{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:05:45Z","timestamp":1791997545911,"version":"4.4.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T00:00:00Z","timestamp":1625616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T00:00:00Z","timestamp":1625616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Climate models (CM) are used to evaluate the impact of climate change on the risk of floods and heavy precipitation events. However, these numerical simulators produce outputs with low spatial resolution that exhibit difficulties representing precipitation events accurately. This is mainly due to computational limitations on the spatial resolution used when simulating multi-scale weather dynamics in the atmosphere. To improve the prediction of high resolution precipitation we apply a Deep Learning (DL) approach using input data from a reanalysis product, that is comparable to a climate model\u2019s output, but can be directly related to precipitation observations at a given time and location. Further, our input excludes local precipitation, but includes model fields (weather variables) that are more predictable and generalizable than local precipitation. To this end, we present TRU-NET (Temporal Recurrent U-Net), an encoder-decoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers to effectively model multi-scale spatio-temporal weather processes. We also propose a non-stochastic variant of the conditional-continuous (CC) loss function to capture the zero-skewed patterns of rainfall. Experiments show that our models, trained with our CC loss, consistently attain lower RMSE and MAE scores than a DL model prevalent in precipitation downscaling and outperform a state-of-the-art dynamical weather model. Moreover, by evaluating the performance of our model under various data formulation strategies, for the training and test sets, we show that there is enough data for our deep learning approach to output robust, high-quality results across seasons and varying regions.<\/jats:p>","DOI":"10.1007\/s10994-021-06022-6","type":"journal-article","created":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T18:01:51Z","timestamp":1625680911000},"page":"2035-2062","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":79,"title":["TRU-NET: a deep learning approach to high resolution prediction of rainfall"],"prefix":"10.1007","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-7938","authenticated-orcid":false,"given":"Rilwan A.","family":"Adewoyin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Dueben","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Watson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritabrata","family":"Dutta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,7]]},"reference":[{"key":"6022_CR1","unstructured":"Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., & Hickey, J. (2019). Machine learning for precipitation nowcasting from radar images. 1912.12132."},{"key":"6022_CR2","unstructured":"Burton, C. (2011). How weather patterns have contributed to extreme precipitation in the united kingdom, and links to past flood events."},{"issue":"9","key":"6022_CR3","doi-asserted-by":"publisher","first-page":"11524","DOI":"10.1029\/2011WR011524","volume":"48","author":"A B\u00e1rdossy","year":"2012","unstructured":"B\u00e1rdossy, A., & Pegram, G. (2012). Multiscale spatial recorrelation of rcm precipitation to produce unbiased climate change scenarios over large areas and small. Water Resources Research, 48(9), 11524. https:\/\/doi.org\/10.1029\/2011WR011524.","journal-title":"Water Resources Research"},{"issue":"1\u20132","key":"6022_CR4","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s00382-017-3580-6","volume":"50","author":"AJ Cannon","year":"2018","unstructured":"Cannon, A. J. (2018). Multivariate quantile mapping bias correction: An N-dimensional probability density function transform for climate model simulations of multiple variables. Climate Dynamics, 50(1\u20132), 31\u201349. https:\/\/doi.org\/10.1007\/s00382-017-3580-6.","journal-title":"Climate Dynamics"},{"key":"6022_CR5","unstructured":"Cornes, R., van der Schrier, G., van den Besselaar, E., & Jones, P. (2019). An ensemble version of the e-obs temperature and precipitation datasets: version 21.0e."},{"key":"6022_CR6","doi-asserted-by":"publisher","unstructured":"Ding, D., Zhang, M., Pan, X., Yang, M., & He, X. (2019). Modeling extreme events in time series prediction. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, New York, NY, USA, KDD\u201919 (pp. 1114\u20131122). https:\/\/doi.org\/10.1145\/3292500.3330896.","DOI":"10.1145\/3292500.3330896"},{"key":"6022_CR7","unstructured":"Gal, Y., & Ghahramani, Z. (2015). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. 1506.02142."},{"key":"6022_CR8","unstructured":"Ghosh, S., Yao, J., & Doshi-Velez, F. (2018). Structured variational learning of Bayesian neural networks with horseshoe priors. 1806.05975."},{"key":"6022_CR9","doi-asserted-by":"publisher","unstructured":"Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Hor\u00e1nyi, A., Mu\u00f1oz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., De\u00a0Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R., H\u00f3lm, E., Janiskov\u00e1, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de\u00a0Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., & Th\u00e9paut, J. N. (2017). Complete era5: Fifth generation of ecmwf atmospheric reanalyses of the global climate. copernicus climate change service (c3s) data store (cds). https:\/\/doi.org\/10.24381\/cds.68d2bb30.","DOI":"10.24381\/cds.68d2bb30"},{"issue":"730","key":"6022_CR10","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1002\/qj.3803","volume":"146","author":"H Hersbach","year":"2020","unstructured":"Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Hor\u00e1nyi, A., & Mu\u00f1oz-Sabater, J. (2020). The era5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146(730), 1999\u20132049. https:\/\/doi.org\/10.1002\/qj.3803.","journal-title":"Quarterly Journal of the Royal Meteorological Society"},{"issue":"D21","key":"6022_CR11","doi-asserted-by":"publisher","first-page":"11799","DOI":"10.1029\/2009JD011799","volume":"114","author":"N Hofstra","year":"2009","unstructured":"Hofstra, N., Haylock, M., New, M., & Jones, P. D. (2009). Testing e-obs European high-resolution gridded data set of daily precipitation and surface temperature. Journal of Geophysical Research: Atmospheres, 114(D21), 11799. https:\/\/doi.org\/10.1029\/2009JD011799.","journal-title":"Journal of Geophysical Research: Atmospheres"},{"issue":"7","key":"6022_CR12","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1002\/joc.1441","volume":"27","author":"GJ Husak","year":"2007","unstructured":"Husak, G. J., Michaelsen, J., & Funk, C. (2007). Use of the gamma distribution to represent monthly rainfall in Africa for drought monitoring applications. International Journal of Climatology, 27(7), 935\u2013944. https:\/\/doi.org\/10.1002\/joc.1441.","journal-title":"International Journal of Climatology"},{"key":"6022_CR13","unstructured":"IPCC. (2007). Fourth Assessment Report: Climate Change 2007: The AR4 Synthesis Report. Geneva: IPCC."},{"key":"6022_CR14","unstructured":"Jauhar, S. K., Gamon, M., & Pantel, P. (2018). Neural task representations as weak supervision for model agnostic cross-lingual transfer. 1811.01115."},{"key":"6022_CR15","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2019a). On the variance of the adaptive learning rate and beyond. 1908.03265."},{"key":"6022_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y. T., Li, Y. J., Yang, F. E., Chen, S. F., & Wang, Y. C. F. (2019b). Learning hierarchical self-attention for video summarization. In 2019 IEEE international conference on image processing (ICIP) (pp. 3377\u20133381).","DOI":"10.1109\/ICIP.2019.8803639"},{"issue":"2","key":"6022_CR17","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s00382-003-0373-x","volume":"22","author":"W May","year":"2004","unstructured":"May, W. (2004). Simulation of the variability and extremes of daily rainfall during the Indian summer monsoon for present and future times in a global time-slice experiment. Climate Dynamics, 22(2), 183\u2013204. https:\/\/doi.org\/10.1007\/s00382-003-0373-x.","journal-title":"Climate Dynamics"},{"key":"6022_CR18","unstructured":"Murphy, J., Harris, G., Sexton, D., Kendon, E., Bett, P., & Clark, R. (2018). Ukcp18 land projections: Science report. Tech. rep., Met Office."},{"key":"6022_CR19","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/978-981-15-5077-5_55","volume-title":"Proceedings of international conference on communication and computational technologies","author":"S Panjwani","year":"2021","unstructured":"Panjwani, S., Naresh Kumar, S., & Ahuja, L. (2021). Bias correction of gcm data using quantile mapping technique. In S. D. Purohit, D. SinghJat, R. C. Poonia, S. Kumar, & S. Hiranwal (Eds.), Proceedings of international conference on communication and computational technologies (pp. 617\u2013621). Singapore: Springer."},{"issue":"39","key":"6022_CR20","doi-asserted-by":"publisher","first-page":"9684","DOI":"10.1073\/pnas.1810286115","volume":"115","author":"S Rasp","year":"2018","unstructured":"Rasp, S., Pritchard, M. S., & Gentine, P. (2018). Deep learning to represent subgrid processes in climate models. Proceedings of the National Academy of Sciences, 115(39), 9684\u20139689. https:\/\/doi.org\/10.1073\/pnas.1810286115.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"6022_CR21","doi-asserted-by":"crossref","unstructured":"Rasp, S., Dueben, P. D., Scher, S., Weyn, J. A., Mouatadid, S., & Thuerey, N. (2020). Weatherbench: A benchmark dataset for data-driven weather forecasting. 2002.00469.","DOI":"10.1029\/2020MS002203"},{"key":"6022_CR22","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. 1505.04597.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"6022_CR23","doi-asserted-by":"publisher","unstructured":"Shaw, P., Uszkoreit, J., & Vaswani, A. (2018). Self-attention with relative position representations. In Proceedings of the 2018 Conference of the North American chapter of the association for computational linguistics: Human language technologies (Short Papers) (Vol. 2, pp. 464\u2013468). https:\/\/doi.org\/10.18653\/v1\/N18-2074.","DOI":"10.18653\/v1\/N18-2074"},{"key":"6022_CR24","unstructured":"Shi, X., Chen, Z., & Wang, H. (2015). Convolutional lstm network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems (Vol. 28, pp. 802\u2013810). Curran Associates, Inc."},{"key":"6022_CR25","unstructured":"Shi, X., Gao, Z., Lausen, L., Wang, H., Yeung, D. Y., Wong, W. k., & Woo, W. c. (2017). Deep learning for precipitation nowcasting: A benchmark and a new model. In Advances in neural information processing systems (pp. 5617\u20135627)."},{"key":"6022_CR26","unstructured":"Shukla, P., Skea, J., Buendia, E. C., Masson-Delmotte, V., & P\u00f6rtner, H. (2019). Ipcc special report on climate change, desertification, land degradation, sustainable land management, food security, and greenhouse gas fluxes in terrestrial ecosystems."},{"issue":"56","key":"6022_CR27","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(56), 1929\u20131958.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"6022_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2307\/2981736","volume":"147","author":"R Stern","year":"1984","unstructured":"Stern, R., & Coe, R. (1984). A model fitting analysis of daily rainfall data. Journal of the Royal Statistical Society Series A (General), 147(1), 1\u201334.","journal-title":"Journal of the Royal Statistical Society Series A (General)"},{"key":"6022_CR29","doi-asserted-by":"publisher","unstructured":"Tai, K. S., Socher, R., & Manning, C. D. (2015). Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Association for Computational Linguistics (pp. 1556\u20131566). Beijing, China, https:\/\/doi.org\/10.3115\/v1\/P15-1150.","DOI":"10.3115\/v1\/P15-1150"},{"key":"6022_CR30","doi-asserted-by":"crossref","unstructured":"Trebing, K., & Mehrkanoon, S. (2020). Smaat-unet: Precipitation nowcasting using a small attention-unet architecture. 2007.04417.","DOI":"10.1016\/j.patrec.2021.01.036"},{"key":"6022_CR31","doi-asserted-by":"publisher","unstructured":"Vandal, T., Kodra, E., Dy, J., Ganguly, S., Nemani, R., & Ganguly, A. R. (2018). Quantifying uncertainty in discrete-continuous and skewed data with bayesian deep learning. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. https:\/\/doi.org\/10.1145\/3219819.3219996.","DOI":"10.1145\/3219819.3219996"},{"key":"6022_CR32","first-page":"5998","volume-title":"Advances in neural information processing systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., et al. (2017). Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 30, pp. 5998\u20136008). New York: Curran Associates Inc."},{"key":"6022_CR33","unstructured":"Wallemacq, P., & Herden, C. (2015). The Human Cost Of Weather Related Disasters. CRED, UNIDSR."},{"issue":"3","key":"6022_CR34","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3390\/atmos8030048","volume":"8","author":"WC Woo","year":"2017","unstructured":"Woo, W. C., & Wong, W. K. (2017). Operational application of optical flow techniques to radar-based rainfall nowcasting. Atmosphere, 8(3), 48. https:\/\/doi.org\/10.3390\/atmos8030048.","journal-title":"Atmosphere"},{"issue":"D20","key":"6022_CR35","doi-asserted-by":"publisher","first-page":"ACL6-1","DOI":"10.1029\/2001JD000659","volume":"107","author":"AW Wood","year":"2002","unstructured":"Wood, A. W., Maurer, E. P., Kumar, A., & Lettenmaier, D. P. (2002). Long-range experimental hydrologic forecasting for the eastern united states. Journal of Geophysical Research: Atmospheres, 107(D20), ACL6-1-ACL6-15. https:\/\/doi.org\/10.1029\/2001JD000659.","journal-title":"Journal of Geophysical Research: Atmospheres"},{"key":"6022_CR36","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Shenm Y., & Yao, J. (2019). Recurrent neural network for text classification with hierarchical multiscale dense connections. In Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI-19, international joint conferences on artificial intelligence organization (pp. 5450\u20135456), https:\/\/doi.org\/10.24963\/ijcai.2019\/757.","DOI":"10.24963\/ijcai.2019\/757"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06022-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06022-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06022-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T16:15:25Z","timestamp":1629216925000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06022-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,7]]},"references-count":36,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["6022"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06022-6","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,7]]},"assertion":[{"value":"29 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}