气象人工智能预报模型上新升级——五大模型分工协作赋能千行百业 □ 本报记者 郭静原 在全球变暖背景下，气候形势日趋复杂多变，高温、暴雨、强对流等灾害的突发性与破坏性显著增 强，既对气象预报预警的精准度、时效性提出更高要求，也推动气象服务加速向智能化转型。日前，中 国气象局发布新的气象人工智能科学模型"风源"，并实现"风清""风雷""风顺"3款气象人工智能预报模 型的同步升级。加上前不久刚刚发布面向气象服务领域的千亿参数语言模型"风和"，5大模型分工协 作，正以更贴心的气象预报预警能力，加速赋能千行百业高质量发展。 提升精准度 近年来，极端天气气候事件频发，"报得快""报得准"的需求和难度也随之增加。中国气象局党组书 记、局长陈振林指出，人工智能技术以其高效的计算和多源数据融合能力，正成为连接气象预报、灾害 预警和应急响应的关键纽带，是突破传统预报局限的"金钥匙"。 聚焦雷暴、短时强降水等灾害性天气的临灾预警，"风雷"模型的表现尤为亮眼。其回波预报产品可 在几分钟内预测对流系统的新生与消散，强回波预报质量提升超过25%。 国家气象中心风雷敏捷攻关团队负责人张小雯介绍，升级推出的"风雷"定量降水预报模型，已在多 ...

Core Viewpoint - The article discusses the advancements in artificial intelligence (AI) models for meteorological services in China, highlighting the launch of new AI models that enhance weather forecasting and disaster warning capabilities in response to increasingly complex climate conditions. Group 1: AI Model Developments - The China Meteorological Administration (CMA) has released the AI model "Fengyuan" and upgraded three other models: "Fengqing," "Fenglei," and "Fengshun," to improve weather forecasting and warning capabilities [1][2] - The newly launched "Fenghe" model, with a trillion parameters, collaborates with the other models to provide personalized weather services across various sectors [1][2] Group 2: Applications and Services - AI is deeply integrated into meteorological services, providing personalized travel and health guidance, and supporting decision-making in agriculture, energy, and transportation [2] - The "Fenghe" model can offer tailored solutions based on intelligent analysis, covering multiple scenarios related to weather [2] Group 3: Precision and Efficiency - The upgraded "Fengshun" model focuses on key agricultural and energy needs, adding over ten critical meteorological factors to enhance service precision [3] - The "Fenglei" model has shown a 25% improvement in the quality of severe weather predictions, demonstrating its effectiveness in real-time disaster warnings [4] Group 4: Future Directions - The CMA's strategy for 2025-2035 emphasizes the integration of numerical forecasting with AI to enhance simulation and prediction capabilities of Earth's systems [7] - The AI models are expected to significantly improve forecasting accuracy and computational efficiency, with the "Fengqing" model capable of generating 15-day global weather forecasts in just three minutes [7]

以往提到天气，人们往往会说"变幻莫测"。而现在，在人工智能助力下，天气渐渐"变幻可测"。 人工智能技术与数值模式、超强算力协同发力，再加上预报员的专业经验，就能提前"算"出风雨雷电的 信号。速度更快、效率更高的气象预报，将加快赋能千行百业，助力经济社会高质量发展。 "目前，风雷技术的先进性及业务化应用程度表明，我国的短临预报业务在人工智能方面处于世界先进 水平。"盛杰介绍。 风清模型是全自主知识产权的人工智能全球短中期预报系统。国家气象中心天气预报技术研发室主任、 雄安气象人工智能创新研究院副院长曹勇介绍，风清模型可精准捕捉台风、暴雨等灾害天气，输出13层 高空要素与11类地面要素预报。目前，风清已实现业务化部署并向全国推广，广泛应用于防灾减灾、光 伏风电调度、航空保障等场景。 除了风雷、风清、风顺、风和，国家卫星气象中心（国家空间天气监测预警中心）还牵头研发了人工智 能风宇模型，这是空间天气链式人工智能预报模型。目前，该模型已应用于卫星通信导航、航天器轨道 管理、电力设施防护及航空安全等领域。 "人工智能+气象"新应用新场景涌现 每年5月，南海夏季风暴发拉开我国主汛期大幕，推动着我国主雨带进程。对南海夏季风 ...