Non-crossing Quantile Regression Neural Network as a Calibration Tool for Ensemble Weather Forecasts  

作　　者：Mengmeng SONG Dazhi YANG Sebastian LERCH Xiang'ao XIA Gokhan Mert YAGLI Jamie M.BRIGHT Yanbo SHEN Bai LIU Xingli LIU Martin Janos MAYER 

机构地区：[1]School of Electrical Engineering and Automation,Harbin Institute of Technology,Harbin,150001,China [2]Heidelberg Institute for Theoretical Studies,Schloss-Wolfsbrunnenweg 35,69118,Heidelberg,Germany [3]Chair of Statistical Methods and Econometrics,Karlsruhe Institute of Technology(KIT),Bluecherstr.17,76185,Karlsruhe,Germany [4]Key Laboratory of Middle Atmosphere and Global Environment Observation,Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing,100029,China [5]Solar Energy Research Institute of Singapore(SERIS),National University of Singapore(NUS),Singapore,117574,Singapore [6]UK Power Networks,London,SE61NP,UK [7]China Meteorological Administration,Beijing,100081,China [8]Heilongjiang Meteorological Bureau,Harbin,150001,China [9]Department of Energy Engineering,Faculty of Mechanical Engineering,Budapest University of Technology and Economics,Műegyetem rkp.3,H-1111,Budapest,Hungary

出　　处：《Advances in Atmospheric Sciences》2024年第7期1417-1437,共21页大气科学进展（英文版）

基　　金：supported by the National Natural Science Foundation of China (Project No.42375192);the China Meteorological Administration Climate Change Special Program (CMA-CCSP;Project No.QBZ202315);support by the Vector Stiftung through the Young Investigator Group"Artificial Intelligence for Probabilistic Weather Forecasting."

摘　　要：Despite the maturity of ensemble numerical weather prediction(NWP),the resulting forecasts are still,more often than not,under-dispersed.As such,forecast calibration tools have become popular.Among those tools,quantile regression(QR)is highly competitive in terms of both flexibility and predictive performance.Nevertheless,a long-standing problem of QR is quantile crossing,which greatly limits the interpretability of QR-calibrated forecasts.On this point,this study proposes a non-crossing quantile regression neural network(NCQRNN),for calibrating ensemble NWP forecasts into a set of reliable quantile forecasts without crossing.The overarching design principle of NCQRNN is to add on top of the conventional QRNN structure another hidden layer,which imposes a non-decreasing mapping between the combined output from nodes of the last hidden layer to the nodes of the output layer,through a triangular weight matrix with positive entries.The empirical part of the work considers a solar irradiance case study,in which four years of ensemble irradiance forecasts at seven locations,issued by the European Centre for Medium-Range Weather Forecasts,are calibrated via NCQRNN,as well as via an eclectic mix of benchmarking models,ranging from the naïve climatology to the state-of-the-art deep-learning and other non-crossing models.Formal and stringent forecast verification suggests that the forecasts post-processed via NCQRNN attain the maximum sharpness subject to calibration,amongst all competitors.Furthermore,the proposed conception to resolve quantile crossing is remarkably simple yet general,and thus has broad applicability as it can be integrated with many shallow-and deep-learning-based neural networks.

关 键 词：ensemble weather forecasting forecast calibration non-crossing quantile regression neural network CORP reliability diagram POST-PROCESSING 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] P456[自动化与计算机技术—控制科学与工程]