Optimal River Interlinking using Data Driven Machine Learning Techniques
Amitabha Nath1, Lalhmingliana2, Goutam Saha3
1Amitabha Nath*, Department of IT, NEHU, Shillong, India.
2Lalhmingliana, Department of Computer Engg., Mizoram University., India.
3Goutam Saha, Department of IT, NEHU, Shillong, India.

Manuscript received on November 15, 2019. | Revised Manuscript received on November 23, 2019. | Manuscript published on November 30, 2019. | PP: 760-765 | Volume-8 Issue-4, November 2019. | Retrieval Number: D7151118419/2019©BEIESP | DOI: 10.35940/ijrte.D7151.118419

Open Access | Ethics and Policies | Cite  | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: India’s increasing population, rapid urbanization and indiscriminate destruction of water bodies creating a grave threat on its existing water demand and supply balance. Primary fresh water sources such as rivers and wells are gradually getting dry. As a consequence, it is estimated that India would become a water scarce nation by 2050. To address the issue, massive survey work was conducted and various inter basin water transfer schemes were chalked out. However, these schemes became subject of controversy owing to its technical risk and huge cost. To make this effort cost efficient, in this investigation, computational approaches have been undertaken to assist in the decision making process. Current research endeavour suggests that these efforts are quite accurate, less costly and can be carried out in much less time. The inputs to these computational models are landscape elevation, land use data, soil information, precipitation level etc.. The estimated optimal river interlinking routes will be the output of the proposed model. Several efforts have been undertaken earlier in this direction with various limitations. In this paper, we address the same issue using machine learning approach. For experimental purpose Jogigopa-Tista link is considered as the test case. Optimal routing path is been estimated using the developed technique. Thereafter, the results are compared with the National Water Development Agency (NWDA) proposed routes. It is found that the proposed model’s outcome exhibits a considerable amount of similarity with the NWDA proposed route.
Keywords: Dijkstra Algorithm, MSO, Multiple Linear Regression, Optimal River Route, River interlinking.
Scope of the Article: Machine Learning.