{"id":"https://openalex.org/W7140572355","doi":"https://doi.org/10.2166/ws.2026.134","title":"Online versus batch retraining in one-step-ahead urban water demand forecasting under concept drift","display_name":"Online versus batch retraining in one-step-ahead urban water demand forecasting under concept drift","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7140572355","doi":"https://doi.org/10.2166/ws.2026.134"},"language":"en","primary_location":{"id":"doi:10.2166/ws.2026.134","doi":"https://doi.org/10.2166/ws.2026.134","is_oa":false,"landing_page_url":"https://doi.org/10.2166/ws.2026.134","pdf_url":null,"source":{"id":"https://openalex.org/S124453322","display_name":"Water Science & Technology Water Supply","issn_l":"1606-9749","issn":["1606-9749","1607-0798"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","ki-jl-1","norway-1","oarl","poland-20","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310320298","host_organization_name":"IWA Publishing","host_organization_lineage":["https://openalex.org/P4310320298"],"host_organization_lineage_names":["IWA Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Water Supply","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093048889","display_name":"Lukas Hans","orcid":"https://orcid.org/0009-0003-0830-1801","observed_orcids":["https://orcid.org/0009-0003-0830-1801"]},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Lukas Hans","raw_affiliation_strings":["a Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen 9700 AB, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0003-0830-1801","affiliations":[{"raw_affiliation_string":"a Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen 9700 AB, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010708932","display_name":"Dietlind Z\u00fchlke","orcid":"https://orcid.org/0000-0003-3751-5887","observed_orcids":["https://orcid.org/0000-0003-3751-5887"]},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dietlind Z\u00fchlke","raw_affiliation_strings":["b Institute of Data Science, Engineering, and Analytics, University of Applied Sciences Cologne, K\u00f6ln 50678, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3751-5887","affiliations":[{"raw_affiliation_string":"b Institute of Data Science, Engineering, and Analytics, University of Applied Sciences Cologne, K\u00f6ln 50678, Germany","institution_ids":["https://openalex.org/I102520234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093048889"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11389537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"4","first_page":"255","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11490","display_name":"Hydrological Forecasting Using AI","score":0.8062000274658203,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11490","display_name":"Hydrological Forecasting Using AI","score":0.8062000274658203,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.09619999676942825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10969","display_name":"Water resources management and optimization","score":0.025100000202655792,"subfield":{"id":"https://openalex.org/subfields/2312","display_name":"Water Science and Technology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/urban-water-demand-forecasting","display_name":"urban water demand forecasting","score":0.9760000109672546},{"id":"https://openalex.org/keywords/concept-drift","display_name":"concept drift","score":0.8579999804496765},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.8180000185966492},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"incremental learning","score":0.8489999771118164},{"id":"https://openalex.org/keywords/one-hour-ahead-forecasting","display_name":"one-hour-ahead forecasting","score":0.6899999976158142},{"id":"https://openalex.org/keywords/nonstationarity","display_name":"non-stationarity","score":0.7760000228881836},{"id":"https://openalex.org/keywords/accuracy-latency-trade-off","display_name":"accuracy-latency trade-off","score":0.8130000233650208},{"id":"https://openalex.org/keywords/ensemble-averaging","display_name":"ensemble averaging","score":0.5770000219345093},{"id":"https://openalex.org/keywords/water-utility-operations","display_name":"water utility operations","score":0.5879999995231628},{"id":"https://openalex.org/keywords/diebold-mariano-test","display_name":"Diebold-Mariano test","score":0.902999997138977}],"concepts":[{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6837000250816345},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.598800003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5282999873161316},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C175706884","wikidata":"https://www.wikidata.org/wiki/Q1130194","display_name":"Moving average","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.37310001254081726},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C112353543","wikidata":"https://www.wikidata.org/wiki/Q5468162","display_name":"Forecast period","level":4,"score":0.3379000127315521},{"id":"https://openalex.org/C51865526","wikidata":"https://www.wikidata.org/wiki/Q5379962","display_name":"Ensemble average","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C2781468064","wikidata":"https://www.wikidata.org/wiki/Q1267117","display_name":"Lead time","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25999999046325684},{"id":"https://openalex.org/C193809577","wikidata":"https://www.wikidata.org/wiki/Q3409300","display_name":"Demand forecasting","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2166/ws.2026.134","doi":"https://doi.org/10.2166/ws.2026.134","is_oa":false,"landing_page_url":"https://doi.org/10.2166/ws.2026.134","pdf_url":null,"source":{"id":"https://openalex.org/S124453322","display_name":"Water Science & Technology Water Supply","issn_l":"1606-9749","issn":["1606-9749","1607-0798"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","ki-jl-1","norway-1","oarl","poland-20","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310320298","host_organization_name":"IWA Publishing","host_organization_lineage":["https://openalex.org/P4310320298"],"host_organization_lineage_names":["IWA Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Water Supply","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/6","score":0.53329998254776,"display_name":"Clean water and sanitation"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1558793738","https://openalex.org/W1974853958","https://openalex.org/W1975994995","https://openalex.org/W2001168879","https://openalex.org/W2017706744","https://openalex.org/W2022775778","https://openalex.org/W2117922789","https://openalex.org/W2146574767","https://openalex.org/W2152323380","https://openalex.org/W2612169505","https://openalex.org/W2754358410","https://openalex.org/W2909693411","https://openalex.org/W2982404449","https://openalex.org/W3095637457","https://openalex.org/W3125947621","https://openalex.org/W4225295290","https://openalex.org/W4291327732","https://openalex.org/W4294958547","https://openalex.org/W4390817916","https://openalex.org/W4392241617","https://openalex.org/W4398142120","https://openalex.org/W4399533101","https://openalex.org/W4400370012","https://openalex.org/W4402023304","https://openalex.org/W4403398881"],"related_works":["https://openalex.org/W2469207380","https://openalex.org/W4399171323","https://openalex.org/W4410445597","https://openalex.org/W7160325768","https://openalex.org/W7133202859","https://openalex.org/W7222947793","https://openalex.org/W7066660010","https://openalex.org/W7215118032","https://openalex.org/W4387076452","https://openalex.org/W2352469340"],"abstract_inverted_index":{"ABSTRACT":[0],"Graphical":[1],"abstract":[2],"combining":[3],"two":[4,190],"example":[5],"water-demand":[6],"time-series":[7],"under":[8,107,155],"concept":[9],"drift":[10,195,198,269],"with":[11,27,40,78,89,110,193,268],"a":[12,25,37,124,129],"comparison":[13],"of":[14,52,56,62,117,206],"forecast":[15],"accuracy":[16,88,161,248],"and":[17,30,54,120,139,157,170,214,245,264,277],"runtime.":[18],"The":[19],"top":[20],"panel":[21,33],"shows":[22,34,67],"Area":[23,35,234,250],"1,":[24,235],"period":[26,39],"reduced":[28],"variability,":[29],"the":[31,79,83,182,211,230,236,258,272],"second":[32],"2,":[36,251],"shape-change":[38],"changing":[41],"demand":[42,105,284],"patterns":[43],"over":[44],"time.":[45],"Two":[46],"summary":[47],"boxes":[48],"report":[49],"average":[50,63],"MAE":[51,64],"391.2":[53],"runtime":[55,66,179],"27.6":[57],"seconds.":[58],"A":[59],"scatter":[60],"plot":[61],"versus":[65,199,243],"online":[68,203,231,237],"models":[69,140,225],"clustered":[70],"at":[71],"much":[72],"lower":[73],"runtimes":[74],"than":[75],"batch":[76,112,153,224,254,279],"models,":[77],"Online":[80],"Ensemble":[81],"near":[82],"lower-left":[84],"region,":[85],"indicating":[86],"strong":[87,247],"high":[90],"computational":[91,265],"efficiency.":[92],"This":[93],"study":[94],"examines":[95],"whether":[96],"incremental":[97,208,275],"learning":[98],"yields":[99],"operationally":[100],"superior":[101],"1-hour-ahead":[102],"urban":[103],"water":[104,283],"forecasts":[106,135],"nonstationarity":[108],"compared":[109],"periodic":[111,278],"retraining.":[113],"Using":[114],"6":[115],"years":[116],"hourly":[118],"consumption":[119],"meteorological":[121],"data":[122],"from":[123,229],"German":[125],"utility,":[126],"we":[127,173],"conduct":[128],"deployment-faithful":[130],"prequential":[131],"evaluation":[132,191],"in":[133,233,249,281],"which":[134],"are":[136,141,226],"generated":[137],"sequentially,":[138],"updated":[142],"either":[143],"(i)":[144],"incrementally":[145],"after":[146],"each":[147],"observation":[148],"or":[149],"(ii)":[150],"via":[151,177],"weekly":[152],"retraining":[154,280],"rolling":[156],"expanding":[158],"windows.":[159],"Beyond":[160],"[mean":[162],"absolute":[163],"error":[164,168],"(MAE)/root":[165],"mean":[166],"squared":[167],"(RMSE)":[169],"Diebold\u2013Mariano":[171],"tests],":[172],"quantify":[174],"update":[175],"efficiency":[176],"end-to-end":[178],"to":[180],"characterize":[181],"accuracy-latency":[183],"trade-off":[184],"relevant":[185],"for":[186],"real-time":[187],"operation.":[188],"Across":[189],"areas":[192],"distinct":[194],"signatures":[196],"(variance/level":[197],"distributional/shape":[200],"drift),":[201],"an":[202],"averaging":[204],"ensemble":[205,232,238],"three":[207],"learners":[209],"achieves":[210],"lowest":[212],"MAE/RMSE":[213],"mitigates":[215],"high-error":[216],"episodes":[217],"that":[218],"dominate":[219],"RMSE.":[220],"While":[221],"several":[222],"expanding-window":[223],"statistically":[227],"indistinguishable":[228],"remains":[239],"consistently":[240],"faster":[241],"(seconds":[242],"minutes/hours)":[244],"retains":[246],"where":[252],"most":[253],"baselines":[255],"degrade.":[256],"Overall,":[257],"findings":[259],"clarify":[260],"how":[261],"adaptation":[262],"speed":[263],"cost":[266],"interact":[267],"intensity,":[270],"informing":[271],"choice":[273],"between":[274],"updating":[276],"operational":[282],"forecasting.":[285]},"counts_by_year":[],"updated_date":"2026-07-07T06:14:10.401900","created_date":"2026-03-27T00:00:00"}