題目：Accurate Medium-Range Global Weather Forecasting with 3D Deep Neural Networks

　　報(bào)告人：田奇

　　時(shí)間：2023年10月20日（周五）,，上午10:00—11:00

　　地點(diǎn)：31-904

　　報(bào)告摘要：

　　Weather forecasting is important for science and society. Currently, the most accurate forecast system is the numerical weather prediction （NWP） method, which represents atmospheric states as discretized grids and numerically solves partial differential equations （PDEs） that describe the transition between those states. However, this procedure is computationally expensive. Recently, AI-based weather forecasting methods have shown potential in accelerating weather forecasting by orders of magnitudes, but the forecast accuracy is still significantly lower than that of NWP methods. In this paper, we introduce an AI-based method for accurate, medium-range global weather forecasting. We show that 3D deep networks equipped with Earth-specific priors are effective at dealing with complex patterns in weather data, and that a hierarchical temporal aggregation strategy reduces accumulation errors in medium-range forecasting. Trained on 39 years of global data, our program, Pangu-Weather, is the first to obtain stronger deterministic forecast results on reanalysis data in all tested variables, when compared with the world’s best NWP system, the operational integrated forecasting system （IFS） of the European Centre for Medium-Range Weather Forecasts （ECMWF）,。 Our method also works well with extreme weather forecasts and ensemble forecasts. When initialized with reanalysis data, the accuracy of tracking tropical cyclones is higher than ECMWF-HRES.

　　報(bào)告人簡(jiǎn)介：

　　田奇，華為云人工智能領(lǐng)域首席科學(xué)家,，國(guó)際歐亞科學(xué)院院士,，教育部長(zhǎng)江講座教授、國(guó)家自然科學(xué)基金海外杰青,，中國(guó)科學(xué)院海外評(píng)審專家,，IEEE/CAAI Fellow，中國(guó)人工智能學(xué)會(huì)吳文俊人工智能領(lǐng)域杰出貢獻(xiàn)獎(jiǎng)獲得者,。2018年6月-2020年3月?lián)稳A為諾亞方舟實(shí)驗(yàn)室計(jì)算視覺(jué)首席科學(xué)家,。田奇教授高中畢業(yè)于成都七中（1987級(jí)），本科畢業(yè)于清華大學(xué)電子工程系（1992）,，后赴美國(guó)伊利諾伊大學(xué)香檳分校學(xué)習(xí),，師從Thomas S. Huang教授獲博士學(xué)位（2002）。后歷任美國(guó)德克薩斯大學(xué)圣安東尼奧分校計(jì)算機(jī)系助理教授,、副教授,、和正教授（2002-2019），2010年獲Google Faculty Research Award,，2017年UTSA校長(zhǎng)杰出研究獎(jiǎng),、2016年獲評(píng)多媒體領(lǐng)域10大最具影響力的學(xué)者，并于2018年入選國(guó)家級(jí)領(lǐng)軍人才創(chuàng)新項(xiàng)目,。田教授是IEEE TMM, TCSVT, TNNLS, ACM TOMM,、Multimedia Systems Journal等多個(gè)期刊的Associate Editor。他擁有多項(xiàng)美國(guó)專利,，在計(jì)算機(jī)視覺(jué)及多媒體方向頂級(jí)期刊及會(huì)議如IEEE TPAMI,，IJCV，TIP,，TMM,，CVPR,? ICCV，ECCV,，ACM MM上發(fā)表文章約750+余篇（包括220 篇IEEE/ACM期刊和210篇CCF A類會(huì)議文章）,，谷歌學(xué)術(shù)引用次數(shù)57000+，h指數(shù)為106，有8篇論文獲最佳論文獎(jiǎng)或者最佳學(xué)生論文包括ACM Multimedia等,。田教授的盤古氣象大模型論文發(fā)表于《Nature》雜志正刊,。