Impact of urbanization in the flood prediction at Kickapoo River basin, USA

Abstract

Climate change has significant impacts on river flood discharges, necessitating accurate long-term predictions for effective mitigation and adaptation strategies. This study investigates the influence of Urbanized Land Area (ULA) on flood discharge predictions using Artificial Neural Networks (ANN). Of the many reported studies concerning flood prediction using ANN, most of the studies restrict themselves to rainfall as the primary predictor variable along with its antecedents. Since urbanization strongly correlates with flood occurrences and can enhance predictive accuracy, this research aims to assess whether incorporating ULA alongside antecedent rainfall values as predictor variables improves flood discharge predictions in the Kickapoo River Basin, USA. A unique methodology was developed to identify the most predictive factors, and two ANN models were employed: the RF-Model, which uses only antecedent rainfall values, and the RFULA-Model, which includes ULA as an additional input. Results show a significant improvement in prediction accuracy with the RFULA-Model (Correlation Coefficient [CC] = 0.930; Normalized Root Mean Squared Error [NRMSE] = 0.157) compared to the RF-Model (CC = 0.743; NRMSE = 0.286). Further analysis indicated that the RFULA-Model predicted higher percentages of monthly average discharge exceeding critical thresholds during validation periods (2021-2050, 2051-2080, 2081-2099) at rates of 21%, 33%, and 34%, respectively, compared to 6%, 8%, and 7% for the RF-Model. These findings emphasize the importance of explicitly including causative inputs like ULA in ANN models, offering deeper insights into flood prediction accuracy under changing climate conditions.

Keywords

• Artificial Neural Network
• urbanization
• flood prediction
• impact of urbanization on flood
• climate change
• input selection in ANN

References

1. H. Tabari, “Climate change impact on flood and extreme precipitation increases with water availability,” Scientific Reports, vol. 10 (1), pp. 1–10, 2020.
2. B.K.Singh, M. Delgado-Baquerizo, E. Egidi, E. Emilio Guirado, J. E. Leach, H. Liu and P. Trivedi,"Climate change impacts on plant pathogens, food security and paths forward,". Nature Reviews Microbiology, vol. 21, pp.640–656, 2023.
3. R. Ehsan Eyshi, W. Heidi, A. Senthold, B. Kenneth, D. Jean Louis, E. Frank, M. Pierre, and S.M. Dilys, “Climate change impacts on crop yields,” Nature Reviews Earth & Environment, vol. 4, pp. 831–846, 2023.
4. D. E. H. J. Gernaat, H. S. de Boer, V. Daioglou, S. G. Yalew, C. Müller, and D. P. van Vuuren, “Climate change impacts on renewable energy supply,” Nature Climate Change, vol. 11 (2), pp. 119–125,2021.
5. D. L. Corwin, “Climate change impacts on soil salinity in agricultural areas,” European Journal of Soil Science, vol. 72 (2), pp. 842–862,2021.
6. C. Sivapragasam, P. Saravanan, and S. Balamurali, “Estimation of climate change impact on the flood of Kickapoo River at La Farge,” AIP Conference Proceedings, vol. 2463, p. 1, 2022.
7. A. Chowdhury, S. M. A. Reshad, and M. Kumruzzaman, “Hydrodynamic Flood Modelling for the Jamuna River Using Hec-Ras & Mike 11,” in Proc. 5th International Conference on Advances in Civil Engineering, pp. 21-23, 2020.
8. J. Zhang, M. Zhang, Y. Song, and Y. Lai, “Hydrological simulation of the Jialing River Basin using the MIKE SHE model in changing climate,” Journal of Water and Climate Change, vol. 12 (6), pp. 2495–2514,2021.

9. H. Tansar, M. Babur, and S. L. Karnchanapaiboon, “Flood inundation modeling and hazard assessment in Lower Ping River Basin using MIKE FLOOD,” Arabian Journal of Geosciences, vol. 13 (18), pp. 1–16,2020.
10. S. Malekzadeh, A. Arman, and A. Azari, “Flood Hydrograph Routing using Mike11 Numerical Model and Artificial Intelligence System (Case Study: Seymareh River),” Irrigation and Drainage Structures Engineering Research, vol. 21 (78), pp. 79–98, 2020.
11. V. Kumar, K. V. Sharma, T. Caloiero, D. J. Mehta, and K. Singh, “Comprehensive Overview of Flood Modeling Approaches: A Review of Recent Advances,” Hydrology, Vol. 10, Page 141, vol. 10 (7), p. 141, 2023.
12. C. Sivapragasam, A. Malathy, D. Ishwarya, P. Saravanan, and S. Balamurali, “Modelling the elements of flash flood hydrograph using genetic programming,” Indian Journal of Geo-Marine Sciences, vol. 49 (6), pp. 1031–1038, 2020.
13. N. Razali, S. Ismail, and A. Mustapha, “Machine learning approach for flood risks prediction,” IAES International Journal of Artificial Intelligence, vol. 9 (1), pp. 73–80, 2020.
14. H. Tamiru and M. O. Dinka, “Application of ANN and HEC-RAS model for flood inundation mapping in lower Baro Akobo River Basin, Ethiopia,” Journal of Hydrology: Regional Studies, vol. 36, p. 100855, 2021.
15. E. Samikwa, T. Voigt, and J. Eriksson, “Flood Prediction Using IoT and Artificial Neural Networks with Edge Computing,” in Proc. International Conferences on Internet of Things (i Things) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cyber-matics) 2020, vol. 28 12, pp. 234-240, 2020.
16. R. Tabbussum and A. Q. Dar, “Performance evaluation of artificial intelligence paradigms—artificial neural networks, fuzzy logic, and adaptive neuro-fuzzy inference system for flood prediction,” Environmental Science and Pollution Research, vol. 28 (20), pp. 25265–25282,2021.
17. N. A. Maspo, A. N. Bin Harun, M. Goto, F. Cheros, N. A. Haron, and M. N. Mohd Nawi, “Evaluation of Machine Learning approach in flood prediction scenarios and its input parameters: A systematic review,” IOP Conference Series: Earth and Environmental Science, vol. 479 (1), p. 012038, 2020.
18. A. Z. Dhunny, R.H. Seebocus, Z. Allam, M. Chuttur,M. Eltahan and H. Mehta., “Flood Prediction using Artificial Neural Networks: Empirical Evidence from Mauritius as a Case Study,” Knowledge Engineering and Data Science, vol. 3 (1), pp. 1–10, 2020.
19. N. T. T. Linh, H. Ruigar, S. Golian, G. T. Bawoke, V. Gupta, K. U. Rahman, A. Sankaran and Q. B. Pham., "Flood prediction based on climatic signals using wavelet neural network," Acta Geophysica, vol. 69 (4), pp. 1413–1426, 2021.
20. F. Y. Dtissibe, A. A. A. Ari, C. Titouna, O. Thiare, and A. M. Gueroui, “Flood forecasting based on an artificial neural network scheme,” Natural Hazards, vol. 104 (2), pp. 1211–1237, 2020.
21. A. A. Beshir and J. Song, “Urbanization and its impact on flood hazard: the case of Addis Ababa, Ethiopia,” Natural Hazards, vol. 109 (1), pp. 1167–1190, 2021.
22. M. M. Hasan, M. S. Mondol Nilay, N. H. Jibon, and R. M. Rahman, “LULC changes to riverine flooding: A case study on the Jamuna River, Bangladesh using the multilayer perceptron model,” Results in Engineering, vol. 18, p. 101079, 2023.
23. Z. Mingfang, R. Qingshan, W. Xiaohua, W. Jingsheng, Y. Xiaolin, and J. Zishan, “Climate change, glacier melting and streamflow in the Niyang River Basin, Southeast Tibet, China,” Ecohydrology, vol. 130 (2), pp. 126–130, 2010.
24. N. X. Hoan, D. N. Khoi, and P. T. T. Nhi, “Uncertainty assessment of streamflow projection under the impact of climate change in the Lower Mekong Basin: a case study of the Srepok River Basin, Vietnam,” Water and Environment Journal, vol. 34 (1), pp. 131–142, 2020.
25. A. B. Dariane and E. Pouryafar, “Quantifying and projection of the relative impacts of climate change and direct human activities on streamflow fluctuations,” Climate Change, vol. 165, pp. 1–2, 2021.
26. S. Chand, "Modeling predictability of traffic counts at signalised intersections using Hurst Exponent," Entropy, vol. 23 (2), pp. 188, 2021.
27. P. Saravanan, "Prediction of flood under climate change scenario a data driven approach," PhD. Thesis, Kalasalingam Academy of Research and Education, Srivilliputtur, India, Feb. 2023.
28. L. B. Ferreira, F. F. Cunha, R. A. Oliveira and E. I. F. Filho, "Estimation of reference evapotranspiration in Brazil with limited meteorological data using ANN and SVM – A new approach," Journal of Hydrology, vol. 572, pp. 556–570, 2019.
29. D. B. Topalović, M. D. Davidović, M. Jovanović, A. Bartonova, Z. Ristovski, and M. J. Stojanović., "In search of an optimal in-field calibration method of low-cost gas sensors for ambient air pollutants: Comparison of linear, multilinear and artificial neural network approaches," Atmospheric Environment, vol. 213, pp. 640–658, 2019.
30. S. A. Kelly, Z. Takbiri, P. Belmont, and E. F. Georgiou., "Human amplified changes in precipitation-runoff patterns in large river basins of the Midwestern United States," Hydrology and Earth System Sciences, vol. 21, pp. 5065–5088, 2017.
31. M. N. Ugural and H. I. Burgan., "Project Performance Evaluation using EVA Technique: Kotay Bridge Construction Project on Kayto River in Afghanistan," Technical Gazette, vol. 28, pp. 340–345, 2021.
32. S. B. Levin and C. A. Sanocki., "Estimating Flood Magnitude and Frequency for Unregulated Streams in Wisconsin," U.S. Geological Survey Scientific Investigations Report 2022–5118, 25 p., 2022.
33. W.J.M. Knoben, J.E. Freer, and R.A. Woods., "Technical note: Inherent benchmark or not? Comparing Nash-Sutcliffe and Kling-Gupta efficiency scores," Hydrology and Earth System Sciences, vol. 23 (10), pp. 4323–4331, 2019.
34. G. Golmohammadi, S. Prasher, A. Madani and R, Rudra., Evaluating Three Hydrological Distributed Watershed Models: MIKE-SHE, APEX, SWAT, Hydrology, vol. 1 (1), pp. 20–39, 2014.
35. F. Demirbaş and E. Elmaslar Özbaş, "Review on the use of artificial neural networks to determine therelationship between climate change and the occupancy rates of dams", Environmental Research and Technology, vol. 7 (1), pp. 140–147, 2024.
36. P. F. Juckem, R. J. Hunt, M. P. Anderson, and D. M. Robertson, “Effects of climate and land management change on streamflow in the driftless area of Wisconsin,” Journal of Hydrology, vol. 355 (4), pp. 123–130, 2008.
37. S. Doulabian, S. Golian, A. S. Toosi, C. Murphy, "Evaluating the effects of climate change on precipitation and temperature for Iran using RCP scenarios", Journal of Water and Climate Change, vol. 12 (1), pp.166–184, 2021.