Preprints
https://doi.org/10.5194/hess-2020-208
https://doi.org/10.5194/hess-2020-208
28 May 2020
 | 28 May 2020
Status: this preprint was under review for the journal HESS but the revision was not accepted.

Importance of spatial and depth-dependent drivers in groundwater level modeling through machine learning

Pragnaditya Malakar, Abhijit Mukherjee, Soumendra N. Bhanja, Dipankar Saha, Ranjan Kumar Ray, Sudeshna Sarkar, and Anwar Zahid

Abstract. The water and food security of South Asia is embedded in the groundwater resources of the transboundary aquifer system of Indus-Ganges-Brahmaputra-Meghna (IGBM) rivers, which has been subjected to diverse natural and anthropogenic triggers. Thus, understanding the relative importance of such triggers in groundwater level change and developing a prediction framework is essential to sustain future stress. Although a number of studies on groundwater level prediction and simulation exist in the literature, characterization of predictive performances of groundwater level modeling using a large network of ground-based observations (n = 2303) is not yet reported. To identify the spatial and depth-wise predictors influence, here, we used linear regression based dominance analysis and machine learning methods (Support Vector Machine and Artificial Neural network) on long term (1985–2015) GWLs and/or climatic variables in the parts of IGBM basin aquifers. The results from the dominance analysis show that groundwater level change is primarily influenced by abstraction and population in most of the IGBM, whereas in the Brahmaputra basin, precipitation exhibits greater influence. Our results show a large proportion of the observation wells (n > 50 % for ANN and n > 65 % for SVM) demonstrate good correlation (r > 0.6, p < 0.05), Nash-Sutcliff efficiency (NSE > 0.65), and normalized root mean square error (RMSEn < 0.6) between the observed and simulated values. However, the results in the highly abstracted parts of the basin are poor, due to insufficient knowledge of groundwater abstraction. Furthermore, a significant decrease in performance from shallow (intake depth < 35 m) to deep observation wells (intake depth > 35 m) could be linked to the change in groundwater abstraction pattern from shallow to deep groundwater in recent times. We also find that, in areas where natural factors dominate over anthropogenic factors, climatic variables may be used as suitable predictors for the groundwater level.

Pragnaditya Malakar, Abhijit Mukherjee, Soumendra N. Bhanja, Dipankar Saha, Ranjan Kumar Ray, Sudeshna Sarkar, and Anwar Zahid
 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
Pragnaditya Malakar, Abhijit Mukherjee, Soumendra N. Bhanja, Dipankar Saha, Ranjan Kumar Ray, Sudeshna Sarkar, and Anwar Zahid
Pragnaditya Malakar, Abhijit Mukherjee, Soumendra N. Bhanja, Dipankar Saha, Ranjan Kumar Ray, Sudeshna Sarkar, and Anwar Zahid

Viewed

Total article views: 1,337 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
924 373 40 1,337 150 42 33
  • HTML: 924
  • PDF: 373
  • XML: 40
  • Total: 1,337
  • Supplement: 150
  • BibTeX: 42
  • EndNote: 33
Views and downloads (calculated since 28 May 2020)
Cumulative views and downloads (calculated since 28 May 2020)

Viewed (geographical distribution)

Total article views: 1,204 (including HTML, PDF, and XML) Thereof 1,204 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 27 Mar 2024
Download
Short summary
Groundwater withdrawals and population are the primary influencing factors affecting groundwater level change in most of the Indus-Ganges-Brahmaputra-Meghna basin aquifer of South-Asia. Machine learning-based methods can be used to model groundwater level efficiently in the basin. However, in areas where human influence dominates, these methods have limitations in modeling groundwater level due to insufficient knowledge of spatial and depth-dependent groundwater withdrawals.