山洪對越南山區的生命、基礎設施和財產構成嚴重且不斷升級的威脅。 二十年來，
越南社會經濟快速發展，成為地區發展最快的國家之一。 然而，這一進步伴隨著城
市化、土地覆蓋變化和天然森林覆蓋率的減少，加劇了山洪爆發的風險。
本研究重點在於兩個目標：（1）應用機器學習（ML）模型預測山洪爆發敏感性；
（2）評估近二十年來人類活動對越南山區山洪暴發敏感度的定量影響。
方法
為了實現上述兩個目標，研究檢視了452個歷史山洪點，並分析了15個獨立因素，
包括海拔、坡度、坡向、曲率、地形濕度指數（TWI）、河流功率指數（SPI）、
流量累積、河流密度、到河流的距離、NDVI、NDBI、土地利用/土地覆蓋 (LULC)
。根據這些數據，研究採用了各種機器學習演算法來預測山洪爆發的機率，包括邏
輯回歸（LR）、K最近鄰（KNN）、高斯樸素貝葉斯（GNB）、多層感知器（MLP）
、支援向量機 (SVM)、隨機森林 (RF) 和 XGBoost (XGB)。使用表現出最高性能的
演算法來建立 2001-2010 年和 2013-2022 年期間的山洪暴發敏感度圖。 為了評估人
為影響，我們對土地利用模式的變化進行了詳細分析，並採用了歸一化植被指數（
NDVI）和歸一化差異建成指數（NDBI）等指數。 這些因素在塑造兩個時期山洪發
生機率的差異方面發揮了重要作用。
iii
結果
結果表明，RF、XGB 和 KNN 模型表現出卓越的性能，準確率分別為 0.949、0.941
和 0.919，以及令人印象深刻的 AUC-ROC 值（分別為 0.990、0.989 和 0.974）。
研究還表明，過去二十年人類社會經濟發展活動使高易發區和極高易發區發生山洪
的機率分別增加了7.69%和4.01%，令人擔憂。
結論
這項開創性的努力引入了一套新穎且全面的關聯模型，為現有的洪水預測方法增添
了重要價值。 此外，這些發現提供了切實而有力的證據，決策者可以利用這些證據
來評估持續的社會經濟成長的影響。 此外，它們是製定永續發展計畫的重要基礎，
該計畫優先考慮減輕未來不斷升級的山洪風險。

Background
Flash floods pose a significant and escalating threat to life, infrastructure, and property in
the mountainous regions of Vietnam. Over the past two decades, Vietnam has experienced
rapid socio-economic development, making it one of the fastest-growing countries in the
region. However, this progress has been accompanied by urbanization, land cover
conversion, and reductions in natural forest coverage, exacerbating the risk of flash floods.
This study focuses on two objectives: (1) Applying the Machine learning (ML) model to
predict the flash flood susceptibility and (2) Evaluating the quantitative influence of human
activities on flash flood susceptibility in recent two decades in mountainous of Vietnam.
Methodology
To solve the above two objectives, the study has examined 452 historical flash flood
points and analyzed 15 independent factors encompassing elevation, slope, aspect, curvature,
topographic wetness index (TWI), stream power index (SPI), flow accumulation, river
density, distance to the river, NDVI, NDBI, land use/ land cover (LULC), rainfall, soil type,
geology. From these data, the study has employed various machine learning algorithms to
predict the probability of flash flood, including Logistic Regression (LR), K-Nearest
Neighbors (KNN), Gaussian Naïve Bayes (GNB), Multi-layer Perceptron (MLP), Support
Vector Machines (SVM), Random Forests (RF), and XGBoost (XGB). The algorithm that
exhibits the highest performance was used to build the flash flood susceptibility maps for the
period of 2001-2010 and 2013-2022. To assess the anthropogenic impact, we conducted a
detailed analysis of changes in land use patterns and employed indices such as the
v
Normalized Difference Vegetation Index (NDVI) and Normalized Difference Built-up Index
(NDBI). These factors played a significant role in shaping the differences in flash flood
probability between the two time periods.
Results
The results demonstrated that RF, XGB and KNN models showcasing superior
performance, boasting accuracy rates of 0.949, 0.941, and 0.919, along with impressive
AUC-ROC values of 0.990, 0.989, and 0.974, respectively.
The study also showed that human socio-economic development activities in the last two
decades have increased alarmingly in the probability of flash floods by 7.69% and 4.01% in
areas classified as high and very high susceptibility, respectively.
Conclusion
This pioneering endeavor introduces a novel and comprehensive suite of associative
models, adding significant value to existing flood prediction methodologies. Besides, these
findings provide tangible and robust evidence that policymakers can utilize to evaluate the
implications of ongoing socio-economic growth. Furthermore, they serve as a critical
foundation for formulating sustainable development plans that prioritize mitigating the
future escalating risk of flash floods.

REFERENCES
[1] WMO and GWP, “Management of Flash Floods,” Integr. Flood Manag. Tools Ser. Manag. flash flood, no. 16, p. 44, 2012.
[2] M. Sˇpitalar, J. J. Gourley, C. Lutoff, P. E. Kirstetter, M. Brilly, and N. Carr, “Analysis of flash flood parameters and human impacts in the US from 2006 to 2012,” J. Hydrol., vol. 519, no. PA, pp. 863–870, 2014, doi: 10.1016/j.jhydrol.2014.07.004.
[3] C. G. Collier, “Flash flood forecasting: What are the limits of predictability?,” Q. J. R. Meteorol. Soc., vol. 133, pp. 3–23, 2007, doi: 10.1002/qj.29.
[4] I. Braud, B. Vincendon, S. Anquetin, V. Ducrocq, and J. D. Creutin, “The challenges of flash flood forecasting,” Mobil. Face Extrem. Hydrometeorol. Events 1 Defin. Relev. Scales Anal., pp. 63–88, 2018, doi: 10.1016/B978-1-78548-289-2.50003-3.
[5] WB, “The World Bank in Vietnam,” 2023. https://www.worldbank.org/en/country/vietnam/overview. [accessed 16 June,2023].
[6] R. Pizarro et al., “Inland water bodies in Chile can locally increase rainfall intensity,” J. Hydrol., vol. 481, pp. 56–63, 2013, doi: 10.1016/j.jhydrol.2012.12.012.
[7] V. B. Thao and N. T. T. Huong, “Đánh giá đặc trưng hình thái lưu vực suối đến sự hình thành lũ bùn đá khu vực miền núi phía Bắc,” Tạp chí khoa học và công nghệ thủy lợi, vol. 70, no. 1, pp. 1–16, 2022.
[8] K. Chapi et al., “A novel hybrid artificial intelligence approach for flood susceptibility assessment,” Environ. Model. Softw., vol. 95, pp. 229–245, 2017, doi: 10.1016/j.envsoft.2017.06.012.
[9] P. D. Dao and Y. A. Liou, “Object-based flood mapping and affected rice field estimation with landsat 8 OLI and MODIS data,” Remote Sens., vol. 7, no. 5, pp. 5077–5097, 2015, doi: 10.3390/rs70505077.
[10] L. C. Wang, D. V. Hoang, and Y. A. Liou, “Quantifying the Impacts of the 2020 Flood on Crop Production and Food Security in the Middle Reaches of the Yangtze River, China,” Remote Sens., vol. 14, no. 13, 2022, doi: 10.3390/rs14133140.
[11] D. T. Bui, P. Tsangaratos, P. T. T. Ngo, T. D. Pham, and B. T. Pham, “Flash flood susceptibility modeling using an optimized fuzzy rule based feature selection technique and tree based ensemble methods,” Sci. Total Environ., vol. 668, pp. 1038–1054, 2019, doi: 10.1016/j.scitotenv.2019.02.422.
[12] T. Nachappa, P. S. Tavakkoli, K. Gholamnia, O. Ghorbanzadeh, O. Rahmati, and T. Blaschke, “Flood susceptibility mapping with machine learning, multi-criteria decision analysis and ensemble using Dempster Shafer Theory,” J. Hydrol., vol. 590, p. 125275, 2020, doi: 10.1016/j.jhydrol.2020.125275.
[13] K. A. Nguyen, Y. A. Liou, and J. P. Terry, “Vulnerability of Vietnam to typhoons: A spatial assessment based on hazards, exposure and adaptive capacity,” Sci. Total Environ., vol. 682, pp. 31–46, 2019, doi: 10.1016/j.scitotenv.2019.04.069.
[14] R. Costache et al., “New neural fuzzy-based machine learning ensemble for enhancing the prediction accuracy of flood susceptibility mapping,” Hydrol. Sci. J., vol. 65, no. 16, pp. 2816–2837, 2020, doi: 10.1080/02626667.2020.1842412.
[15] C. Cao, P. Xu, Y. Wang, J. Chen, L. Zheng, and C. Niu, “Flash flood hazard susceptibility mapping using frequency ratio and statistical index methods in coalmine subsidence areas,” Sustain., vol. 8, no. 9, 2016, doi: 10.3390/su8090948.
[16] P. Roy, S. Chandra Pal, R. Chakrabortty, I. Chowdhuri, S. Malik, and B. Das, “Threats of climate and land use change on future flood susceptibility,” J. Clean. Prod., vol. 272, p. 122757, 2020, doi: 10.1016/j.jclepro.2020.122757.
[17] R. Madhuri, S. Sistla, and K. Srinivasa Raju, “Application of machine learning algorithms for flood susceptibility assessment and risk management,” J. Water Clim. Chang., vol. 12, no. 6, pp. 2608–2623, 2021, doi: 10.2166/wcc.2021.051.
[18] M. S. Tehrany, L. Kumar, and F. Shabani, “A novel GIS-based ensemble technique for flood susceptibility mapping using evidential belief function and support vector machine: Brisbane, Australia,” PeerJ, vol. 2019, no. 10, 2019, doi: 10.7717/peerj.7653.
[19] W. Chen et al., “Modeling flood susceptibility using data-driven approaches of naïve Bayes tree, alternating decision tree, and random forest methods,” Sci. Total Environ., vol. 701, p. 134979, 2020, doi: 10.1016/j.scitotenv.2019.134979.
[20] A. Arora et al., “Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India,” Sci. Total Environ., vol. 750, p. 141565, 2021, doi: 10.1016/j.scitotenv.2020.141565.
[21] H. D. Nguyen, “Spatial modeling of flood hazard using machine learning and GIS in Ha Tinh province, Vietnam,” J. Water Clim. Chang., vol. 14, no. 1, pp. 200–222, 2023, doi: 10.2166/wcc.2022.257.
[22] N. T. T. Linh et al., “Flood susceptibility modeling based on new hybrid intelligence model: Optimization of XGboost model using GA metaheuristic algorithm,” Adv. Sp. Res., vol. 69, no. 9, pp. 3301–3318, 2022, doi: 10.1016/j.asr.2022.02.027.
[23] R. Abedi, R. Costache, H. Shafizadeh-Moghadam, and Q. B. Pham, “Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees,” Geocarto Int., vol. 37, no. 19, pp. 5479–5496, 2021, doi: 10.1080/10106049.2021.1920636.
[24] T. S. V. Razavi, A. Kornejady, H. R. Pourghasemi, and S. Keesstra, “Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms,” Sci. Total Environ., vol. 615, pp. 438–451, 2018, doi: 10.1016/j.scitotenv.2017.09.262.
[25] Q. T. Bui, Q. H. Nguyen, X. L. Nguyen, V. D. Pham, H. D. Nguyen, and V. M. Pham, “Verification of novel integrations of swarm intelligence algorithms into deep learning neural network for flood susceptibility mapping,” J. Hydrol., vol. 581, p. 124379, 2020, doi: 10.1016/j.jhydrol.2019.124379.
[26] H. D. Vinh and Y.-A. Liou, “Assessing the influence of human activities on flash flood susceptibility in mountainous regions of Vietnam,” Ecol. Indic., vol. 158, no. November 2023, p. 111417, 2024, doi: 10.1016/j.ecolind.2023.111417.
[27] M. B. Kia, S. Pirasteh, B. Pradhan, A. R. Mahmud, W. N. A. Sulaiman, and A. Moradi, “An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia,” Environ. Earth Sci., vol. 67, no. 1, pp. 251–264, 2012, doi: 10.1007/s12665-011-1504-z.
[28] M. S. Tehrany, S. Jones, and F. Shabani, “Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques,” Catena, vol. 175, no. December 2018, pp. 174–192, 2019, doi: 10.1016/j.catena.2018.12.011.
[29] S. Lee, J. C. Kim, H. S. Jung, M. J. Lee, and S. Lee, “Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea,” Geomatics, Nat. Hazards Risk, vol. 8, no. 2, pp. 1185–1203, 2017, doi: 10.1080/19475705.2017.1308971.
[30] Moore et al., “Digital terrain modelling: A review of hydrological, geomorphological, and biological applications,” Hydrol. Process., vol. 5, no. 1, pp. 3–30, 1991, doi: 10.1002/hyp.3360050103.
[31] P. P. Santos, E. Reis, S. Pereira, and M. Santos, “A flood susceptibility model at the national scale based on multicriteria analysis,” Sci. Total Environ., vol. 667, pp. 325–337, 2019, doi: 10.1016/j.scitotenv.2019.02.328.
[32] I. Chowdhuri, S. C. Pal, and R. Chakrabortty, “Flood susceptibility mapping by ensemble evidential belief function and binomial logistic regression model on river basin of eastern India,” Adv. Sp. Res., vol. 65, no. 5, pp. 1466–1489, 2020, doi: 10.1016/j.asr.2019.12.003.
[33] M. Panahi et al., “Flood spatial prediction modeling using a hybrid of meta-optimization and support vector regression modeling,” Catena, vol. 199, no. December 2020, p. 105114, 2021, doi: 10.1016/j.catena.2020.105114.
[34] E. Dodangeh et al., “Integrated machine learning methods with resampling algorithms for flood susceptibility prediction,” Sci. Total Environ., vol. 705, p. 135983, 2020, doi: 10.1016/j.scitotenv.2019.135983.
[35] M. H. Shafizadeh, R. Valavi, H. Shahabi, K. Chapi, and A. Shirzadi, “Novel forecasting approaches using combination of machine learning and statistical models for flood susceptibility mapping,” J. Environ. Manage., vol. 217, pp. 1–11, 2018, doi: 10.1016/j.jenvman.2018.03.089.
[36] G. Zhao, B. Pang, Z. Xu, D. Peng, and L. Xu, “Assessment of urban flood susceptibility using semi-supervised machine learning model,” Sci. Total Environ., vol. 659, pp. 940–949, 2019, doi: 10.1016/j.scitotenv.2018.12.217.
[37] O. Rahmati, H. Zeinivand, and M. Besharat, “Flood hazard zoning in Yasooj region, Iran, using GIS and multi-criteria decision analysis,” Geomatics, Nat. Hazards Risk, vol. 7, no. 3, pp. 1000–1017, 2016, doi: 10.1080/19475705.2015.1045043.
[38] T. Gudiyangada Nachappa, S. Tavakkoli Piralilou, K. Gholamnia, O. Ghorbanzadeh, O. Rahmati, and T. Blaschke, “Flood susceptibility mapping with machine learning, multi-criteria decision analysis and ensemble using Dempster Shafer Theory,” J. Hydrol., vol. 590, no. July, p. 125275, 2020, doi: 10.1016/j.jhydrol.2020.125275.
[39] H. Hong, P. Tsangaratos, I. Ilia, J. Liu, A. X. Zhu, and W. Chen, “Application of fuzzy weight of evidence and data mining techniques in construction of flood susceptibility map of Poyang County, China,” Sci. Total Environ., vol. 625, pp. 575–588, 2018, doi: 10.1016/j.scitotenv.2017.12.256.
[40] M. Sahana and P. P. Patel, “A comparison of frequency ratio and fuzzy logic models for flood susceptibility assessment of the lower Kosi River Basin in India,” Environ. Earth Sci., vol. 78, no. 10, pp. 1–27, 2019, doi: 10.1007/s12665-019-8285-1.
[41] A. E. M. Al-Juaidi, A. M. Nassar, and O. E. M. Al-Juaidi, “Evaluation of flood susceptibility mapping using logistic regression and GIS conditioning factors,” Arab. J. Geosci., vol. 11, no. 24, pp. 1–10, 2018, doi: 10.1007/s12517-018-4095-0.
[42] M. Shafapour Tehrany, F. Shabani, M. Neamah Jebur, H. Hong, W. Chen, and X. Xie, “GIS-based spatial prediction of flood prone areas using standalone frequency ratio, logistic regression, weight of evidence and their ensemble techniques,” Geomatics, Nat. Hazards Risk, vol. 8, no. 2, pp. 1538–1561, 2017, doi: 10.1080/19475705.2017.1362038.
[43] H. Hong, Y. Miao, J. Liu, and A. X. Zhu, “Exploring the effects of the design and quantity of absence data on the performance of random forest-based landslide susceptibility mapping,” Catena, vol. 176, no. December 2018, pp. 45–64, 2019, doi: 10.1016/j.catena.2018.12.035.
[44] B. Sahoo, C. Chatterjee, N. S. Raghuwanshi, R. Singh, and R. Kumar, “Flood Estimation by GIUH-Based Clark and Nash Models,” J. Hydrol. Eng., vol. 11, no. 6, pp. 515–525, 2006, doi: 10.1061/(asce)1084-0699(2006)11:6(515).
[45] A. Mosavi, P. Ozturk, and K. W. Chau, “Flood prediction using machine learning models: Literature review,” Water (Switzerland), vol. 10, no. 11, pp. 1–40, 2018, doi: 10.3390/w10111536.
[46] Z. Wang, C. Qin, B. Wan, and W. W. Song, “A comparative study of common nature‐inspired algorithms for continuous function optimization,” Entropy, vol. 23, no. 7, pp. 1–40, 2021, doi: 10.3390/e23070874.
[47] A. Arabameri et al., “Flood susceptibility mapping using meta-heuristic algorithms,” Geomatics, Nat. Hazards Risk, vol. 13, no. 1, pp. 949–974, 2022, doi: 10.1080/19475705.2022.2060138.
[48] S. Talukdar, P. Singha, S. Mahato, S. Pal, Y. Liou, and R. A., “Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations — A Review,” Remote Sens., vol. 12(7):1135, 2020, [Online]. Available: https://doi.org/10.%0A3390/rs12071135.
[49] Y. A. Liou, Q. V. Nguyen, D. V. Hoang, and D. P. Tran, “Prediction of soil erosion and sediment transport in a mountainous basin of Taiwan,” Prog. Earth Planet. Sci., vol. 9, no. 1, 2022, doi: 10.1186/s40645-022-00512-4.
[50] D. P. Roy et al., “Characterization of Landsat-7 to Landsat-8 reflective wavelength and normalized difference vegetation index continuity,” Remote Sens. Environ., vol. 185, pp. 57–70, 2016, doi: 10.1016/j.rse.2015.12.024.
[51] J. Ju and J. G. Masek, “The vegetation greenness trend in Canada and US Alaska from 1984-2012 Landsat data,” Remote Sens. Environ., vol. 176, pp. 1–16, 2016, doi: 10.1016/j.rse.2016.01.001.
[52] Z. Pironkova, R. Whaley, and K. Lan, “Time series analysis of Landsat NDVI composites with Google Earth Engine and Science and Research Technical Manual TM-06,” Sci. Res. Tech. Man. TM-06 Time, no. December, p. 39, 2018, doi: 10.13140/RG.2.2.16830.95040.
[53] F. E. Fassnacht, C. Schiller, T. Kattenborn, X. Zhao, and J. Qu, “A Landsat-based vegetation trend product of the Tibetan Plateau for the time-period 1990–2018,” Sci. Data, vol. 6, no. 1, pp. 1–11, 2019, doi: 10.1038/s41597-019-0075-9.
[54] G. F. Bonham-Carter, Geographic information systems for geoscientists-modeling with GIS., Computer m. Pergamon, 1994.
[55] R. Frank, “The Perceptron: a Probabilistic Model for Information Storage and Organization in the Brain,” Psychol. Rev., vol. 65, no. 6, pp. 386–408, 1958.
[56] H. M. Rizeei, B. Pradhan, and M. A. Saharkhiz, “Allocation of emergency response centres in response to pluvial flooding-prone demand points using integrated multiple layer perceptron and maximum coverage location problem models,” Int. J. Disaster Risk Reduct., vol. 38, p. 101205, 2019, doi: 10.1016/j.ijdrr.2019.101205.
[57] G. H. John and P. Langley, “Estimating Continuous Distributions in Bayesian Classifiers,” Proc. Elev. Conf. Uncertain. Artif. Intell., pp. 338–345, 1995, [Online]. Available: http://arxiv.org/abs/1302.4964.
[58] B. Boser, I. Guyon, V. V.-P. of the 5th, and U. 2003, “A training algorithm for optimal margin classifiers,” Gautampendse.Com, pp. 144–152., 1992.
[59] K. N. Stevens, T. M. Cover, and P. E. Hart, “Nearest Neighbor pattern classification,” IEEE Trans. Inf. theory, vol. IT-13, no. No.1, pp. 21–27, 1967, doi: 10.1007/springerreference_62518.
[60] H. Shahabi et al., “Flood detection and susceptibility mapping using Sentinel-1 remote sensing data and a machine learning approach: Hybrid intelligence of bagging ensemble based on K-Nearest Neighbor classifier,” Remote Sens., vol. 12, no. 2, 2020, doi: 10.3390/rs12020266.
[61] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-Augu, pp. 785–794, 2016, doi: 10.1145/2939672.2939785.
[62] J. Kennedy and E. Russell, “Particle Swarm Optimization,” TIn Proc. IEEE Int. Conf. neural networks, no. 4 pp, pp. 1942–1948, 1995, doi: 10.1007/978-3-319-46173-1_2.
[63] A. Sheta, “A Comparsion between Genetic Algorithms and Sequential Quadratic Programming in Solving Constrained Optimization Problems,” AIML J., vol. 6, no. January, pp. 67–74, 2006.
[64] S. N. Sivanandam and S. N. Deepa, Introduction to genetic algorithms. 2008.
[65] J. Hair, W. C. Black, B. J. Babin, and R. E. Anderson, Multivariate Data Analysis 7th Edition, 7th ed. Prentice Hall, New York, 2010.
[66] B. Feizizadeh and T. Blaschke, “GIS-multicriteria decision analysis for landslide susceptibility mapping: Comparing three methods for the Urmia lake basin, Iran,” Nat. Hazards, vol. 65, no. 3, pp. 2105–2128, 2013, doi: 10.1007/s11069-012-0463-3.
[67] D. Lallemant, P. Hamel, M. Balbi, T. N. Lim, R. Schmitt, and S. Win, “Nature-based solutions for flood risk reduction: A probabilistic modeling framework,” One Earth, vol. 4, no. 9, pp. 1310–1321, 2021, doi: 10.1016/j.oneear.2021.08.010.
[68] A. Beckers et al., “Contribution of land use changes to future flood damage along the river Meuse in the Walloon region,” Nat. Hazards Earth Syst. Sci., vol. 13, no. 9, pp. 2301–2318, 2013, doi: 10.5194/nhess-13-2301-2013.