Publication:
Flood mapping based on novel ensemble modeling involving the deep learning, Harris Hawk optimization algorithm and stacking based machine learning

Simple item page
dc.citedby8
dc.contributor.authorCostache R.en_US
dc.contributor.authorPal S.C.en_US
dc.contributor.authorPande C.B.en_US
dc.contributor.authorIslam A.R.M.T.en_US
dc.contributor.authorAlshehri F.en_US
dc.contributor.authorAbdo H.G.en_US
dc.contributor.authorid55888132500en_US
dc.contributor.authorid57208776491en_US
dc.contributor.authorid57193547008en_US
dc.contributor.authorid57218543677en_US
dc.contributor.authorid57224683617en_US
dc.contributor.authorid57193090158en_US
dc.date.accessioned2025-03-03T07:43:27Z
dc.date.available2025-03-03T07:43:27Z
dc.date.issued2024
dc.description.abstractAmong the various natural disasters that take place around the world, flood is considered to be the most extensive. There have been several floods in Buz?u river basin, and as a result of this, the area has been chosen as the study area. For the purpose of this research, we applied deep learning and machine learning benchmarks in order to prepare flood potential maps at the basin scale. In this regard 12 flood predictors, 205 flood and 205 non-flood locations were used as input data into the following 3 complex models: Deep Learning Neural Network-Harris Hawk Optimization-Index of Entropy (DLNN-HHO-IOE), Multilayer Perceptron-Harris Hawk Optimization-Index of Entropy (MLP-HHO-IOE) and Stacking ensemble-Harris Hawk Optimization-Index of Entropy (Stacking-HHO-IOE). The flood sample was divided into training (70%) and validating (30%) sample, meanwhile the prediction ability of flood conditioning factors was tested through the Correlation-based Feature Selection method. ROC Curve and statistical metrics were involved in the results validation. The modeling process through the stated algorithms showed that the most important flood predictors are represented by: slope (importance � 20%), distance from river (importance � 17.5%), land use (importance � 12%) and TPI (importance � 10%). The importance values were used to compute the flood susceptibility, while Natural Breaks method was used to classify the results. The high and very high flood susceptibility is spread on approximately 35?40% of the study zone. The ROC Curve, in terms of Success, Rate shows that the highest performance was achieved FPIDLNN-HHO-IOE (AUC = 0.97), followed by FPIStacking-HHO-IOE (AUC = 0.966) and FPIMLP-HHO-IOE (AUC = 0.953), while the Prediction Rate indicates the FPIStacking-HHO-IOE as being the most performant model with an AUC of 0.977, followed by FPIDLNN-HHO-IOE (AUC = 0.97) and FPIMLP-HHO-IOE (AUC = 0.924). ? The Author(s) 2024.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo78
dc.identifier.doi10.1007/s13201-024-02131-4
dc.identifier.issue4
dc.identifier.scopus2-s2.0-85187780321
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85187780321&doi=10.1007%2fs13201-024-02131-4&partnerID=40&md5=816ac9634095b754debe10731ee0d8a7
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/36620
dc.identifier.volume14
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.relation.ispartofAll Open Access; Gold Open Access
dc.sourceScopus
dc.sourcetitleApplied Water Science
dc.subjectRomania
dc.subjectDeep learning
dc.subjectDisasters
dc.subjectEntropy
dc.subjectLand use
dc.subjectLearning algorithms
dc.subjectMultilayer neural networks
dc.subjectOptimization
dc.subjectRivers
dc.subjectWatersheds
dc.subjectBuz?u river basin
dc.subjectFlood potential
dc.subjectLearning neural networks
dc.subjectMachine-learning
dc.subjectMultilayers perceptrons
dc.subjectOptimisations
dc.subjectOptimization algorithms
dc.subjectRiver basins
dc.subjectRomania
dc.subjectStackings
dc.subjectalgorithm
dc.subjectartificial intelligence
dc.subjectflooding
dc.subjectmachine learning
dc.subjectmapping
dc.subjectmodeling
dc.subjectoptimization
dc.subjectstacking
dc.subjectFloods
dc.titleFlood mapping based on novel ensemble modeling involving the deep learning, Harris Hawk optimization algorithm and stacking based machine learningen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS