Artificial Intelligence (AI) weather prediction (AIWP) models often produce "blurry" precipitation forecasts that overestimate drizzle and underestimate extremes. This study provides a novel solution to tackle this problem -- integrating terrain-following coordinates with global mass and energy conservation schemes into AIWP models. Forecast experiments are conducted to evaluate the effectiveness of this solution using FuXi, an example AIWP model, adapted to 1.0-degree grid spacing data. Verification results show large performance gains. The conservation schemes are found to reduce drizzle bias, whereas using terrain-following coordinates improves the estimation of extreme events and precipitation intensity spectra. Furthermore, a case study reveals that terrain-following coordinates capture near-surface winds better over mountains, offering AIWP models more accurate information on understanding the dynamics of precipitation processes. The proposed solution of this study can benefit a wide range of AIWP models and bring insights into how atmospheric domain knowledge can support the development of AIWP models.

翻译：人工智能（AI）天气预报（AIWP）模型常产生“模糊”的降水预报，即高估毛毛雨而低估极端降水。本研究提出一种解决该问题的新方案——将地形跟随坐标与全球质量和能量守恒方案集成到AIWP模型中。通过预报实验评估该方案的有效性，实验使用示例AIWP模型FuXi，并适配至1.0度网格间距数据。验证结果表明性能显著提升。研究发现，守恒方案减少了毛毛雨偏差，而使用地形跟随坐标则改善了极端事件和降水强度谱的估计。此外，案例研究表明，地形跟随坐标能更好地捕捉山区近地表风场，为AIWP模型提供了更准确的信息以理解降水过程的动力学机制。本研究提出的方案可广泛应用于各类AIWP模型，并为大气领域知识如何支持AIWP模型的发展提供了新的见解。