) detection of model performance bias in precipitation forecasting, (2) visualization of model reasoning processes, and (3) explicit expression of output confidence. Integrating SHAP, LIME, and confidence interval estimation, we develop an interactive XAI interface system. A/B testing and user studies demonstrate that intuitive, human-centered explanations significantly outperform algorithmic ones—improving forecasters’ decision accuracy by 12.3% and system trust by 27.6%. Our work establishes a reusable XAI design paradigm for meteorology, shifting the focus of explainability from technical correctness toward decision-oriented practicality.