Publication:
Investigation of cross-entropy-based streamflow forecasting through an efficient interpretable automated search process

Simple item page
dc.citedby14
dc.contributor.authorChong K.L.en_US
dc.contributor.authorHuang Y.F.en_US
dc.contributor.authorKoo C.H.en_US
dc.contributor.authorSherif M.en_US
dc.contributor.authorAhmed A.N.en_US
dc.contributor.authorEl-Shafie A.en_US
dc.contributor.authorid57208482172en_US
dc.contributor.authorid55807263900en_US
dc.contributor.authorid57204843657en_US
dc.contributor.authorid7005414714en_US
dc.contributor.authorid57214837520en_US
dc.contributor.authorid16068189400en_US
dc.date.accessioned2024-10-14T03:21:36Z
dc.date.available2024-10-14T03:21:36Z
dc.date.issued2023
dc.description.abstractStreamflow forecasting has always been important in water resources management, particularly the peak flow, which often determines the seriousness of the impending flood. However, the highly imbalanced flow distribution often hinders the machine learning algorithm's performance. In this paper, streamflow forecasting was approached through the formulation of two distinct machine learning problems: categorical streamflow forecast and regression streamflow forecast. Due to the distinctive characteristics of these two adopted forms, selecting the correct algorithm for the machine learning problem along with their hyperparameter tuning process is critical to the realization of the desired results. For the distinct streamflow formulated scenarios, three neural network algorithms and their hyperparameter tuning strategy were investigated. The comparative empirical studies had revealed that formulated categorical-based streamflow forecast is a better choice than a regression-based streamflow forecast, regardless of the algorithms useden_US
dc.description.abstractfor instance, the f1-score of 0.7 (categorical based) is obtained compared to the 0.53 (regression based) for the LSTM in scenario 1 (binary). Furthermore, forest-based algorithms were investigated and shown to be superior at forecasting high streamflow fluctuations in situations featuring low-dimensional streamflow input. Besides, encoding the streamflow time series as images (input) for forecasting purposes would require a thorough analysis as there is a discrepancy in the results, revealing that not all approaches are suitable for streamflow image transformation. The functional ANOVA analysis provided evidence to substantiate the Bayesian optimization results, implying that the hyperparameters were effectively optimized. � 2022, The Author(s).en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo6
dc.identifier.doi10.1007/s13201-022-01790-5
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85141876820
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85141876820&doi=10.1007%2fs13201-022-01790-5&partnerID=40&md5=9db022d5eb620b7cf3a1e17f2ae136f7
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/34670
dc.identifier.volume13
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.relation.ispartofAll Open Access
dc.relation.ispartofGold Open Access
dc.sourceScopus
dc.sourcetitleApplied Water Science
dc.subjectDeep learning algorithms
dc.subjectHyperparameter optimization
dc.subjectMachine learning algorithms
dc.subjectStreamflow forecasting
dc.subjectForecasting
dc.subjectLong short-term memory
dc.subjectRegression analysis
dc.subjectStream flow
dc.subjectTime series analysis
dc.subjectWater resources
dc.subjectAutomated searches
dc.subjectCross entropy
dc.subjectDeep learning algorithm
dc.subjectEntropy-based
dc.subjectHyper-parameter
dc.subjectHyper-parameter optimizations
dc.subjectMachine learning algorithms
dc.subjectMachine learning problem
dc.subjectStreamflow forecast
dc.subjectStreamflow forecasting
dc.subjectalgorithm
dc.subjectempirical analysis
dc.subjectentropy
dc.subjectmachine learning
dc.subjectoptimization
dc.subjectpeak flow
dc.subjectstreamflow
dc.subjectwater management
dc.subjectLearning algorithms
dc.titleInvestigation of cross-entropy-based streamflow forecasting through an efficient interpretable automated search processen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS