{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T19:53:38Z","timestamp":1772567618293,"version":"3.50.1"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100010785","name":"Canada First Research Excellence Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Environmental Modelling &amp; Software"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1016\/j.envsoft.2020.104926","type":"journal-article","created":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T12:02:52Z","timestamp":1605268972000},"page":"104926","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":124,"special_numbering":"C","title":["The proper care and feeding of CAMELS: How limited training data affects streamflow prediction"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4587-898X","authenticated-orcid":false,"given":"Martin","family":"Gauch","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1132-2342","authenticated-orcid":false,"given":"Juliane","family":"Mai","sequence":"additional","affiliation":[]},{"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.envsoft.2020.104926_bib1","doi-asserted-by":"crossref","first-page":"8792","DOI":"10.1029\/2018WR022606","article-title":"A ranking of hydrological signatures based on their predictability in space","volume":"54","author":"Addor","year":"2018","journal-title":"Water Resour. Res."},{"key":"10.1016\/j.envsoft.2020.104926_bib2","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":"10.1016\/j.envsoft.2020.104926_bib3","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/0893-6080(93)90013-M","article-title":"A universal theorem on learning curves","volume":"6","author":"Amari","year":"1993","journal-title":"Neural Network."},{"key":"10.1016\/j.envsoft.2020.104926_bib4","series-title":"Proceedings of the First International Conference on Human Language Technology Research","first-page":"1","article-title":"Mitigating the paucity-of-data problem: exploring the effect of training corpus size on classifier performance for natural language processing","author":"Banko","year":"2001"},{"key":"10.1016\/j.envsoft.2020.104926_bib5","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1175\/JHM-D-14-0158.1","article-title":"The plumbing of land surface models: benchmarking model performance","volume":"16","author":"Best","year":"2015","journal-title":"J. Hydrometeorol."},{"key":"10.1016\/j.envsoft.2020.104926_bib6","series-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"10.1016\/j.envsoft.2020.104926_bib7","series-title":"Statistical Power Analysis for the Behavioral Sciences","author":"Cohen","year":"2013"},{"key":"10.1016\/j.envsoft.2020.104926_bib8","first-page":"293","article-title":"Application of machine learning approaches in rainfall-runoff modeling (case study: zayandeh Rood basin in Iran)","volume":"51","author":"Dastorani","year":"2018","journal-title":"Civ. Eng. Infrastruct. J."},{"key":"10.1016\/j.envsoft.2020.104926_bib9","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1080\/02626669809492102","article-title":"An artificial neural network approach to rainfall-runoff modelling","volume":"43","author":"Dawson","year":"1998","journal-title":"Hydrol. Sci. J."},{"key":"10.1016\/j.envsoft.2020.104926_bib10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S1464-1909(01)85005-X","article-title":"River flow forecasting using artificial neural networks","volume":"26","author":"Dibike","year":"2001","journal-title":"Phys. Chem. Earth - Part B Hydrol., Oceans Atmos."},{"key":"10.1016\/j.envsoft.2020.104926_bib11","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1126\/science.aac7358","article-title":"Time for in situ renaissance","volume":"349","author":"Fekete","year":"2015","journal-title":"Science"},{"key":"10.1016\/j.envsoft.2020.104926_bib12","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"10.1016\/j.envsoft.2020.104926_bib13","series-title":"Proceedings of the NeurIPS 2019 Workshop on Tackling Climate Change with Machine Learning","article-title":"Streamflow prediction with limited spatially-distributed input data","author":"Gauch","year":"2019"},{"key":"10.1016\/j.envsoft.2020.104926_bib14","article-title":"Data-driven vs. physically-based streamflow prediction models","author":"Gauch","year":"2019","journal-title":"Proceedings of 9th International Workshop on Climate Informatics"},{"key":"10.1016\/j.envsoft.2020.104926_bib15","series-title":"The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction","author":"Gauch","year":"2019"},{"key":"10.1016\/j.envsoft.2020.104926_bib16","series-title":"Deep Learning Scaling Is Predictable, Empirically","author":"Hestness","year":"2017"},{"key":"10.1016\/j.envsoft.2020.104926_bib17","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.envsoft.2020.104926_bib18","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.3390\/w10111543","article-title":"Deep learning with a Long Short-Term Memory networks approach for rainfall-runoff simulation","volume":"10","author":"Hu","year":"2018","journal-title":"Water"},{"key":"10.1016\/j.envsoft.2020.104926_bib20","series-title":"Grupo bimbo inventory demand, winners' interview: clustifier & alex & andrey. No free hunch","year":"2016"},{"key":"10.1016\/j.envsoft.2020.104926_bib21","series-title":"Rossmann store sales, winner's interview: 2nd place, Nima Shahbazi. No Free Hunch","year":"2016"},{"key":"10.1016\/j.envsoft.2020.104926_bib22","doi-asserted-by":"crossref","first-page":"6005","DOI":"10.5194\/hess-22-6005-2018","article-title":"Rainfall--runoff modelling using long short-term memory (LSTM) networks","volume":"22","author":"Kratzert","year":"2018","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"10.1016\/j.envsoft.2020.104926_bib23","first-page":"1","article-title":"Benchmarking a catchment-aware Long Short-Term Memory network (LSTM) for large-scale hydrological modeling","author":"Kratzert","year":"2019","journal-title":"Hydrol. Earth Syst. Sci. Discuss."},{"key":"10.1016\/j.envsoft.2020.104926_bib24","series-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM","first-page":"1842","article-title":"AccuAir: winning solution to air quality prediction for KDD Cup 2018","author":"Luo","year":"2019"},{"key":"10.1016\/j.envsoft.2020.104926_bib25","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":"10.1016\/j.envsoft.2020.104926_bib26","series-title":"Econometric Foundations","first-page":"73","author":"Mittelhammer","year":"2000"},{"key":"10.1016\/j.envsoft.2020.104926_bib27","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.5194\/hess-23-2601-2019","article-title":"On the choice of calibration metrics for \u2018\u2018high-flow\u2019\u2019 estimation using hydrologic models","volume":"23","author":"Mizukami","year":"2019","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"10.1016\/j.envsoft.2020.104926_bib28","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":"10.1016\/j.envsoft.2020.104926_bib29","series-title":"A large-sample watershed-scale hydrometeorological dataset for the contiguous USA","author":"Newman","year":"2014"},{"key":"10.1016\/j.envsoft.2020.104926_bib30","doi-asserted-by":"crossref","first-page":"597","DOI":"10.22237\/jmasm\/1257035100","article-title":"New effect size rules of thumb","volume":"8","author":"Sawilowsky","year":"2009","journal-title":"J. Mod. Appl. Stat. Methods"}],"container-title":["Environmental Modelling &amp; Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136481522030983X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136481522030983X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T23:05:45Z","timestamp":1761260745000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S136481522030983X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":29,"alternative-id":["S136481522030983X"],"URL":"https:\/\/doi.org\/10.1016\/j.envsoft.2020.104926","relation":{},"ISSN":["1364-8152"],"issn-type":[{"value":"1364-8152","type":"print"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"The proper care and feeding of CAMELS: How limited training data affects streamflow prediction","name":"articletitle","label":"Article Title"},{"value":"Environmental Modelling & Software","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.envsoft.2020.104926","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2020 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"104926"}}