FDNet: A Deep Learning Approach with Two Parallel Cross Encoding Pathways for Precipitation Nowcasting
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；School of Mathematical Sciences, Peking University（北京大学数学科学学院）；Guiyang Academy of Information Technology（贵阳信息技术研究院）；NTT DATA Corporation（NTT DATA株式会社）；NTT DATA Institute of Management Consulting Inc.（NTT DATA经营研究所）
Bi-Ying Yan, Chao Yang, Feng Chen, Kohei Takeda, Changjun Wang
With the goal of predicting the future rainfall intensity in a local region over a relatively short period time, precipitation nowcasting has been a long-time scientific challenge with great social and economic impact. The radar echo extrapolation approaches for precipitation nowcasting take radar echo images as input, aiming to generate future radar echo images by learning from the historical images. To effectively handle complex and high non-stationary evolution of radar echoes, we propose to decompose the movement into optical flow field motion and morphologic deformation. Following this idea, we introduce Flow-Deformation Network (FDNet), a neural network that models flow and deformation in two parallel cross pathways. The flow encoder captures the optical flow field motion between consecutive images and the deformation encoder distinguishes the change of shape from the translational motion of radar echoes. We evaluate the proposed network architecture on two real-world radar echo datasets. Our model achieves state-of-the-art prediction results compared with recent approaches. To the best of our knowledge, this is the first network architecture with flow and deformation separation to model the evolution of radar echoes for precipitation nowcasting. We believe that the general idea of this work could not only inspire much more effective approaches but also be applied to other similar spatiotemporal prediction tasks
Institut de Recherche Technologique Saint-Exupéry（圣埃克苏佩里技术研究院）；Institut de Recherche en Informatique de Toulouse（图卢兹计算机科学研究院）；Météo-France（法国气象局）；Centre Européen de Recherche et de Formation Avancée en Calcul Scientifique（欧洲科学计算高级研究与培训中心）；Climate, Environment, Coupling and Uncertainties（气候、环境、耦合与不确定性研究所）
Stable Attention Response for Reliable Precipitation Nowcasting
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；School of Life and Environmental Science, The University of Sydney（悉尼大学生命与环境科学学院）；School of Computer Science and Information Technology, The University of Adelaide（阿德莱德大学计算机科学与信息技术学院）；Digital Agriculture, Orange Agricultural Institute（数字农业，橙色农业研究所）；School of Science, Edith Cowan University（埃迪斯科文大学科学学院）
Exploring Geometric Deep Learning For Precipitation Nowcasting
Technical University of Munich (TUM)（慕尼黑工业大学）；Potsdam Institute for Climate Impact Research（波茨坦气候影响研究所）；Indian Institute of Technology Delhi（印度理工学院德里分校）
FusionCast: Enhancing Precipitation Nowcasting with Asymmetric Cross-Modal Fusion and Future Radar Priors
School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；School of Earth and Space Science and Technology, Wuhan University（武汉大学地球和空间科学与技术学院）
QWRF-Net: A Quantum-Wavelet Framework with Rectified Flow for Short-Term Precipitation Nowcasting
School of Computer Science and Technology (School of Artificial Intelligence), Yibin University（宜宾大学计算机科学与技术学院（人工智能学院））；College of Computer Science and Engineering, Chongqing University of Technology（重庆理工大学计算机科学与工程学院）
RainBalance: Alleviating Dual Imbalance in GNSS-based Precipitation Nowcasting via Continuous Probability Modeling
Sanya Science and Education Innovation Park, Wuhan University of Technology（武汉理工大学三亚科技创新园）；Wuhan University of Technology（武汉理工大学）；School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；School of Earth and Space Science and Technology, Wuhan University（武汉大学地球空间科学与技术学院）；Wuhan University（武汉大学）；School of Water Resources and Hydropower Engineering, Wuhan University（武汉大学水利水电工程学院）；GNSS Research Center, Wuhan University（武汉大学GNSS研究中心）
DYffCast: Regional Precipitation Nowcasting Using IMERG Satellite Data. A case study over South America
Imperial College London（帝国理工学院）；Data Science Institute, Imperial College London（帝国理工学院数据科学研究所）；University of California San Diego（加利福尼亚大学圣迭戈分校）；Grantham Institute for Climate Change and the Environment（格兰瑟姆气候与环境研究所）；National Center for Artificial Intelligence CENIA, Chile（智利国家人工智能中心）
Laboratory of Intelligent Collaborative Computing, University of Electronic Science（智能协同计算实验室，电子科学科技大学）；School of Computer Science（计算机科学学院）；Technology (School of Artificial Intelligence), Yibin University（技术（人工智能学院），宜宾大学）；College of Humanities（人文学院）；General Education, Chengdu Textile College（通识教育，成都纺织学院）
How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcasting
Sanya Science and Education Innovation Park, Wuhan University of Technology（武汉理工大学三亚科技创新园）；Wuhan University of Technology（武汉理工大学）；School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；Interdisciplinary Artificial Intelligence Research Institute, Wuhan College（武汉学院交叉人工智能研究院）；Shanghai Artificial Intelligence Laboratory, Shanghai（上海人工智能实验室）；School of Earth and Space Science and Technology, Wuhan University（武汉大学地球空间科学与技术学院）；School of Water Resources and Hydropower Engineering, Wuhan University（武汉大学水利水电学院）；GNSS Research Center, Wuhan University（武汉大学GNSS研究中心）
McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting
School of Computer Science, The University of Sydney, Australia（悉尼大学计算机科学学院，澳大利亚）；School of Life and Environmental Science, The University of Sydney, Australia（悉尼大学生命与环境科学学院，澳大利亚）
Skillful Precipitation Nowcasting using Deep Generative Models of Radar
Met Office（英国气象局）
降水临近预报，即提前两小时对降水进行高分辨率预报，支持许多依赖天气决策的部门的现实社会经济需求。国家的最先进的业务临近预报方法通常平流降水场与雷达为基础的风估计，并努力捕捉重要的非线性事件，如对流启动。最近引入的深度学习方法使用雷达直接预测未来的降雨率，不受物理限制。虽然它们准确地预测了低强度降雨，但它们的业务效用有限，因为它们缺乏约束，在较长的提前时间内产生模糊的临近预报，在更罕见的中到大雨事件中表现不佳。为了解决这些挑战，我们提出了一个深生成模型的概率临近预报雷达降水。我们的模型在长达1536 km x 1280 km的区域内产生现实和时空一致的预测，提前5 - 90分钟。在英国气象局50多位专家预测员的系统评估中，我们的生成模型在88%的情况下与两种竞争性方法相比，其准确性和实用性排名第一，证明了其决策价值和为现实世界专家提供物理见解的能力。当定量验证时，这些临近预报是熟练的，而不是诉诸模糊。我们表明，生成式临近预报可以提供概率预测，提高预测值和支持业务效用，并在决议和交货期的替代方法的斗争。
Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar Observations and Foundation Model Priors
1 Key Laboratory of Big Data \& Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, China；2 CMA Key Laboratory of Transportation Meteorology, Nanjing Innovation Institute for Atmospheric Sciences, Nanjing, China
SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization
University of Science and Technology of China（中国科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Chinese University of Hong Kong（香港中文大学）
