{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T14:35:11Z","timestamp":1761921311235,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology","doi-asserted-by":"publisher","award":["UIDB\/04625\/2020"],"award-info":[{"award-number":["UIDB\/04625\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Hydrology"],"abstract":"<jats:p>The transformative potential of deep learning models is felt in many research fields, including hydrology and water resources. This study investigates the effectiveness of the Temporal Fusion Transformer (TFT), a deep neural network architecture for predicting daily streamflow in Portugal, and benchmarks it against the popular Hydrologiska Byr\u00e5ns Vattenbalansavdelning (HBV) hydrological model. Additionally, it evaluates the performance of TFTs through selected forecasting examples. Information is provided about key input variables, including precipitation, temperature, and geomorphological characteristics. The study involved extensive hyperparameter tuning, with over 600 simulations conducted to fine\u2013tune performances and ensure reliable predictions across diverse hydrological conditions. The results showed that TFTs outperformed the HBV model, successfully predicting streamflow in several catchments of distinct characteristics throughout the country. TFTs not only provide trustworthy predictions with associated probabilities of occurrence but also offer considerable advantages over classical forecasting frameworks, i.e., the ability to model complex temporal dependencies and interactions across different inputs or weight features based on their relevance to the target variable. Multiple practical applications can rely on streamflow predictions made with TFT models, such as flood risk management, water resources allocation, and support climate change adaptation measures.<\/jats:p>","DOI":"10.3390\/hydrology11120217","type":"journal-article","created":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T06:50:44Z","timestamp":1734591044000},"page":"217","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep Learning Prediction of Streamflow in Portugal"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6266-020X","authenticated-orcid":false,"given":"Rafael","family":"Francisco","sequence":"first","affiliation":[{"name":"Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049\u2013001 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4592-1455","authenticated-orcid":false,"given":"Jos\u00e9 Pedro","family":"Matos","sequence":"additional","affiliation":[{"name":"Civil Engineering Research and Innovation for Sustainability (CERIS), Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049\u2013001 Lisboa, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2024,12,19]]},"reference":[{"key":"ref_1","unstructured":"United Nations Department of Economic and Social Affairs, and International River Foundation (2024, October 25). Thriving and Resilient Rivers for Future Generations\u2014Addressing the Global Water Challenge. Sustainable Development. Available online: https:\/\/sdgs.un.org\/partnerships\/thriving-and-resilient-rivers-future-generations-addressing-global-water-challenges#description."},{"key":"ref_2","unstructured":"Ritchie, H., Rod\u00e9s-Guirao, L., Mathieu, E., Gerber, M., Ortiz-Ospina, E., Hasell, J., and Roser, M. (2024, May 06). Population Growth. OurWorldInData.Org. Available online: https:\/\/ourworldindata.org\/population-growth."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100123","DOI":"10.1016\/j.pdisas.2020.100123","article-title":"Water-related disasters and their health impacts: A global review","volume":"8","author":"Lee","year":"2020","journal-title":"Prog. Disaster Sci."},{"key":"ref_4","unstructured":"Kuzma, S., and Luo, T. (2020). The Number of People Affected by Floods Will Double Between 2010 and 2030, Word Resources Institute. Available online: https:\/\/www.wri.org\/insights\/number-people-affected-floods-will-double-between-2010-and-2030."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1002\/2016EF000485","article-title":"Global projections of river flood risk in a warmer world","volume":"5","author":"Alfieri","year":"2017","journal-title":"Earth\u2019s Future"},{"key":"ref_6","unstructured":"Camilo, D. (2024, May 05). Cheias Fizeram 293 Milh\u00f5es de Euros de Preju\u00edzos. Governo Anuncia 185 Milh\u00f5es em Apoios. Renascen\u00e7a. Available online: https:\/\/rr.sapo.pt\/noticia\/economia\/2023\/01\/12\/cheias-fizeram-293-milhoes-de-euros-de-prejuizos-governo-anuncia-185-milhoes-em-apoios\/315654\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_8","unstructured":"Centre de Recherche sur L\u2019environnement Alpin (CREALP), and HydroCosmos SA (2024, April 07). RS Minerve v. 2.9.1.0 (Software). Available online: https:\/\/www.crealp.ch\/en\/rs-minerve-software\/."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"131301","DOI":"10.1016\/j.jhydrol.2024.131301","article-title":"Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence","volume":"637","author":"Koya","year":"2024","journal-title":"J. Hydrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101665","DOI":"10.1016\/j.rineng.2023.101665","article-title":"Flood hazards and susceptibility detection for Ganga river, Bihar state, India: Employment of remote sensing and statistical approaches","volume":"21","author":"Yaseen","year":"2024","journal-title":"Results Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"171489","DOI":"10.1016\/j.scitotenv.2024.171489","article-title":"Prolonged drought periods over the last four decades increase flood intensity in southern Africa","volume":"924","author":"Franchi","year":"2024","journal-title":"Sci. Total Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1186\/s12302-022-00685-1","article-title":"Assessment of the 2021 summer flood in Central Europe","volume":"34","author":"Lehmkuhl","year":"2022","journal-title":"Environ. Sci. Eur. (Ed.)"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"130688","DOI":"10.1016\/j.jhydrol.2024.130688","article-title":"Impacts of climate change on flood volumes over North American catchments","volume":"630","author":"Ionno","year":"2024","journal-title":"J. Hydrol."},{"key":"ref_14","unstructured":"Buschschl\u00fcter, V. (2024, May 17). Brazil Floods: Hundreds of Rio Grande do Sul Towns Under Water. BBC News, Available online: https:\/\/www.bbc.com\/news\/world-latin-america-68968987."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"265","DOI":"10.5194\/hess-26-265-2022","article-title":"Ensemble streamflow forecasting over a cascade reservoir catchment with integrated hydrometeorological modeling and machine learning","volume":"26","author":"Liu","year":"2022","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Dick, S. (2019). Artificial Intelligence. HDSR, 1.","DOI":"10.1162\/99608f92.92fe150c"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hunter, B., Hindocha, S., and Lee, R.W. (2022). The Role of Artificial Intelligence in Early Cancer Diagnosis. Cancers, 14.","DOI":"10.3390\/cancers14061524"},{"key":"ref_19","first-page":"362","article-title":"A survey of deep learning techniques for autonomous driving","volume":"37","author":"Grigorescu","year":"2019","journal-title":"J. Robot. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"77364","DOI":"10.1109\/ACCESS.2020.2990123","article-title":"Artificial Intelligence for Smart Renewable Energy Sector in Europe\u2014Smart Energy Infrastructures for Next Generation Smart Cities","volume":"8","author":"Lytras","year":"2020","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chang, F.-J., Chang, L.-C., and Chen, J.-F. (2023). Artificial Intelligence Techniques in Hydrology and Water Resources Management. Water, 15.","DOI":"10.3390\/books978-3-0365-7784-5"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"104572","DOI":"10.1016\/j.autcon.2022.104572","article-title":"Fast identification of concrete cracks using 1D deep learning and explainable artificial intelligence-based analysis","volume":"143","author":"Geetha","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kim, Y.I., Park, W.H., Shin, Y., Park, J.-W., Engel, B., Yun, Y.-J., and Jang, W.S. (2024). Applications of Machine Learning and Remote Sensing in Soil and Water Conservation. Hydrology, 11.","DOI":"10.20944\/preprints202410.0048.v1"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s43503-024-00029-3","article-title":"Predicting the compressive strength of self-compacting concrete using artificial intelligence techniques: A review","volume":"3","author":"Terlumun","year":"2024","journal-title":"AI Civ. Eng."},{"key":"ref_25","unstructured":"Chollet, F. (2021). Deep Learning with Python, Manning Publications. [2nd ed.]."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kadiyala, L.A., Mermer, O., Samuel, D.J., Sermet, Y., and Demir, I. (2024). The Implementation of Multimodal Large Language Models for Hydrological Applications: A Comparative Study of GPT-4 Vision, Gemini, LLaVa, and Multimodal-GPT. Hydrology, 11.","DOI":"10.3390\/hydrology11090148"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Mohammadi, B. (2023). Modeling Various Drought Time Scales via a Merged Artificial Neural Network with a Firefly Algorithm. Hydrology, 10.","DOI":"10.3390\/hydrology10030058"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mehedi, M.A.A., Khosravi, M., Yazdan, M.M.S., and Shabanian, H. (2022). Exploring Temporal Dynamics of River Discharge Using Univariate Long Short-Term Memory (LSTM) Recurrent Neural Network at East Branch of Delaware River. Hydrology, 9.","DOI":"10.20944\/preprints202209.0398.v1"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Dabire, N., Ezin, E.C., and Firmin, A.M. (2024). Forecasting Lake Nokou\u00e9 Water Levels Using Long Short-Term Memory Network. Hydrology, 11.","DOI":"10.20944\/preprints202403.1218.v1"},{"key":"ref_30","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_31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. Available online: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf."},{"key":"ref_32","unstructured":"Sistema Nacional de Recursos H\u00eddricos (Ag\u00eancia Portuguesa do Ambiente) (2024, March 21). Daily Streamflow Records [Data Set]. Available online: https:\/\/snirh.apambiente.pt\/."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4349","DOI":"10.5194\/essd-13-4349-2021","article-title":"ERA5-Land: A State-of-the-Art Global Reanalysis Dataset for Land Applications","volume":"13","author":"Dutra","year":"2021","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6643","DOI":"10.1002\/joc.8225","article-title":"A first assessment of ERA5 and ERA5-Land reanalysis air temperature in Portugal","volume":"43","author":"Almeida","year":"2023","journal-title":"Int. J. Clim."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"100448","DOI":"10.1016\/j.wace.2022.100448","article-title":"Extreme heat events in the Iberia Peninsula from extreme value mixture modeling of ERA5-Land air temperature","volume":"36","author":"Barbosa","year":"2022","journal-title":"Weather. Clim. Extrem."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1061\/JRCEA4.0001390","article-title":"Estimating Potential Evapotranspiration","volume":"108","author":"Hargreaves","year":"1982","journal-title":"J. Irrig. Drain. Div."},{"key":"ref_37","unstructured":"U.S. National Centers for Environmental Prediction (NCEP) (2024, October 01). Global Forecasting System Documentation, Available online: https:\/\/www.emc.ncep.noaa.gov\/emc\/pages\/numerical_forecast_systems\/gfs.php."},{"key":"ref_38","first-page":"1","article-title":"Development and Application of a Conceptual Runoff Model for Scandinavian Catchments","volume":"134","year":"1976","journal-title":"SMHI Rep. RHO 7"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/S0022-1694(97)00041-3","article-title":"Development and Test of the Distributed HBV-96 Hydrological Model","volume":"201","author":"Johansson","year":"1997","journal-title":"J. Hydrol."},{"key":"ref_40","unstructured":"Oreshkin, B.N., Carpov, D., and Smelyanskiy, M. (2020). PyTorch Forecasting: A Package for Time Series Forecasting with Deep Learning, GitHub Repository. Available online: https:\/\/github.com\/jdb78\/pytorch-forecasting."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/0022-1694(70)90255-6","article-title":"River Flow Forecasting through Conceptual Models Part I\u2014A Discussion of Principles","volume":"10","author":"Nash","year":"1970","journal-title":"J. Hydrol."},{"key":"ref_42","first-page":"559","article-title":"Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems","volume":"15","author":"Hersbach","year":"2000","journal-title":"WAF"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3253","DOI":"10.5194\/hess-15-3253-2011","article-title":"Recent Developments in Predictive Uncertainty Assessment Based on the Model Conditional Processor Approach","volume":"15","author":"Coccia","year":"2011","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2009WR008328","article-title":"Understanding Predictive Uncertainty in Hydrologic Modeling: The Challenge of Identifying Input and Structural Errors","volume":"46","author":"Renard","year":"2010","journal-title":"Water Resour. Res."},{"key":"ref_45","unstructured":"Portuguese Ministry of Foreign Affairs (2024, May 07). About Portugal\u2014Diplomatic Portal, Available online: https:\/\/portaldiplomatico.mne.gov.pt\/en\/about-portugal."},{"key":"ref_46","unstructured":"European Space Agency (ESA) (2019). Copernicus DEM GLO-30 (Raster), European Space Agency."},{"key":"ref_47","unstructured":"OpenStreetMap Contributors (2024, November 14). OpenStreetMap Portugal continental e Madeira: Water Bodies. OpenStreetMap. Available online: https:\/\/www.openstreetmap.org."},{"key":"ref_48","unstructured":"Assembleia da Rep\u00fablica (2005). Republic Diary No. 249\/2005. Di\u00e1rio Rep\u00fablica Ser. I, 58, 7280\u20137310. Available online: https:\/\/diariodarepublica.pt\/dr\/detalhe\/lei\/58-2005-469068."},{"key":"ref_49","unstructured":"Esri Inc (2024). ArcGIS Pro (v. 3.1), Esri Inc.. Available online: https:\/\/www.esri.com\/en-us\/arcgis\/products\/arcgis-pro."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1038\/s41597-023-02008-2","article-title":"Global Dam Tracker: A Database of More than 35,000 Dams with Location, Catchment, and Attribute Information","volume":"10","author":"Zhang","year":"2023","journal-title":"Sci. Data"},{"key":"ref_51","unstructured":"European Environment Agency (EEA) (2018). Copernicus CORINE Land Cover (Vector), European Environment Agency."},{"key":"ref_52","unstructured":"Beitner, J. (2024, June 18). PyTorch Forecasting Documentation: TemporalFusionTransformer. Available online: https:\/\/pytorch-forecasting.readthedocs.io\/en\/stable\/api\/pytorch_forecasting.models.temporal_fusion_transformer.TemporalFusionTransformer.html#pytorch_forecasting.models.temporal_fusion_transformer.TemporalFusionTransformer."},{"key":"ref_53","unstructured":"Falcon, W., and PyTorch Lightning Team (2023). PyTorch Lightning Documentation 2.2.5: Trainer, Available online: https:\/\/lightning.ai\/docs\/pytorch\/stable\/common\/trainer.html#."}],"container-title":["Hydrology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5338\/11\/12\/217\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:55:26Z","timestamp":1760115326000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5338\/11\/12\/217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,19]]},"references-count":53,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["hydrology11120217"],"URL":"https:\/\/doi.org\/10.3390\/hydrology11120217","relation":{},"ISSN":["2306-5338"],"issn-type":[{"type":"electronic","value":"2306-5338"}],"subject":[],"published":{"date-parts":[[2024,12,19]]}}}