Research on Flood Impact Assessment of Mountainous Small Watersheds Based on AI Technology

Authors

  • Zhisong Yang

    Bijiang District Water Affairs Bureau, Tongren 554300, China

DOI:

https://doi.org/10.30564/jees.v8i8.13547
Received: 12 June 2026 | Revised: 18 July 2026 | Accepted: 17 August 2026 | Published Online: 25 August 2026

Abstract

This article focuses on improving the accuracy and systematic approach of flash flood disaster prevention in the central urban area of Tongren. This study is based on hydrological and water resources theory along with a disaster risk assessment framework. The study covers a 758.3 km2 area in Bijiang and Wanshan Districts. It integrates hydrological, meteorological, topographic and socio-economic data from 1951 to 2021. The results show that flash floods in the central urban area are characterized by "strong destructive power of rainstorms, rapid confluence response, and spatial concentration of risks." 82% of riverside villages have flood control capabilities below the 20-year return period standard. The Xieqiao River (drainage area 198 km2) and Sanzhai River (drainage area 45 km2) are high-risk core areas, with design peak flows of 894 m3/s and 345 m3/s respectively for a 100-year return period. Among the 39 danger zones classified by risk level, extremely high-risk zones (recurrence period <5 years) account for 30.8%, concentrated in densely populated areas such as the Heping resettlement area and Xiaohaha Commercial City. The critical rainfall warning index range for 1–24 h is 34–204 mm, requiring differentiated response thresholds for different risk zones (69 mm for immediate evacuation in high-risk zones and 41 mm in low-risk zones). The research findings can provide theoretical support and a technical paradigm for risk management and precise early warning of urban flood disasters in southwestern mountainous areas.

Keywords:

Tongren Central Urban Area; Flash Flood Disaster; Design Flood; Danger Zone Delineation; Critical Early Warning Indicators; Geographic Information Systems (GIS) Spatial Analysis; Risk Assessment

References

[1] Chen, Z., Feng, M., Johnson, M.F., et al., 2026. Flash Floods in Mountainous Regions: Global Research Trends, Process Mechanisms, and Control Measures. EGUsphere. 2026, 1–42.

[2] Chukwuma Sr, C., 2025. Invariance of extreme hydrologic events and climate change in the risk reduction on environment and health. Greenfort International Journal of Applied Medical Science. 3(2), 92–102.

[3] Wang, W., Sang, G., Zhao, Q., et al., 2024. Prediction of flash flood peak discharge in hilly areas with ungauged basins based on machine learning. Hydrology Research. 55(8), 801–814.

[4] Bu, M., Zhou, J., 2020. Flood Disaster Risk Assessment of Tongren, Guizhou Based on WMS and SMS. World Scientific Research Journal. 6(4), 168–176.

[5] Liu, C., Guo, L., Ye, L., et al., 2018. A review of advances in China’s flash flood early-warning system. Natural Hazards. 92(2), 619–634.

[6] Singh, G., Pandey, A., 2021. Flash flood vulnerability assessment and zonation through an integrated approach in the Upper Ganga Basin of the Northwest Himalayan region in Uttarakhand. International Journal of Disaster Risk Reduction. 66, 102573.

[7] Yang, S., Han, X., Cao, B., et al., 2018. Cloud-model-based method for risk assessment of mountain torrent disasters. Water. 10(7), 830.

[8] Azadgar, A., Nyka, L., Salata, S., 2024. Advancing urban flood resilience: A systematic review of urban flood risk mitigation model, research trends, and future directions. Land. 13(12), 2138.

[9] Zhang, S., Zhang, X., Pei, X., et al., 2019. Model test study on the hydrological mechanisms and early warning thresholds for loess fill slope failure induced by rainfall. Engineering Geology. 258, 105135.

[10] Khan, M.A.R., Akter, M.S., Sultana, N., et al., 2025. Development of a fog computing-based real-time flood prediction and early warning system using machine learning and remote sensing data. Journal of Sustainable Development and Policy. 1(1), 144–169.

[11] Liu, D., Yang, D., Zhang, L., et al., 2023. Regional flood disaster risk assessment and driving mechanism based on BOA–SVM model. Transactions of the Chinese Society for Agricultural Machinery. 54(10), 304–315. (in Chinese)

[12] Gao, J., Zhang, Y., Zuo, L., 2023. The optimal explanatory power of soil erosion and water yield in karst mountainous areas. Journal of Geographical Sciences. 33(10), 2077–2093.

[13] Zhang, X., Chen, H., Cao, S., et al., 2025. The Impact of Near-Surface Meteorological Factors and Underlying Surface Conditions on Icing in Low Mountain and Hilly Areas and Its Application in Newly-Built Transmission Line Projects: A Case Study of a Newly-Built Transmission Line in Wanshan District, Tongren City. In Proceedings of the 2025 6th New Power System International Forum-Power System and New Energy Technology Innovation Forum (NPSIF), Boao, China, 29–31 October 2025.

[14] Wang, Z., Liu, S., Liu, M., et al., 2025. Coupling relationships between water‑carbon ecosystem service flows under the integrated perspective of “Three Waters”: A case study in Guizhou province. Ecological Frontiers. 45(6), 1774–1783.

[15] Zhao, J., Yang, L., Zhu, L., et al., 2026. Analysis of urban design rainstorm patterns based on parameter estimation and model approaches. Stochastic Environmental Research and Risk Assessment. 40(4), 93.

[16] Lin, S., Du, J., Fan, J., 2025. Spatio-Temporal Evolution of Surface Urban Heat Island Distribution in Mountainous Urban Areas Based on Local Climate Zones: A Case Study of Tongren, China. Sustainability. 17(19), 8744.

[17] Wu, J., Yu, L., Cao, G., et al., 2018. Spatial and Temporal Characteristics of Precipitation in Yungui Plateau during 1961–2015. Proceedings of the E3S Web of Conferences. 38, 01021.

[18] Zhou, Y., Shen, D., Huang, N., et al., 2019. Urban flood risk assessment using storm characteristic parameters sensitive to catchment-specific drainage system. Science of the Total Environment. 659, 1362–1369.

[19] Shao, Z., Wang, J., Zhang, X., et al., 2025. Bridging Uncertainty in SWMM Model Calibration: A Bayesian Analysis of Optimal Rainfall Selection. Water. 17(23), 3435.

[20] Zhang, Q., Gu, X., Singh, V.P., et al., 2014. Flood frequency analysis with consideration of hydrological alterations: Changing properties, causes and implications. Journal of Hydrology. 519, 803–813.

[21] Nikolopoulos, E.I., Borga, M., Zoccatelli, D., et al., 2014. Catchment-scale storm velocity: Quantification, scale dependence and effect on flood response. Hydrological Sciences Journal. 59(7), 1363–1376.

[22] Salas, J.D., Obeysekera, J., 2014. Revisiting the concepts of return period and risk for nonstationary hydrologic extreme events. Journal of Hydrologic Engineering. 19(3), 554–568.

[23] Xu, S., Liu, D., Chen, H., et al., 2026. Flood Risk Assessment Considering the Spatial and Temporal Characteristics of Disaster-Causing Factors. Sustainability. 18(7), 3646.

[24] Wang, L., Cui, S., Li, Y., et al., 2022. A review of the flood management: From flood control to flood resilience. Heliyon. 8(11), e11763.

[25] Zhang, R., Li, R., Chen, T., et al., 2024. Flood risk identification in high-density urban areas of Macau based on disaster scenario simulation. International Journal of Disaster Risk Reduction. 107, 104485.

[26] Yang, Z.S., 2024. Application of hydrology and water resources in flood disaster risk assessment and zoning. Water Resources Science and Technology. (7), 7. (in Chinese)

[27] Wang, S., Zhang, K., Chao, L., et al., 2023. Assessment of flood and landslide hazard risk based on ensemble simulation over upstream of the Han River. Water Resources Protection. 39(6), 70–76.

[28] Si, L.L., Zhao, L., Wei, T.X., et al., 2023. Risk Assessment of Flood Disaster Based on Shared Socioeconomic Pathways: A Case Study of the Small- and Medium-Sized River Basins in the Upper Reaches of Xiong'an New Area. Meteorological Monthly. 49(6), 745–756. (in Chinese)

[29] Zhang, Y., Vaze, J., Chiew, F.H., et al., 2014. Predicting hydrological signatures in ungauged catchments using spatial interpolation, index model, and rainfall–runoff modelling. Journal of Hydrology. 517, 936–948.

[30] Nishiguchi, R., Tagata, S., Kageyama, K., et al., 2022. River Flow Inverse Analysis and Data Assimilation. Journal of JSCE. 10(1), 430–442.

[31] Zang, Y., Meng, Y., Guan, X., et al., 2022. Study on urban flood early warning system considering flood loss. International Journal of Disaster Risk Reduction. 77, 103042.

[32] Kuksina, L., Golosov, V.N., Kuznetsova, Y.S., 2017. Cloudburst floods in mountains: State of knowledge, occurrence, factors of formation. Geography and Natural Resources. 38(1), 20–29.

[33] Chen, Y., Zhang, N., Zhang, X., et al., 2025. A novel dynamic flash flood early warning framework based on distributed hydrologic modeling. Ecological Indicators. 172, 113247.

[34] Panganiban, E.B., Cruz, J.C.D., 2017. Rain water level information with flood warning system using flat clustering predictive technique. In Proceedings of the TENCON 2017-2017 IEEE Region 10 Conference, Penang, Malaysia, 5–8 November 2017.

Downloads

How to Cite

Yang, Z. (2026). Research on Flood Impact Assessment of Mountainous Small Watersheds Based on AI Technology. Journal of Environmental & Earth Sciences, 8(8), 1192–1201. https://doi.org/10.30564/jees.v8i8.13547

Issue

Vol. 8 , Iss. 8 (August 2026): In Progress

Article Type

Review

License

Copyright © 2026 Zhisong Yang

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC