Data-driven rainfall prediction at a regional scale: a case study with Ghana
Faculty of Computing and Data Sciences, Boston University, Boston, USA(计算机与数据科学学院,波士顿大学,波士顿,美国);Department of Mathematics and Statistics, Boston University, Boston, USA(数学与统计学系,波士顿大学,波士顿,美国)
With a warming planet, tropical regions are expected to experience the brunt of climate change, with more intense and more volatile rainfall events. Currently, state-of-the-art numerical weather prediction (NWP) models are known to struggle to produce skillful rainfall forecasts in tropical regions of Africa. There is thus a pressing need for improved rainfall forecasting in these regions. Over the last decade or so, the increased availability of large-scale meteorological datasets and the development of powerful machine learning models have opened up new opportunities for data-driven weather forecasting. Focusing on Ghana in this study, we use these tools to develop two U-Net convolutional neural network (CNN) models, to predict 24h rainfall at 12h and 30h lead-time. The models were trained using data from the ERA5 reanalysis dataset, and the GPM-IMERG dataset. A special attention was paid to interpretability. We developed a novel statistical methodology that allowed us to probe the relative importance of the meteorological variables input in our model, offering useful insights into the factors that drive precipitation in the Ghana region. Empirically, we found that our 12h lead-time model has performances that match, and in some accounts are better than the 18h lead-time forecasts produced by the ECMWF (as available in the TIGGE dataset). We also found that combining our data-driven model with classical NWP further improves forecast accuracy.
Diffusion Precipitation Generation with Medium-range Weather Forecasting
Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学);The Hong Kong University of S & T(香港科技大学);Sun Yat-Sen University(中山大学);NSCC-SZ(国家超级计算深圳中心);China Meteorological Administration(中国气象局);GBA Weather Research Center(粤港澳大湾区天气研究中心);Huawei Technologies Co., Ltd(华为技术有限公司)
HRRRCast: a data-driven emulator for regional weather forecasting at convection allowing scales
Cooperative Institute for Research in Environmental Sciences(环境科学研究院);Cooperative Institute for Research in the Atmosphere(大气研究院);Cooperative Institute for Severe and High-Impact Weather Research and Operations(严重和高影响天气研究与运作研究院);NOAA Global Systems Laboratory(国家海洋和大气管理局全球系统实验室);NOAA Physical Sciences Laboratory(国家海洋和大气管理局物理科学实验室);NOAA National Severe Storms Laboratory(国家海洋和大气管理局严重风暴实验室)
Learning Regional Monsoon Patterns with a Multimodal Attention U-Net
1Computer Science \& Engineering, Indian Institute of Technology Roorkee, India 2Computer Science \& Engineering, Indian Institute of Technology Ropar, India 3 Computer Science \& Engineering, Indian Institute of Technology (BHU) Varanasi, India
Analysis of Rainfall Variability and Water Extent of Selected Hydropower Reservoir Using Google Earth Engine (GEE): A Case Study from Two Tropical Countries, Sri Lanka and Vietnam
International Water Management Institute(国际水资源管理研究所)
Differentiable, learnable, regionalized process-based models with physical outputs can approach state-of-the-art hydrologic prediction accuracy
The Pennsylvania State University(宾夕法尼亚州立大学)
整个水循环中水文变量的预测对于水资源管理以及下游应用(如生态系统和水质建模)具有重要价值。最近,纯数据驱动的深度学习模型(如长短期记忆(LSTM))在降雨径流和其他地球科学变量建模方面表现出似乎难以克服的性能,但它们无法预测未经训练的物理变量,并且仍然具有挑战性解释。在这里,我们展示了可微分、可学习、基于过程的模型(这里称为δ模型)可以接近LSTM的性能水平,用于区域化参数化的密集观测变量(流量)。我们使用一个简单的水文模型HBV作为骨干,并使用嵌入式神经网络,它只能在一个可微的编程框架中进行训练,以参数化,增强或替换基于过程的模型模块。在不使用集合或后处理器的情况下,δ模型可以为Daymet强迫数据集获得美国671个流域的中值Nash Sutcliffe效率为0.732,而具有相同设置的最先进的LSTM模型为0.748。对于另一个强迫数据集,差异甚至更小:0.715 vs. 0.722。同时,所得到的可学习的基于过程的模型可以输出一整套未经训练的变量,例如,土壤和地下水储存,积雪,蒸散和基流,后来受到他们的观察。模拟的蒸散量和基流排放量与其他估计值一致。通用框架可以处理具有各种过程复杂性的模型,并为从大数据中学习物理开辟了道路。
RainAtlas: A Multi-Continental Dataset for Precipitation Downscaling
IVADO;Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);connAIx Research School, Tübingen AI Center, University of Tübingen(蒂宾根大学connAIx研究学院,蒂宾根AI中心);Cluster of Excellence Machine Learning, University of Tübingen(蒂宾根大学机器学习卓越集群);Mila - Quebec AI Institute(Mila-魁北克人工智能研究所)
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)