{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-uncertainty-quantification-a-machine","title":"Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting","arxiv_id":"1812.09467","date":"2018-12-22","proceeding":null,"authors":["Bin Wang","Jie Lu","Zheng Yan","Huaishao Luo","Tianrui Li","Yu Zheng","Guangquan Zhang"],"abstract":"Weather forecasting is usually solved through numerical weather prediction\n(NWP), which can sometimes lead to unsatisfactory performance due to\ninappropriate setting of the initial states. In this paper, we design a\ndata-driven method augmented by an effective information fusion mechanism to\nlearn from historical data that incorporates prior knowledge from NWP. We cast\nthe weather forecasting problem as an end-to-end deep learning problem and\nsolve it by proposing a novel negative log-likelihood error (NLE) loss\nfunction. A notable advantage of our proposed method is that it simultaneously\nimplements single-value forecasting and uncertainty quantification, which we\nrefer to as deep uncertainty quantification (DUQ). Efficient deep ensemble\nstrategies are also explored to further improve performance. This new approach\nwas evaluated on a public dataset collected from weather stations in Beijing,\nChina. Experimental results demonstrate that the proposed NLE loss\nsignificantly improves generalization compared to mean squared error (MSE) loss\nand mean absolute error (MAE) loss. Compared with NWP, this approach\nsignificantly improves accuracy by 47.76%, which is a state-of-the-art result\non this benchmark dataset. The preliminary version of the proposed method won\n2nd place in an online competition for daily weather forecasting.","url_abs":"http://arxiv.org/abs/1812.09467v3","url_pdf":"http://arxiv.org/pdf/1812.09467v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-uncertainty-quantification-a-machine","repo_url":"https://github.com/BruceBinBoxing/Deep_Learning_Weather_Forecasting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-uncertainty-quantification-a-machine","repo_url":"https://github.com/BruceBinBoxing/WF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-uncertainty-quantification-a-machine","repo_url":"https://github.com/BruceBinBoxing/Weather_Forecasting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"weather-forecasting","task_name":"Weather Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}