{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T06:21:12Z","timestamp":1764829272238,"version":"build-2065373602"},"reference-count":35,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Spanish Ministry of Science and Innovation (MICINN)","award":["MCIN\/AEI\/10.13039\/501100011033\/FEDER","PID2021-125258OB-I00","SGR2021-00643"],"award-info":[{"award-number":["MCIN\/AEI\/10.13039\/501100011033\/FEDER","PID2021-125258OB-I00","SGR2021-00643"]}]},{"name":"the European Regional Development Fund (FEDER)","award":["MCIN\/AEI\/10.13039\/501100011033\/FEDER","PID2021-125258OB-I00","SGR2021-00643"],"award-info":[{"award-number":["MCIN\/AEI\/10.13039\/501100011033\/FEDER","PID2021-125258OB-I00","SGR2021-00643"]}]},{"name":"the Catalan Government","award":["MCIN\/AEI\/10.13039\/501100011033\/FEDER","PID2021-125258OB-I00","SGR2021-00643"],"award-info":[{"award-number":["MCIN\/AEI\/10.13039\/501100011033\/FEDER","PID2021-125258OB-I00","SGR2021-00643"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>This work presents a novel approach to rainfall\u2013runoff modeling. We incorporate GAN-based data compaction into a spatial-attention-enhanced transductive long short-term memory (TLSTM) network. The GAN component reduces data dimensions while retaining essential features. This compaction enables the TLSTM to capture complex temporal dependencies in rainfall\u2013runoff patterns more effectively. When tested on the CAMELS dataset, the model significantly outperforms benchmark LSTM-based models. For 8-day runoff forecasts, our model achieves an NSE of 0.536, compared to 0.326 from the closest competitor. The integration of GAN-based feature extraction with spatial attention mechanisms improves predictive accuracy, particularly for peak-flow events. This method offers a powerful solution for addressing current challenges in water resource management and disaster planning under extreme climate conditions.<\/jats:p>","DOI":"10.3390\/rs16203889","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T09:58:24Z","timestamp":1729504704000},"page":"3889","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Integration of Generative-Adversarial-Network-Based Data Compaction and Spatial Attention Transductive Long Short-Term Memory for Improved Rainfall\u2013Runoff Modeling"],"prefix":"10.3390","volume":"16","author":[{"given":"Bahareh","family":"Ghanati","sequence":"first","affiliation":[{"name":"Department of Information and Communications Engineering, Universitat Aut\u00f2noma de Barcelona, 08193 Bellaterra, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4729-9292","authenticated-orcid":false,"given":"Joan","family":"Serra-Sagrist\u00e0","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Universitat Aut\u00f2noma de Barcelona, 08193 Bellaterra, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,19]]},"reference":[{"key":"ref_1","first-page":"123","article-title":"A Hybrid Approach Combining Conceptual Hydrological Models, Support Vector Machines, and Remote Sensing Data for Rainfall-Runoff Modeling","volume":"12","author":"Smith","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_2","first-page":"4373","article-title":"Hydrologically informed machine learning for rainfall-runoff modelling: Towards distributed modelling","volume":"18","author":"Anderson","year":"2023","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"126353","DOI":"10.1016\/j.jhydrol.2021.126353","article-title":"A novel deep neural network architecture for real-time water demand forecasting","volume":"599","author":"Salloom","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"126067","DOI":"10.1016\/j.jhydrol.2021.126067","article-title":"Daily runoff forecasting by deep recursive neural network","volume":"596","author":"Zhang","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"126800","DOI":"10.1016\/j.jhydrol.2021.126800","article-title":"Long short-term memory neural network (LSTM-NN) for aquifer level time series forecasting using in-situ piezometric observations","volume":"601","author":"Solgi","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5517","DOI":"10.5194\/hess-25-5517-2021","article-title":"Benchmarking data-driven rainfall-runoff models in Great Britain: A comparison of long short-term memory (LSTM)-based models with four lumped conceptual models","volume":"25","author":"Lees","year":"2021","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"126636","DOI":"10.1016\/j.jhydrol.2021.126636","article-title":"A hybrid deep learning algorithm and its application to streamflow prediction","volume":"601","author":"Lin","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"126672","DOI":"10.1016\/j.jhydrol.2021.126672","article-title":"Multi-station runoff-sediment modeling using seasonal LSTM models","volume":"601","author":"Nourani","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"11344","DOI":"10.1029\/2019WR026065","article-title":"Toward improved predictions in ungauged basins: Exploiting the power of machine learning","volume":"55","author":"Kratzert","year":"2019","journal-title":"Water Resour. Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"126371","DOI":"10.1016\/j.jhydrol.2021.126371","article-title":"Fusing stacked autoencoder and long short-term memory for regional multistep-ahead flood inundation forecasts","volume":"598","author":"Kao","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput."},{"key":"ref_12","first-page":"473","article-title":"LSTM can solve hard long time lag problems","volume":"9","author":"Hochreiter","year":"1996","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, Z., Ding, C., Yuan, B., Qiu, Q., Wang, Y., and Liang, Y. (2018, January 25\u201327). C-LSTM: Enabling efficient LSTM using structured compression techniques on FPGAs. Proceedings of the 2018 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, CA, USA.","DOI":"10.1145\/3174243.3174253"},{"key":"ref_14","first-page":"e220036","article-title":"Emulating Rainfall-Runoff-Inundation Model Using Deep Neural Network with Dimensionality Reduction","volume":"2","author":"Momoi","year":"2023","journal-title":"Artif. Intell. Earth Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Young, S.R., Rose, D.C., Karnowski, T.P., Lim, S.-H., and Patton, R.M. (2015, January 15). Optimizing deep learning hyper-parameters through an evolutionary algorithm. Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, Austin, TX, USA.","DOI":"10.1145\/2834892.2834896"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhou, F., Chen, Y., and Liu, J. (2023). Application of a New Hybrid Deep Learning Model That Considers Temporal and Feature Dependencies in Rainfall\u2013Runoff Simulation. Remote Sens., 15.","DOI":"10.3390\/rs15051395"},{"key":"ref_17","first-page":"256","article-title":"Using Remote Sensing Techniques to Improve Hydrological Predictions in a Rapidly Changing World","volume":"15","author":"Zhang","year":"2021","journal-title":"Hydrol. Sci. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5293","DOI":"10.5194\/hess-21-5293-2017","article-title":"The CAMELS data set: Catchment attributes and meteorology for large-sample studies","volume":"21","author":"Addor","year":"2017","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_19","unstructured":"Thornton, P.E., Thornton, M.M., Mayer, B.W., Wei, Y., Devarakonda, R., Vose, R.S., and Cook, R.B. (2014). Daymet: Daily Surface Weather Data on a 1-Km Grid for North America, Version 2, Oak Ridge National Lab (ORNL)."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3237","DOI":"10.1175\/1520-0442(2002)015<3237:ALTHBD>2.0.CO;2","article-title":"A long-term hydrologically based dataset of land surface fluxes and states for the conterminous United States","volume":"15","author":"Maurer","year":"2002","journal-title":"J. Clim."},{"key":"ref_21","unstructured":"Massari, C., Brocca, L., Tarpanelli, A., and Moramarco, T. (2023). Data Assimilation of Satellite Soil Moisture into Rainfall-Runoff Modelling: A Complex Recipe?. Remote Sens., 15."},{"key":"ref_22","unstructured":"Khan, M., Rehman, N., and Hussain, A. (2023). Rainfall-Runoff Modeling Using Machine Learning in the Ungauged Urban Watershed of Quetta Valley, Balochistan (Pakistan), Springer."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1287\/ijoc.6.2.154","article-title":"Genetic algorithms and random keys for sequencing and optimization","volume":"6","author":"Bean","year":"1994","journal-title":"ORSA J. Comput."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shrestha, S.G., and Pradhanang, S.M. (2023). Performance of LSTM over SWAT in Rainfall-Runoff Modeling in a Small, Forested Watershed: A Case Study of Cork Brook, RI. Remote Sens., 15.","DOI":"10.3390\/w15234194"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1109\/4235.797971","article-title":"The Compact Genetic Algorithm","volume":"3","author":"Goldberg","year":"1999","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv.","DOI":"10.1007\/978-3-642-24797-2_3"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.5194\/hess-23-2601-2019","article-title":"On the choice of calibration metrics for \u201chigh-flow\u201d estimation using hydrologic models","volume":"23","author":"Mizukami","year":"2019","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"127781","DOI":"10.1016\/j.jhydrol.2022.127781","article-title":"RR-Former: Rainfall-runoff modeling based on Transformer","volume":"609","author":"Yin","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e2019WR025326","DOI":"10.1029\/2019WR025326","article-title":"A rainfall-runoff model with LSTM-based sequence-to-sequence learning","volume":"56","author":"Xiang","year":"2020","journal-title":"Water Resour. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"126378","DOI":"10.1016\/j.jhydrol.2021.126378","article-title":"Rainfall-runoff modeling using LSTM-based multi-state-vector sequence-to-sequence model","volume":"598","author":"Yin","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1002\/hyp.11476","article-title":"Upper and lower benchmarks in hydrological modelling","volume":"32","author":"Seibert","year":"2018","journal-title":"Hydrol. Process."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"13991","DOI":"10.1029\/2019JD030767","article-title":"Diagnostic evaluation of large-domain hydrologic models calibrated across the contiguous United States","volume":"124","author":"Rakovec","year":"2019","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"8020","DOI":"10.1002\/2017WR020401","article-title":"Towards seamless large-domain parameter estimation for hydrologic models","volume":"53","author":"Mizukami","year":"2017","journal-title":"Water Resour. Res."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.1175\/JHM-D-16-0284.1","article-title":"Benchmarking of a physically based hydrologic model","volume":"18","author":"Newman","year":"2017","journal-title":"J. Hydrometeorol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e2019WR026793","DOI":"10.1029\/2019WR026793","article-title":"Enhancing Streamflow Forecast and Extracting Insights Using Long-Short Term Memory Networks with Data Integration at Continental Scales","volume":"56","author":"Feng","year":"2020","journal-title":"Water Resour. Res."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/20\/3889\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:16:45Z","timestamp":1760113005000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/20\/3889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,19]]},"references-count":35,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["rs16203889"],"URL":"https:\/\/doi.org\/10.3390\/rs16203889","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2024,10,19]]}}}