Journal of Applied Science and Engineering

Published by Tamkang University Press


Impact Factor



Hao Duc DoThis email address is being protected from spambots. You need JavaScript enabled to view it.

FPT University, Ho Chi Minh city, Vietnam


Received: August 29, 2023
Accepted: November 28, 2023
Publication Date: March 1, 2024

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||  

This research proposes a new approach using multivariable linear regression to predict the riverbank erosion speed. As a simple and interpretable model, the proposed approach gains two main achievements. First, it can specify the main factors causing riverbank erosion. Notably, the method identifies the river’s depth and the water flow’s hydraulic gradient, contributing primarily to the erosion speed. Second, multivariable linear regression can be learned from such a small dataset. This aspect makes the range of applications for the method much broader. The Experimental results show that the multivariable linear regression can predict erosion speed well. With a dataset with only 27 records, the method can predict the erosion speed with an error of around 2 meters per year. In the future, a more extensive training dataset or a more complicated regression model is requested to gain a better result.


Keywords: riverbank erosion prediction, multivariable linear regression, machine learning

  1. [1] A. Ghosh, M. B. Roy, and P. K. Roy, (2022) “Evaluating lateral riverbank erosion with sediment yield through integrated model in lower Gangetic floodplain, India" Acta Geophysica 70: 1769–1795. DOI: 10.1007/s11600-022-00822-7.
  2. [2] B. K. Ghosh, (2022) “An empirical study of riverbank erosion in Charbhadrasan Upazila of Faridpur District, Bangladesh" Urban, Planning and Transport Research 10: 502–513. DOI: 10.1080/21650020.2022.2123034.
  3. [3] E. J. Hickin and G. C. Nanson, (1984) “Lateral Migration Rates of River Bends" Journal of Hydraulic Engineering 110: 1557–1567. DOI: 10.1061/(ASCE)0733- 9429(1984)110:11(1557).
  4. [4] H. J.M., (1980) “Magnitude and Distribution of Rates of River Bank Erosion" Earth Surface Processes: 143–157. DOI: 10.1002/esp.3760050205.
  5. [5] B. J.C., (1982) “Stream Channel Stability Assessment" Report No. FHWA/RD-82/021: 41.
  6. [6] P. M. Keady P.D., (1977) “The Downstream Migration Rate of River Meandering Patterns" 12th Mississippi Water Resources Conference: 29–34.
  7. [7] A. J. Odgaard and A. Spoljaric, (1986) “Sediment Control by Submerged Vanes" Journal of Hydraulic Engineering 112: 1164–1180. DOI: 10.1061/(ASCE)0733- 9429(1986)112:12(1164).
  8. [8] J.-L. Briaud, F. C. K. Ting, H.-C. Chen, Y. Cao, S.-W. Han, and K. Kwak, (2001) “Erosion function apparatus for scour rate predictions" Journal of Geotechnical and Geoenvironmental Engineering 127: 105–113. DOI: 10.1061/(ASCE)1090-0241(2001)127:2(105).
  9. [9] E. R. Thieler, E. A. Himmelstoss, J. L. Zichichi, and A. Ergul. “The Digital Shoreline Analysis System (DSAS) Version 4.0 - An ArcGIS extension for calculating shoreline change”. In: 2009. DOI: 10.3133/ofr20081278.
  10. [10] A. Q, (2020) “Multiple Linear Regression" Principles of Managerial Statistics and Data Science:
  11. [11] S. K. Gupta and A. P. Agarwal, (2021) “Predicting Total Sugar Production Using Multivariable Linear Regression" 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS): 465–469. DOI: 10.1109/ICCCIS51004.2021.9397078.
  12. [12] H. G. Perros, (2021) “Multivariable Linear Regression" An Introduction to IoT Analytics:
  13. [13] D. Q. Thien, T. T. Nhan, N. Q. Tuan, and H. T. Thanh, (2017) “Experiment with semi-empirical method of Hickin E.J - Nanson G.C to predict the erosion of Gianh - Nhat Le riverbanks in Quang Binh province" Journal of Science of Lac Hong University Special issue: 60–67.