{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T23:41:16Z","timestamp":1782430876865,"version":"3.54.5"},"reference-count":23,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of the Xinjiang Uygur Autonomous Region","award":["2021D01C080"],"award-info":[{"award-number":["2021D01C080"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Short-term precipitation forecasting methods are mainly divided into statistical forecasting, numerical model-based forecasting, and radar image extrapolation techniques. The two methods based on statistical prediction and numerical model have the disadvantages of being unstable and generating large errors. Therefore, this study proposes the use of deep learning for radar image extrapolation for precipitation forecasting, in particular by developing algorithms for ConvLSTM and SmaAT-UNet. The ConvLSTM model is a fusion of a CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory network), which solves the challenge of processing spatial sequence data, which is a task that traditional LSTM models cannot accomplish. At the same time, SmaAT-UNet enhances the traditional UNet structure by incorporating the CBAM (Convolutional Block Attention Module) attention mechanism and replacing the standard convolutional layer with depthwise separable convolution. This innovative approach aims to improve the efficiency and accuracy of short-term precipitation forecasting by improving feature extraction and data processing techniques. Evaluation and analysis of experimental data show that both models exhibit good predictive ability, with the SmaAT-UNet model outperforming ConvLSTM in terms of accuracy. The results show that the performance indicators of precipitation prediction, especially detection probability (POD) and the Critical Success index (CSI), show a downward trend with the extension of the prediction time. This trend highlights the inherent challenges of maintaining predictive accuracy over longer periods of time and highlights the superior performance and resilience of the SmaAT-UNet model under these conditions. Compared with the statistical forecasting method and numerical model forecasting method, its accuracy in short-term rainfall forecasting is improved.<\/jats:p>","DOI":"10.3390\/s24113576","type":"journal-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T05:58:00Z","timestamp":1717394280000},"page":"3576","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Short-Term and Imminent Rainfall Prediction Model Based on ConvLSTM and SmaAT-UNet"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9901-2613","authenticated-orcid":false,"given":"Yuanyuan","family":"Liao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Urumqi 830049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouqian","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Urumqi 830049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,1]]},"reference":[{"key":"ref_1","unstructured":"Wang, T., Liu, Y., Dong, C., and Li, J. (2019). Review of Short-term and Imminent Precipitation Forecasting Methods and Their Applications. Electron. World, 11\u201313."},{"key":"ref_2","first-page":"57","article-title":"Application of Doppler radar for observation and analysis of rainstorm and its approaching warning","volume":"27","author":"Chai","year":"2007","journal-title":"Meteorol. Sci."},{"key":"ref_3","first-page":"903","article-title":"Multi-scale analysis and near-term warning of short-term heavy precipitation","volume":"38","author":"Hao","year":"2012","journal-title":"Meteorology"},{"key":"ref_4","first-page":"124","article-title":"Application of artificial neural network in short-term precipitation prediction","volume":"123","author":"Zhang","year":"2016","journal-title":"Sci. Technol. Wind."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11269-006-9141-0","article-title":"Runoff Analysis for a Small Watershed of Tono Area Japan by Back Propagation Artificial Neural Network with Seasonal Data","volume":"22","author":"Sohail","year":"2008","journal-title":"Water Resour. Manag. Int. J. Publ. Eur. Water Resour. Assoc. (EWRA)"},{"key":"ref_6","first-page":"771","article-title":"Long-term runoff forecasting for the autumn flood season in the Danjiangkou Reservoir","volume":"21","author":"Liu","year":"2010","journal-title":"Adv. Water Sci."},{"key":"ref_7","first-page":"411","article-title":"Nowforecasting method based on convolutional gated recurrent unit neural network","volume":"40","author":"Chen","year":"2021","journal-title":"Plateau Meteorol."},{"key":"ref_8","first-page":"61","article-title":"Application of recurrent neural network in radar nowcasting","volume":"30","author":"Han","year":"2019","journal-title":"J. Appl. Meteorol."},{"key":"ref_9","first-page":"661","article-title":"Radar echo extrapolation method based on convolutional neural network","volume":"38","author":"Shi","year":"2018","journal-title":"Comput. Appl."},{"key":"ref_10","first-page":"41","article-title":"Evaluation of short-term and imminent prediction accuracy based on deep learning and radar observations in South China","volume":"41","author":"Liang","year":"2020","journal-title":"Meteorol. Res. Appl."},{"key":"ref_11","unstructured":"Shi, X., Chen, Z., Wang, H., and Yeung, D.-Y. (2015). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, MIT Press."},{"key":"ref_12","unstructured":"(2024, May 15). Academician Zhang Pingwen: Artificial Intelligence Makes Weather Forecasts for the Winter Olympics More Accurate. Available online: http:\/\/bda.pku.edu.cn\/info\/1003\/2291.htm."},{"key":"ref_13","unstructured":"Zhang, Y., Kers, J., Cassol, C.A., Roelofs, J.J., Idrees, N., Farber, A., Haroon, S., Daly, K.P., Ganguli, S., and Chitalia, V.C. (2021). U-Net-and-a-half: Convolutional network for biomedical image segmentation using multiple expert-driven annotations. arXiv."},{"key":"ref_14","unstructured":"Pamuk, S. (2005, January 1\u20135). A Case Study: Graduate student\u2019s perspective on faculty technology mentoring within the CBAM framework. Proceedings of the Society for Information Technology & Teacher Education International Conference, Phoenix, AZ, USA."},{"key":"ref_15","first-page":"203","article-title":"Research on Stock Prediction based on LSTM-CNN-CBAM Model","volume":"57","author":"Zhao","year":"2019","journal-title":"Comput. Eng. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/MSP.2011.2179329","article-title":"A tour of modern image filtering: New insights and methods, both practical and theoretical","volume":"30","author":"Milanfar","year":"2013","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_17","first-page":"505","article-title":"Analysis of precipitation trend and its evolution process in Hong Kong","volume":"5","author":"Zhang","year":"2010","journal-title":"J. Hohai Univ. Nat. Sci. Ed."},{"key":"ref_18","unstructured":"Zhou, Z. (2019). Machine Learning, Tsinghua University Press."},{"key":"ref_19","unstructured":"Dou, H. (2022). Research on Short-Term and Imminent Precipitation Forecasting Based on ConvLSTM Deep Spatiotemporal Network, Nanjing University of Posts and Telecommunications."},{"key":"ref_20","first-page":"2121","article-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_21","unstructured":"Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv."},{"key":"ref_22","first-page":"122","article-title":"Based on Dopout and ADAM optimizer improve CNN algorithm","volume":"46\u201348","author":"Yang","year":"2018","journal-title":"J. Huazhong Univ. Sci. Technol. (Nat. Sci. Ed.)"},{"key":"ref_23","unstructured":"Molnar, C. (2021). Interpretable Machine Learning, Publishing House of Electronics Industry."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/11\/3576\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:52:22Z","timestamp":1760107942000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/11\/3576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":23,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["s24113576"],"URL":"https:\/\/doi.org\/10.3390\/s24113576","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,1]]}}}