{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T21:24:15Z","timestamp":1768857855163,"version":"3.49.0"},"reference-count":48,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2022A1515011494"],"award-info":[{"award-number":["2022A1515011494"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["202201011726"],"award-info":[{"award-number":["202201011726"]}]},{"name":"Science and Technology Program of Guangzhou","award":["2022A1515011494"],"award-info":[{"award-number":["2022A1515011494"]}]},{"name":"Science and Technology Program of Guangzhou","award":["202201011726"],"award-info":[{"award-number":["202201011726"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Data-driven flood susceptibility modeling is an efficient way to map the spatial distribution of flood likelihood. The quality of the flood susceptibility model relies on the learning technique and the data used for learning. The performance of learning techniques has been extensively examined. However, to date, the impact of data sampling strategies has received limited attention. Random sampling is widely favored because of its ease of use. It treats flood-related data as tabular and excludes their spatial dimensions. Flood occurrence is typically uneven over space. Therefore, non-flood sampling should not be completely random. To represent the impact of the spatial dimension, this study proposed a new sampling approach based on spatial dependence, called inverse-occurrence sampling. It selects more non-flood data in low-risk areas than in high-risk areas. The new sampling approach was compared with random and stratified sampling, using six machine learning techniques in two urban areas in Guangzhou, China, with distinct flood mechanisms, that is, Tianhe (flood density 1.5\/km2, clustered distribution, average slope 9.02\u00b0, downtown district) and Panyu (flood density 0.15\/km2, random distribution, average slope 4.55\u00b0, suburban district). Learning techniques include support vector machine (SVM), random forest (RF), artificial neural networks (ANNs), convolutional neural networks (CNNs), CNN-SVM, and CNN-RF. The main findings of this study were as follows: (1) Sampling approaches had a greater impact on model performance than learning techniques in terms of area under the receiver operating characteristic curve (AUC). The AUC variations caused by learning techniques ranged from 0.04 to 0.09. Meanwhile, the AUC variations caused by sampling approaches were between 0.15 and 0.22, all larger than 0.1. (2) The new sampling approach outperformed that of the other two sampling approaches for high average AUC values and small AUC variations. The outperformance is robust in regard to multiple learning techniques and different flooding mechanisms. AUCs in the inverse group had a narrower range (0.14\u20130.18 in Tianhe and 0.35\u20130.39 in Panyu) than in the random group (0.24\u20130.28 in Tianhe and 0.43\u20130.53 in Panyu) and the stratified group (0.23\u20130.30 in Tianhe and 0.42\u20130.48 in Panyu). (3) The most accurate learning technique for AUC was CNN-RF, followed by SVM, CNN-SVM, RF, CNN, and ANN. (4) ANN- and CNN-based models tended to produce polarized patterns in flood susceptibility maps, contradicting the ascending order of flood density with increasing susceptibility levels. Flood density outliers tended to appear in the models derived using RF and CNN-RF. Finally, the newly proposed sampling approach is suggested to be applied to flood susceptibility mapping to reflect the impact of spatial dependence.<\/jats:p>","DOI":"10.3390\/rs15225384","type":"journal-article","created":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:49:47Z","timestamp":1700182187000},"page":"5384","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["An Inverse-Occurrence Sampling Approach for Urban Flood Susceptibility Mapping"],"prefix":"10.3390","volume":"15","author":[{"given":"Changpeng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China"}]},{"given":"Yangchun","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China"},{"name":"China Water Resources Pearl River Planning, Surveying & Designing Co., Ltd., Guangzhou 510611, China"}]},{"given":"Zhiwen","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9076-692X","authenticated-orcid":false,"given":"Jiayin","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China"}]},{"given":"Wenkai","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-0296","authenticated-orcid":false,"given":"Huabing","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"ref_1","unstructured":"UNDRR (United Nations Office for Disaster Risk Reduction) (2020, May 07). Human Cost of Disasters: An Overview of the Last 20 Years 2000\u20132019. Available online: https:\/\/www.undrr.org\/publication\/human-cost-disasters-overview-last-20-years-2000-2019."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103423","DOI":"10.1016\/j.pce.2023.103423","article-title":"Understanding the role of surface runoff in potential flood inundation in the Kashmir valley, Western Himalayas","volume":"131","author":"Ahmad","year":"2023","journal-title":"Phys. Chem. Earth"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1038\/s41586-023-06468-9","article-title":"Global evidence of rapid urban growth in flood zones since 1985","volume":"622","author":"Rentschler","year":"2023","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/S1665-6423(14)70604-2","article-title":"Flood Risk Assessment in Humanitarian Logistics Process Design","volume":"12","author":"Delgado","year":"2014","journal-title":"J. Appl. Res. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102237","DOI":"10.1016\/j.ijdrr.2021.102237","article-title":"A multisource trend analysis of floods in Asia-Pacific 1990\u20132018: Implications for climate change in sustainable development goals","volume":"59","author":"Kimuli","year":"2021","journal-title":"Int. J. Disaster Risk Reduct."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1007\/s00477-015-1021-9","article-title":"Flood susceptibility analysis and its verification using a novel ensemble support vector machine and frequency ratio method","volume":"29","author":"Tehrany","year":"2015","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s12665-019-8285-1","article-title":"A comparison of frequency ratio and fuzzy logic models for flood susceptibility assessment of the lower Kosi River Basin in India","volume":"78","author":"Sahana","year":"2019","journal-title":"Environ. Earth Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1007\/s00477-021-02115-9","article-title":"Efficiency exploration of frequency ratio, entropy and weights of evidence-information value models in flood vulnerabilityassessment: A study of raiganj subdivision, Eastern India","volume":"36","author":"Saha","year":"2022","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cao, Y., Jia, H., Xiong, J., Cheng, W., Li, K., Pang, Q., and Yong, Z. (2020). Flash Flood Susceptibility Assessment Based on Geodetector, Certainty Factor, and Logistic Regression Analyses in Fujian Province, China. ISPRS Int. J. Geo-Inf., 9.","DOI":"10.3390\/ijgi9120748"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.jhydrol.2014.03.008","article-title":"Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS","volume":"512","author":"Tehrany","year":"2014","journal-title":"J. Hydrol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1016\/j.scitotenv.2017.12.256","article-title":"Application of fuzzy weight of evidence and data mining techniques in construction of flood susceptibility map of Poyang County, China","volume":"625","author":"Hong","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1007\/s12665-016-5323-0","article-title":"Flood hazard mapping in Jamaica using principal component analysis and logistic regression","volume":"75","author":"Nandi","year":"2016","journal-title":"Environ. Earth Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106620","DOI":"10.1016\/j.ecolind.2020.106620","article-title":"GIS-based comparative assessment of flood susceptibility mapping using hybrid multi-criteria decision-making approach, na\u00efve Bayes tree, bivariate statistics and logistic regression: A case of Top\u013ea basin, Slovakia","volume":"117","author":"Ali","year":"2020","journal-title":"Ecol. Indic."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"128055","DOI":"10.1016\/j.jhydrol.2022.128055","article-title":"Optimality of flood influencing factors for flood hazard mapping: An evaluation of two multi-criteria decision-making methods","volume":"612","author":"Sabtu","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1007\/s11069-022-05248-4","article-title":"Evaluation of the prediction capability of AHP and F-AHP methods in flood susceptibility mapping of Ernakulam district (India)","volume":"112","author":"Vilasan","year":"2022","journal-title":"Nat. Hazards"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jhydrol.2019.02.034","article-title":"A new approach to flood susceptibility assessment in data-scarce and ungauged regions based on GIS-based hybrid multi criteria decision-making method","volume":"572","author":"Arabsheibani","year":"2019","journal-title":"J. Hydrol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"125275","DOI":"10.1016\/j.jhydrol.2020.125275","article-title":"Flood susceptibility mapping with machine learning, multi-criteria decision analysis and ensemble using Dempster Shafer Theory","volume":"590","author":"Gholamnia","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"102614","DOI":"10.1016\/j.ijdrr.2021.102614","article-title":"Evaluating urban flood risk using hybrid method of TOPSIS and machine learning","volume":"66","author":"Azareh","year":"2021","journal-title":"Int. J. Disaster Risk Reduct."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"128268","DOI":"10.1016\/j.jhydrol.2022.128268","article-title":"Flood hazard zone mapping incorporating geographic information system (GIS) and multi-criteria analysis (MCA) techniques","volume":"612","author":"Chen","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1016\/j.scitotenv.2017.10.037","article-title":"Mapping flood susceptibility in mountainous areas on a national scale in China","volume":"615","author":"Zhao","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s11069-020-04453-3","article-title":"Urban flood hazard mapping using machine learning models: GARP, RF, MaxEnt and NB","volume":"106","author":"Norallahi","year":"2021","journal-title":"Nat. Hazards"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"101253","DOI":"10.1016\/j.gsf.2021.101253","article-title":"A novel index to evaluate discretization methods: A case study of flood susceptibility assessment based on random forest","volume":"12","author":"Tang","year":"2021","journal-title":"Geosci. Front."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1007\/s11069-022-05347-2","article-title":"Flood risk mapping for the lower Narmada basin in India: A machine learning and IoT-based framework","volume":"113","author":"Mangukiya","year":"2022","journal-title":"Nat. Hazards"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xiong, J., Li, J., Cheng, W., Wang, N., and Guo, L. (2019). A GIS-Based Support Vector Machine Model for Flash Flood Vulnerability Assessment and Mapping in China. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8070297"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1016\/j.scitotenv.2018.12.217","article-title":"Assessment of urban flood susceptibility using semi-supervised machine learning model","volume":"659","author":"Zhao","year":"2019","journal-title":"Sci. Total Environ."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104450","DOI":"10.1016\/j.catena.2019.104450","article-title":"Exploring effectiveness of frequency ratio and support vector machine models in storm surge flood susceptibility assessment: A study of Sundarban Biosphere Reserve, India","volume":"189","author":"Sahana","year":"2020","journal-title":"Catena"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"112731","DOI":"10.1016\/j.jenvman.2021.112731","article-title":"Integration of hard and soft supervised machine learning for flood susceptibility mapping","volume":"291","author":"Andaryani","year":"2021","journal-title":"J. Environ. Manag."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"134979","DOI":"10.1016\/j.scitotenv.2019.134979","article-title":"Modeling flood susceptibility using data-driven approaches of na\u00efve Bayes tree, alternating decision tree, and random forest methods","volume":"701","author":"Chen","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"104536","DOI":"10.1016\/j.catena.2020.104536","article-title":"Flood susceptibility assessment based on a novel random Na\u00efve Bayes method: A comparison between different factor discretization methods","volume":"190","author":"Tang","year":"2020","journal-title":"Catena"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"125552","DOI":"10.1016\/j.jhydrol.2020.125552","article-title":"Convolutional neural network approach for spatial prediction of flood hazard at national scale of Iran","volume":"591","author":"Khosravi","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"124482","DOI":"10.1016\/j.jhydrol.2019.124482","article-title":"Flood susceptibility mapping using convolutional neural network frameworks","volume":"582","author":"Wang","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"125235","DOI":"10.1016\/j.jhydrol.2020.125235","article-title":"Urban flood susceptibility assessment based on convolutional neural networks","volume":"590","author":"Zhao","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3295","DOI":"10.1007\/s00477-022-02195-1","article-title":"Deep learning algorithms to develop Flood susceptibility map in Data-Scarce and Ungauged River Basin in India","volume":"36","author":"Saha","year":"2022","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"101425","DOI":"10.1016\/j.gsf.2022.101425","article-title":"Multi-hazard susceptibility mapping based on Convolutional Neural Networks","volume":"13","author":"Ullah","year":"2022","journal-title":"Geosci. Front."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"101100","DOI":"10.1016\/j.gsf.2020.10.007","article-title":"Flash flood susceptibility mapping using a novel deep learning model based on deep belief network, back propagation and genetic algorithm","volume":"12","author":"Shahabi","year":"2021","journal-title":"Geosci. Front."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"125734","DOI":"10.1016\/j.jhydrol.2020.125734","article-title":"Predicting flood susceptibility using LSTM neural networks","volume":"594","author":"Fang","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"125475","DOI":"10.1016\/j.jhydrol.2020.125475","article-title":"In flood susceptibility assessment, is it scientifically correct to represent flood events as a point vector format and create flood inventory map?","volume":"590","author":"Pradhan","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"128091","DOI":"10.1016\/j.jhydrol.2022.128091","article-title":"Hybrid approach for flood susceptibility assessment in a flood-prone mountainous catchment in China","volume":"612","author":"Fang","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1007\/s00477-021-02035-8","article-title":"A method to increase the number of positive samples for machine learning-based urban waterlogging susceptibility assessments","volume":"36","author":"Tang","year":"2022","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"127877","DOI":"10.1016\/j.jhydrol.2022.127877","article-title":"Exploring the additional value of class imbalance distributions on interpretable flash flood susceptibility prediction in the Black Warrior River basin, Alabama, United States","volume":"610","author":"Koc","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"135983","DOI":"10.1016\/j.scitotenv.2019.135983","article-title":"Integrated machine learning methods with resampling algorithms for flood susceptibility prediction","volume":"705","author":"Dodangeh","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1016\/j.jhydrol.2019.06.058","article-title":"Urban waterlogging susceptibility assessment based on a PSO-SVM method using a novel repeatedly random sampling idea to select negative samples","volume":"576","author":"Tang","year":"2019","journal-title":"J. Hydrol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1007\/s11069-021-04860-0","article-title":"Exploring the sample size and replications scenarios effect on spatial prediction of flood, using MARS and MaxEnt methods case study: Saliantape catchment, Golestan, Iran","volume":"109","author":"Rajabi","year":"2021","journal-title":"Nat. Hazards"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"234","DOI":"10.2307\/143141","article-title":"A Computer Movie Simulating Urban Growth in the Detroit Region","volume":"46","author":"Tobler","year":"1970","journal-title":"Econ. Geogr."},{"key":"ref_45","unstructured":"Winters, B.A., Angel, J.R., Ballerine, C., Byard, J., Flegel, A., Gambill, D., Jenkins, E., McConkey, S.A., Markus, M., and Bender, B.A. (2015). Report for the Urban Flooding Awareness Act, Illinois Department of Natural Resources."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1016\/j.scitotenv.2015.02.027","article-title":"Assessing urban potential flooding risk and identifying effective risk-reduction measures","volume":"514","author":"Cherqui","year":"2015","journal-title":"Sci. Total Environ."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.scitotenv.2017.11.358","article-title":"The changing pattern of urban flooding in Guangzhou, China","volume":"622\u2013623","author":"Huang","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Huang, H., Pan, Y., Wang, C., and Wang, X. (2023). Nonlinear Flood Responses to Tide Level and Land Cover Changes in Small Watersheds. Land, 12.","DOI":"10.3390\/land12091743"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/22\/5384\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:24:17Z","timestamp":1760131457000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/22\/5384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,16]]},"references-count":48,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["rs15225384"],"URL":"https:\/\/doi.org\/10.3390\/rs15225384","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,16]]}}}