Enhancing spatial prediction of flash floods with Balancing Composite Motion Optimized Random Forest: A case study in High-Frequency Torrential rainfall area

Hoa Pham Viet; Binh Nguyen An; Hong Pham Viet; An Nguyen Ngoc; Thao Giang Thi Phuong; Hanh Nguyen Cao; Bui Dieu Tien

doi:10.15625/2615-9783/22189

Author affiliations

Authors

Pham Viet Hoa Ho Chi Minh City Institute of Resources Geography, Vietnam Academy of Science and Technology, Mac Dinh Chi 1, Ben Nghe, 1 District, Ho Chi Minh City 700000, Vietnam
Nguyen An Binh Ho Chi Minh City Institute of Resources Geography, Vietnam Academy of Science and Technology, Mac Dinh Chi 1, Ben Nghe, 1 District, Ho Chi Minh City 700000, Vietnam
Pham Viet Hong Institute of Marine Geology and Geophysics, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay District, Hanoi 10000, Vietnam
Nguyen Ngoc An Ho Chi Minh City Institute of Resources Geography, Vietnam Academy of Science and Technology, Mac Dinh Chi 1, Ben Nghe, 1 District, Ho Chi Minh City 700000, Vietnam
Giang Thi Phuong Thao Ho Chi Minh City Institute of Resources Geography, Vietnam Academy of Science and Technology, Mac Dinh Chi 1, Ben Nghe, 1 District, Ho Chi Minh City 700000, Vietnam
Nguyen Cao Hanh Ho Chi Minh City Institute of Resources Geography, Vietnam Academy of Science and Technology, Mac Dinh Chi 1, Ben Nghe, 1 District, Ho Chi Minh City 700000, Vietnam
Bui Dieu Tien GIS Group, Department of Business and IT, University of South-Eastern Norway, Gullbringvegen 36, 3800 Bø i Telemark, Norway

DOI:

https://doi.org/10.15625/2615-9783/22189

Keywords:

Flash flood susceptibility, Random Forest; Balancing Composite Motion Optimization, GIS, Tropical areas

Abstract

Flash floods continue to emerge as a serious and growing natural hazard for many communities worldwide, especially in areas affected by tropical storms. These floods damage critical infrastructure and severely strain economic resources, underscoring the urgent need for advanced flood prediction tools. This study presents an innovative integrated machine learning approach, BCMO-RF, which merges Balancing Composite Motion Optimization (BCMO) with Random Forest (RF) to map flash flood susceptibility. In the BCMO-RF approach, the RF algorithm is applied to develop the flash flood model, while BCMO is used to explore and optimize the model's parameters. The study concentrates on areas in Thanh Hoa Province, Vietnam, frequently impacted by flash floods. Accordingly, various geospatial data sources were utilized to compile a geodatabase comprising 2,540 flash flood locations and 12 influencing factors. The geodatabase served as the basis for training and validating the BCMO-RF model. Results show that the BCMO-RF model attained high prediction accuracy (93.7%), achieving a Kappa coefficient of 0.874 and an AUC score of 0.988, outperforming the Deep Learning model benchmark. The study finds that the BCMO-RF model is reliable for accurately mapping areas susceptible to flash floods.

Downloads

Download data is not yet available.

References

Abedi R., Costache R., Shafizadeh-Moghadam H., Pham Q.B., 2022. Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees. Geocarto International, 37(19), 5479–5496.

Amiri A., Soltani K., Ebtehaj I., Bonakdari H., 2024. A Novel Machine Learning Tool for Current and Future Flood Susceptibility Mapping by Integrating Remote Sensing and Geographic Information Systems. Journal of Hydrology, 130936.

Bournas A., Baltas E., 2022. Investigation of the gridded flash flood Guidance in a Peri-Urban basin in greater Athens area, Greece. Journal of Hydrology, 610, 127820.

Breiman L., 2001. Random forests. Machine learning, 45, 5–32.

Bryndal T., Franczak P., Kroczak R., Cabaj W., Kołodziej A., 2017. The impact of extreme rainfall and flash floods on the flood risk management process and geomorphological changes in small Carpathian catchments: a case study of the Kasiniczanka river (Outer Carpathians, Poland). Natural Hazards, 88(1), 95–120.

Bui D.T., Ngo P.-T.T., Pham T.D., Jaafari A., Minh N.Q., Hoa P.V., Samui P., 2019. A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping. Catena, 179, 184–196.

Degiorgis M., Gnecco G., Gorni S., Roth G., Sanguineti M., Taramasso, A.C., 2013. Flood hazard assessment via threshold binary classifiers: case study of the Tanaro river basin. Irrigation and Drainage, 62(S2), 1-10.

Ding L., Ma L., Li L., Liu C., Li N., Yang Z., Yao Y., Lu H., 2021. A survey of remote sensing and geographic information system applications for flash floods. Remote Sensing, 13(9), 1818.

Dinh T.N., Thi H.L., 2024. Models of residential space for ethnic minorities in Thanh Hoa Province associated with sustainable livelihoods. Heritage and Sustainable Development, 6(1), 127–144.

Godara N., Bruland O., Alfredsen K., 2023. Simulation of flash flood peaks in a small and steep catchment using rain‐on‐grid technique. Journal of Flood Risk Management, 16(3), e12898.

Group W.B., Bank A.D., 2021. Climate Risk Country Profile: Vietnam. World Bank.

Guo K., Guan M., Yu D., 2021. Urban surface water flood modelling a comprehensive review of current models and future challenges. Hydrology and Earth System Sciences, 25(5), 2843–2860.

Hamidifar H., Nones M., Rowinski P.M., 2024. Flood modeling and fluvial dynamics: A scoping review on the role of sediment transport. Earth-Science Reviews, 253, 104775.

Hoa P.V., Binh N.A., Hong P.V., An N.N., Thao G.T.P., Hanh N.C., Ngo P.T.T., Bui D.T., 2024. One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: A case study in North Central Vietnam. Earth Science Informatics, 1–22.

Jodar-Abellan A., Valdes-Abellan J., Pla C., Gomariz-Castillo F., 2019. Impact of land use changes on flash flood prediction using a sub-daily SWAT model in five Mediterranean ungauged watersheds (SE Spain). Science of the Total Environment, 657, 1578–1591.

Knocke E.T., Kolivras K.N., 2007. Flash flood awareness in southwest Virginia. Risk Analysis: An International Journal, 27(1), 155–169.

Le-Duc T., Nguyen Q.-H., Nguyen-Xuan H., 2020. Balancing composite motion optimization. Information Sciences, 520, 250–270.

Linh L.K., Vinh L.Q., Truong N.Q., 2019. New records of skinks (Squamata: Scincidae) from Nam Dong valuable Gymnosperm conservation area, Thanh Hoa province. Journal of Forestry Science and Technology, 8, 109–116.

Ngo P.-T.T., Pham T.D., Hoang N.-D., Tran D.A., Amiri M., Le T.T., Hoa P.V., Van Bui P., Nhu V.-H., Bui D.T., 2021. A new hybrid equilibrium optimized SysFor based geospatial data mining for tropical storm-induced flash flood susceptible mapping. Journal of Environmental Management, 280, 111858.

Pepe, M.S., 2000. Receiver operating characteristic methodology. Journal of the American Statistical Association, 95(449), 308–311.

Pham N.T.T., Nong D., Sathyan A.R., Garschagen M., 2020. Vulnerability assessment of households to flash floods and landslides in the poor upland regions of Vietnam. Climate Risk Management, 28, 100215.

Plate E.J., 2007. Early warning and flood forecasting for large rivers with the lower Mekong as example. Journal of Hydro-environment Research, 1(2), 80–94.

Psomiadis E., 2016. Flash flood area mapping utilising SENTINEL-1 radar data, Earth resources and environmental remote sensing/GIS applications VII. SPIE, 382–392.

Sabӑu D.A., Şerban G., Breţcan P., Dunea D., Petrea D., Rus I., Tanislav D., 2023. Combining radar quantitative precipitation estimates (QPEs) with distributed hydrological model for controlling transit of flash-flood upstream of crowded human habitats in Romania. Natural Hazards, 116(1), 1209–1238.

Saint-Fleur B.E., Allier S., Lassara E., Rivet A., Artigue G., Pistre S., Johannet A., 2023. Towards a better consideration of rainfall and hydrological spatial features by a deep neural network model to improve flash floods forecasting: case study on the Gardon basin, France. Modeling Earth Systems and Environment, 9(3), 3693–3708.

Suresh S., Hossain F., Minocha S., Das P., Khan S., Lee H., Andreadis K., Oddo P., 2024. Satellite-based tracking of reservoir operations for flood management during the 2018 extreme weather event in Kerala, India. Remote Sensing of Environment, 307, 114149.

Tan X., Li Y., Wu X., Dai C., Zhang X., Cai Y., 2024. Identification of the key driving factors of flash flood based on different feature selection techniques coupled with random forest method. Journal of Hydrology: Regional Studies, 51, 101624.

Tien Bui D., Pradhan B., Lofman O., Revhaug I., Dick O.B., 2012. Landslide susceptibility mapping at Hoa Binh province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS. Computers & Geosciences, 45, 199–211.

Trong N.G., Quang P.N., Cuong N.V., Le H.A., Nguyen H.L., Tien Bui D., 2023. Spatial Prediction of Fluvial Flood in High-Frequency Tropical Cyclone Area Using TensorFlow 1D-Convolution Neural Networks and Geospatial Data. Remote Sensing, 15(22), 5429.

Tsangaratos P., Ilia I., Chrysafi A.-A., Matiatos I., Chen, W., Hong H., 2023. Applying a 1D Convolutional Neural Network in Flood Susceptibility Assessments: The Case of the Island of Euboea, Greece. Remote Sensing, 15(14), 3471.

Tuan T.A., Pha P.D., Tam T.T., Bui D.T., 2023. A new approach based on Balancing Composite Motion Optimization and Deep Neural Networks for spatial prediction of landslides at tropical cyclone areas. IEEE Access.

Tuyet Hanh T.T., Huong L.T.T., Huong N.T.L., Linh T.N.Q., Quyen N.H., Nhung N.T.T., Ebi K., Cuong N.D., Van Nhu H., Kien T.M., 2020. Vietnam climate change and health vulnerability and adaptation assessment, 2018. Environmental Health Insights, 14. https://doi.org/10.1177/1178630220924658.

Wang Y., Fu Z., Cheng Z., Xiang Y., Chen J., Zhang P., Yang X., 2024. Uncertainty analysis of dam-break flood risk consequences under the influence of non-structural measures. International Journal of Disaster Risk Reduction, 102, 104265.

Wdowinski S., Bray R., Kirtman B.P., Wu Z., 2016. Increasing flooding hazard in coastal communities due to rising sea level: Case study of Miami Beach, Florida. Ocean & Coastal Management, 126, 1–8.

Willner S.N., Levermann A., Zhao F., Frieler K., 2018. Adaptation required to preserve future high-end river flood risk at present levels. Science Advances, 4(1), eaao1914.

Zevenbergen L.W., Thorne C.R., 1987. Quantitative analysis of land surface topography. Earth Surface Processes and Landforms, 12(1), 47–56.

Zhao G., Liu R., Yang M., Tu T., Ma M., Hong Y., Wang X., 2022. Large-scale flash flood warning in China using deep learning. Journal of Hydrology, 604, 127222.