%0 Journal Article %1 schultz_can_2021 %A Schultz, M. G. %A Betancourt, C. %A Gong, B. %A Kleinert, F. %A Langguth, M. %A Leufen, L. H. %A Mozaffari, A. %A Stadtler, S. %D 2021 %J Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences %K AI deep ecomodelling learning, machine numerical pattern prediction, recognition, spatiotemporal weather %N 2194 %P 20200097 %R 10.1098/rsta.2020.0097 %T Can deep learning beat numerical weather prediction? %U https://royalsocietypublishing.org/doi/full/10.1098/rsta.2020.0097 %V 379 %X 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, 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’.}, added-at = {2023-07-31T08:05:54.000+0200}, 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.}, biburl = {https://www.bibsonomy.org/bibtex/2d935c6431e792446a2fcd8702328f2e6/jascal_panetzky}, doi = {10.1098/rsta.2020.0097}, file = {Full Text PDF:/Users/pascal/Zotero/storage/LS7DJ88P/Schultz et al. - 2021 - Can deep learning beat numerical weather predictio.pdf:application/pdf}, interhash = {23023519111be37f3c06657ab7fe3c12}, intrahash = {d935c6431e792446a2fcd8702328f2e6}, journal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences}, keywords = {AI deep ecomodelling learning, machine numerical pattern prediction, recognition, spatiotemporal weather}, month = feb, note = {Publisher: Royal Society}, number = 2194, pages = 20200097, timestamp = {2023-07-31T08:07:14.000+0200}, title = {Can deep learning beat numerical weather prediction?}, url = {https://royalsocietypublishing.org/doi/full/10.1098/rsta.2020.0097}, urldate = {2023-07-11}, volume = 379, year = 2021 }