Can deep learning beat numerical weather prediction?. Schultz, M. G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L. H., Mozaffari, A., & Stadtler, S. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 379(2194):20200097, April, 2021. ![Can deep learning beat numerical weather prediction? [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.
@article{schultz_can_2021,
title = {Can deep learning beat numerical weather prediction?},
volume = {379},
issn = {1364-503X, 1471-2962},
url = {https://royalsocietypublishing.org/doi/10.1098/rsta.2020.0097},
doi = {10.1098/rsta.2020.0097},
abstract = {The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach.
This article is part of the theme issue ‘Machine learning for weather and climate modelling’.},
language = {en},
number = {2194},
urldate = {2021-11-15},
journal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},
author = {Schultz, M. G. and Betancourt, C. and Gong, B. and Kleinert, F. and Langguth, M. and Leufen, L. H. and Mozaffari, A. and Stadtler, S.},
month = apr,
year = {2021},
keywords = {AI, AI4EO, AIforEOWS, ML, Machine Learning, ml4esop},
pages = {20200097},
}
Downloads: 0
{"_id":"3zwf6Gbn4kPee26JQ","bibbaseid":"schultz-betancourt-gong-kleinert-langguth-leufen-mozaffari-stadtler-candeeplearningbeatnumericalweatherprediction-2021","author_short":["Schultz, M. G.","Betancourt, C.","Gong, B.","Kleinert, F.","Langguth, M.","Leufen, L. H.","Mozaffari, A.","Stadtler, S."],"bibdata":{"bibtype":"article","type":"article","title":"Can deep learning beat numerical weather prediction?","volume":"379","issn":"1364-503X, 1471-2962","url":"https://royalsocietypublishing.org/doi/10.1098/rsta.2020.0097","doi":"10.1098/rsta.2020.0097","abstract":"The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.","language":"en","number":"2194","urldate":"2021-11-15","journal":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences","author":[{"propositions":[],"lastnames":["Schultz"],"firstnames":["M.","G."],"suffixes":[]},{"propositions":[],"lastnames":["Betancourt"],"firstnames":["C."],"suffixes":[]},{"propositions":[],"lastnames":["Gong"],"firstnames":["B."],"suffixes":[]},{"propositions":[],"lastnames":["Kleinert"],"firstnames":["F."],"suffixes":[]},{"propositions":[],"lastnames":["Langguth"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Leufen"],"firstnames":["L.","H."],"suffixes":[]},{"propositions":[],"lastnames":["Mozaffari"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Stadtler"],"firstnames":["S."],"suffixes":[]}],"month":"April","year":"2021","keywords":"AI, AI4EO, AIforEOWS, ML, Machine Learning, ml4esop","pages":"20200097","bibtex":"@article{schultz_can_2021,\n\ttitle = {Can deep learning beat numerical weather prediction?},\n\tvolume = {379},\n\tissn = {1364-503X, 1471-2962},\n\turl = {https://royalsocietypublishing.org/doi/10.1098/rsta.2020.0097},\n\tdoi = {10.1098/rsta.2020.0097},\n\tabstract = {The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach.\n This article is part of the theme issue ‘Machine learning for weather and climate modelling’.},\n\tlanguage = {en},\n\tnumber = {2194},\n\turldate = {2021-11-15},\n\tjournal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},\n\tauthor = {Schultz, M. G. and Betancourt, C. and Gong, B. and Kleinert, F. and Langguth, M. and Leufen, L. H. and Mozaffari, A. and Stadtler, S.},\n\tmonth = apr,\n\tyear = {2021},\n\tkeywords = {AI, AI4EO, AIforEOWS, ML, Machine Learning, ml4esop},\n\tpages = {20200097},\n}\n\n","author_short":["Schultz, M. G.","Betancourt, C.","Gong, B.","Kleinert, F.","Langguth, M.","Leufen, L. H.","Mozaffari, A.","Stadtler, S."],"key":"schultz_can_2021","id":"schultz_can_2021","bibbaseid":"schultz-betancourt-gong-kleinert-langguth-leufen-mozaffari-stadtler-candeeplearningbeatnumericalweatherprediction-2021","role":"author","urls":{"Paper":"https://royalsocietypublishing.org/doi/10.1098/rsta.2020.0097"},"keyword":["AI","AI4EO","AIforEOWS","ML","Machine Learning","ml4esop"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/iagogv","dataSources":["ovn29uG6Mbp3JWCRR"],"keywords":["ai","ai4eo","aiforeows","ml","machine learning","ml4esop"],"search_terms":["deep","learning","beat","numerical","weather","prediction","schultz","betancourt","gong","kleinert","langguth","leufen","mozaffari","stadtler"],"title":"Can deep learning beat numerical weather prediction?","year":2021}