Study on the correlation between deforestation and flood occurrence: an analysis based on Lasso regression
Abstract
to natural factors such as heavy rain, melting ice and snow, and storm surges. As a natural disaster with strong suddenness and wide impact,
it poses a serious threat to human society. Based on historical flood event data, this paper focuses on the study of the multi-level risk warning
system of flood disasters, aiming to improve the response capability and disaster reduction efficiency of flood events. Through Lasso regression and cross-validation technology, five key factors closely related to flood occurrence are screened out-”deforestation, climate change, silt
deposition, agricultural practice and insufficient planning”. The role mechanism of these factors in causing floods is further analyzed, and
scientific suggestions and optimization measures for early prevention of floods are proposed, in order to provide data support and theoretical
basis for the formulation of disaster prevention and mitigation policies.
Keywords
Full Text:
PDFReferences
[1]Satapathy, D. P., & Mishra, B. P. (2024). Flood susceptibility modeling by integrating tree‐based regression with metaheuristic algorithm, BWO. Transactions in GIS, 28(5), 1043-1064.
[2]Gao, B., Shan, Y., Liu, X., Yin, S., Yu, B., Cui, C., & Cao, L. (2024). Prediction and driving factors of forest fire occurrence in Jilin
Province, China. Journal of Forestry Research, 35(1), 21.
[3]Shojaeian, A., Shafizadeh-Moghadam, H., Sharafati, A., & Shahabi, H. (2024). Extreme flash flood susceptibility mapping using a
novel PCA-based model stacking approach. Advances in Space Research.
[4]Tapias-Rivera, J., & Gutiérrez, J. D. (2023). Environmental and socio-economic determinants of the occurrence of malaria clusters
in Colombia. Acta Tropica, 241, 106892.
[5]Khosravi, K., Golkarian, A., Melesse, A. M., & Deo, R. C. (2022). Suspended sediment load modeling using advanced hybrid rotation forest based elastic network approach. Journal of Hydrology, 610, 127963.
[6]Kainthura, P., & Sharma, N. (2022). Hybrid machine learning approach for landslide prediction, Uttarakhand, India. Scientific reports,12(1), 20101.
[7]Kamil, N. N., Xiao, S., Salleh, S. N. S., Xu, H., & Zhuang, C. C. (2024). Nonlinear impacts of climate anomalies on oil palm productivity.Heliyon, 10(15).
[8]Kalu, I., Ndehedehe, C. E., Okwuashi, O., & Eyoh, A. E. (2021). Assessing freshwater changes over Southern and Central Africa
(2002–2017). Remote Sensing, 13(13), 2543.
DOI: http://dx.doi.org/10.18686/ag.v8i4.13862
Refbacks
- There are currently no refbacks.
