{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:23:57Z","timestamp":1771266237637,"version":"3.50.1"},"reference-count":57,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T00:00:00Z","timestamp":1703203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41975066"],"award-info":[{"award-number":["41975066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Accurate and timely precipitation forecasts are critical in modern society, influencing both economic activity and daily life. While deep learning methods leveraging remotely sensed radar data have become prevalent for precipitation nowcasting, longer-term forecasting remains challenging. This is due to accumulated errors in deep learning models and insufficient information about precipitation systems over longer time horizons. To address these challenges, we introduce the Short-Term Precipitation Forecast Network (STPF-Net), a recurrent neural network designed for longer-term precipitation prediction. STPF-Net uses a multi-tier structure with varying temporal resolutions to mitigate the accumulated errors during longer forecasts. Additionally, its transformer-based module incorporates larger spatial contexts, providing more complete information about precipitation systems. We evaluated STPF-Net on radar data from southeastern China, training separate models for 6 and 12 h forecasts. Quantitative results demonstrate STPF-Net achieved superior accuracy and lower errors compared to benchmark deep learning and numerical weather prediction models. Visualized case studies indicate reasonably coherent 6 h predictions from STPF-Net versus other methods. For 12 h forecasts, while STPF-Net outperformed other models, it still struggled with storm initiation over longer forecasting time.<\/jats:p>","DOI":"10.3390\/rs16010052","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T04:44:40Z","timestamp":1703220280000},"page":"52","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["STPF-Net: Short-Term Precipitation Forecast Based on a Recurrent Neural Network"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3165-6876","authenticated-orcid":false,"given":"Jingnan","family":"Wang","sequence":"first","affiliation":[{"name":"College of Computer, National University of Defense and Technology, Changsha 410073, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8949-5967","authenticated-orcid":false,"given":"Xiaodong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense and Technology, Changsha 410073, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0038-3650","authenticated-orcid":false,"given":"Jiping","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Meteorology and Oceanography, National University of Defense and Technology, Changsha 410073, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-4826","authenticated-orcid":false,"given":"Lifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Meteorology and Oceanography, National University of Defense and Technology, Changsha 410073, China"}]},{"given":"Fuhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi\u2019an Satellite Control Center, Xi\u2019an 710049, China"}]},{"given":"Tao","family":"Chang","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense and Technology, Changsha 410073, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1038\/nature14956","article-title":"The quiet revolution of numerical weather prediction","volume":"525","author":"Bauer","year":"2015","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2599","DOI":"10.1175\/1520-0493(1998)126<2599:CTFFAM>2.0.CO;2","article-title":"Convective trigger function for a mass-flux cumulus parameterization scheme","volume":"126","author":"Hong","year":"1998","journal-title":"Mon. Weather Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1175\/JAS-D-13-0163.1","article-title":"Representing equilibrium and nonequilibrium convection in large-scale models","volume":"71","author":"Bechtold","year":"2014","journal-title":"J. Atmos. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1002\/qj.2982","article-title":"A review of operational methods of variational and ensemble-variational data assimilation","volume":"143","author":"Bannister","year":"2017","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1175\/1520-0493(2004)132<0897:ATVDAS>2.0.CO;2","article-title":"A three-dimensional variational data assimilation system for MM5: Implementation and initial results","volume":"132","author":"Barker","year":"2004","journal-title":"Mon. Weather Rev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3183","DOI":"10.1256\/qj.02.132","article-title":"The potential of the ensemble kalman filter for nwp\u2014A comparison with 4D-Var","volume":"129","author":"Lorenc","year":"2010","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"(2004). Short-range quantitative precipitation forecasting in Hong Kong. J. Hydrol., 288, 189\u2013209.","DOI":"10.1016\/j.jhydrol.2003.11.034"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1002\/asl.72","article-title":"The next generation of NWP: Explicit forecastsof convection using the weather research andforecasting (WRF) model","volume":"5","author":"Done","year":"2004","journal-title":"Atmos. Sci. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/S0022-1694(00)00352-8","article-title":"Improving the nowcasting of precipitation in an alpine region with an enhanced radar echo tracking algorithm","volume":"239","author":"Mecklenburg","year":"2000","journal-title":"J. Hydrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1286","DOI":"10.1175\/1520-0450(1995)034<1286:NOMAGO>2.0.CO;2","article-title":"Nowcasting of motion and growth of precipitation with radar over a complex orography","volume":"34","author":"Li","year":"1995","journal-title":"J. Appl. Meteorol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1175\/2008JTECHA1084.1","article-title":"3d convective storm identification, tracking, and forecasting\u2014An enhanced titan algorithm","volume":"26","author":"Han","year":"2009","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1175\/JTECH-D-15-0119.1","article-title":"Storm tracking via tree structure representation of radar data","volume":"34","author":"Hou","year":"2017","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.jhydrol.2003.11.011","article-title":"Development of a precipitation nowcasting algorithm based upon optical flow techniques","volume":"288","author":"Bowler","year":"2004","journal-title":"J. Hydrol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","article-title":"Deep learning and process understanding for data-driven earth system science","volume":"566","author":"Reichstein","year":"2019","journal-title":"Nature"},{"key":"ref_15","first-page":"20200097","article-title":"Can deep learning beat numerical weather prediction?","volume":"379","author":"Schultz","year":"2021","journal-title":"Philos. Trans. R. Soc. Math. Phys. Eng. Sci."},{"key":"ref_16","unstructured":"Prudden, R., Adams, S., Kangin, D., Robinson, N., Ravuri, S., Mohamed, S., and Arribas, A. (2020). A review of radar-based nowcasting of precipitation and applicable machine learning techniques. arXiv."},{"key":"ref_17","unstructured":"Shi, X., and Yeung, D.Y. (2018). Machine learning for spatiotemporal sequence forecasting: A survey. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B.V., Gulcehre, C., BaHdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_20","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., and Bengio, Y. (2014). Generative adversarial nets. arXiv."},{"key":"ref_21","unstructured":"Defferrard, M., Bresson, X., and Vandergheynst, P. (2016, January 5\u201310). Convolutional neural networks on graphs with fast localized spectral filtering. Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain."},{"key":"ref_22","unstructured":"Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., and Hickey, J. (2019). Machine learning for precipitation nowcasting from radar images. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2631","DOI":"10.5194\/gmd-13-2631-2020","article-title":"Rainnet v1.0: A convolutional neural network for radar-based precipitation nowcasting","volume":"13","author":"Ayzel","year":"2020","journal-title":"Geosci. Model Dev."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1109\/TGRS.2019.2948070","article-title":"Convolutional neural network for convective storm nowcasting using 3D doppler weather radar data","volume":"58","author":"Han","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4103508","DOI":"10.1109\/TGRS.2021.3100847","article-title":"Convective precipitation nowcasting using U-Net model","volume":"60","author":"Han","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.patrec.2021.01.036","article-title":"SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture","volume":"145","author":"Trebing","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kaparakis, C., and Mehrkanoon, S. (2023). Wf-unet: Weather fusion unet for precipitation nowcasting. arXiv.","DOI":"10.1016\/j.procs.2023.08.160"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e2022GL097904","DOI":"10.1029\/2022GL097904","article-title":"Short-term precipitation prediction for contiguous united states using deep learning","volume":"49","author":"Chen","year":"2022","journal-title":"Geophys. Res. Lett."},{"key":"ref_29","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-k., and Woo, W.-c. (2015, January 7\u201312). Convolutional lstm network: A machine learning approach for precipitation nowcasting. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_30","unstructured":"Shi, X., Gao, Z., Lausen, L., Wang, H., Yeung, D.-Y., Wong, W.-k., and Woo, W.-c. (2017, January 4\u20139). Deep learning for precipitation nowcasting: A benchmark and a new model. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_31","unstructured":"Wang, Y., Long, M., Wang, J., Gao, Z., and Yu, P.S. (2017, January 4\u20139). PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_32","unstructured":"Wang, Y., Gao, z., Long, M., Wang, J., and Yu, P.S. (2018). PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Jing, J., Li, Q., Peng, X., Ma, Q., and Tang, S. (2020, January 4\u20138). HPRNN: A hierarchical sequence prediction model for long-term weather radar echo extrapolation. Proceedings of the ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9054232"},{"key":"ref_34","unstructured":"Snderby, C.K., Espeholt, L., Heek, J., Dehghani, M., Oliver, A., Salimans, T., Agrawal, S., Hickey, J., and Kalchbrenner, N. (2020). MetNet: A neural weather model for precipitation forecasting. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Espeholt, L., Agrawal, S., S\u00f8nderby, C., Kumar, M., Heek, J., Bromberg, C., Gazen, C., Hickey, J., Bell, A., and Kalchbrenner, N. (2021). Skillful twelve hour precipitation forecasts using large context neural networks. arXiv.","DOI":"10.1038\/s41467-022-32483-x"},{"key":"ref_36","unstructured":"Yan, B.Y., Yang, C., Chen, F., Takeda, K., and Wang, C. (2021). FDNet: A deep learning approach with two parallel cross encoding pathways for precipitation nowcasting. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhang, F., Wang, X., Guan, J., Wu, M., and Guo, L. (2021). RN-Net: A deep learning approach to 0\u20132 h rainfall nowcasting based on radar and automatic weather station data. Sensors, 21.","DOI":"10.3390\/s21061981"},{"key":"ref_38","unstructured":"Klocek, S., Dong, H., Dixon, M., Kanengoni, P., Kazmi, N., Luferenko, P., Lv, Z., Sharma, S., Weyn, J., and Xiang, S. (2021). MS-nowcasting: Operational precipitation nowcasting with convolutional lstms at microsoft weather. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"127748","DOI":"10.1016\/j.jhydrol.2022.127748","article-title":"A spatiotemporal deep learning model ST-LSTM-SA for hourly rainfall forecasting using radar echo images","volume":"609","author":"Liu","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_40","first-page":"4102212","article-title":"Pixel-CRN: A new machine learning approach for convective storm nowcasting","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1038\/s41586-021-03854-z","article-title":"Skillful precipitation nowcasting using deep generative models of radar","volume":"597","author":"Ravuri","year":"2021","journal-title":"Nature"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4104308","DOI":"10.1109\/TGRS.2021.3108812","article-title":"Very short-term rainfall prediction using ground radar observations and conditional generative adversarial networks","volume":"60","author":"Kim","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1038\/s41586-023-06184-4","article-title":"Skilful nowcasting of extreme precipitation with NowcastNet","volume":"619","author":"Zhang","year":"2023","journal-title":"Nature"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"4023305","DOI":"10.1109\/LGRS.2022.3162882","article-title":"Rainformer: Features extraction balanced network for radar-based precipitation nowcasting","volume":"19","author":"Bai","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_45","first-page":"390","article-title":"Earthformer: Exploring space-time transformers for earth system forecasting","volume":"35","author":"Gao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e2022MS003211","DOI":"10.1029\/2022MS003211","article-title":"Swinvrnn: A data-driven ensemble forecasting model via learned distribution perturbation","volume":"15","author":"Hu","year":"2022","journal-title":"J. Adv. Model. Earth Syst."},{"key":"ref_47","first-page":"809","article-title":"Design and application of radar reflectivity quality control algorithm in SWAN","volume":"41","author":"Wu","year":"2013","journal-title":"Meteorol. Sci. Technol."},{"key":"ref_48","unstructured":"Li, P.W., Wong, W.-K., Chan, K.Y., and Lai, E.S.T. (2000). Swirls\u2014An Evolving Nowcasting System."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. arXiv.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_50","unstructured":"Bojesomo, A., Al-Marzouqi, H., and Liatsis, P. (2022). A novel transformer network with shifted window cross-attention for spatiotemporal weather forecasting. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"3429","DOI":"10.1007\/s11434-008-0462-7","article-title":"On the development of the GRAPES\u2014A new generation of the national operational NWP system in China","volume":"53","author":"Zhang","year":"2008","journal-title":"Sci. Bull."},{"key":"ref_52","first-page":"1001","article-title":"Recent progress on GRAPES research and application","volume":"6","author":"Chen","year":"2006","journal-title":"J. Appl. Meteorol. Sci."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"3433","DOI":"10.1007\/s11434-008-0494-z","article-title":"New generation of multi-scale NWP system (GRAPES):general scientific design","volume":"53","author":"Chen","year":"2008","journal-title":"Chin. Sci. Bull."},{"key":"ref_54","first-page":"1146","article-title":"The impacts of time-step size and spatial resolution on the prediction skill of the GRAPES-meso forecast system","volume":"42","author":"Liu","year":"2015","journal-title":"Chin. J. Atmos. Sci."},{"key":"ref_55","first-page":"14","article-title":"Comprehensive evaluations of GRAPES_3km numerical model in forecasting convective storms using various verification methods","volume":"46","author":"Zhang","year":"2020","journal-title":"Meteorol. Mon."},{"key":"ref_56","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). Pytorch: An imperative style, high-performance deep learning library. arXiv."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Zhang, F., Wang, X., and Guan, J. (2021). A novel multi-input multi-output recurrent neural network based on multimodal fusion and spatiotemporal prediction for 0\u20134 h precipitation nowcasting. Atmosphere, 12.","DOI":"10.3390\/atmos12121596"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/1\/52\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:40:11Z","timestamp":1760132411000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/1\/52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,22]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["rs16010052"],"URL":"https:\/\/doi.org\/10.3390\/rs16010052","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,22]]}}}