Reconstructing high-resolution groundwater level data using a hybrid random forest model to quantify distributed groundwater changes in the Indus Basin

Arshad, Arfan, Mirchi, Ali, Vilcaez, Javier, Umar Akbar, Muhammad and Madani, Kaveh, (2024). Reconstructing high-resolution groundwater level data using a hybrid random forest model to quantify distributed groundwater changes in the Indus Basin. Journal of Hydrology, 628 N/A-N/A

Document type:
Article
Collection:
UNU-INWEH Journal Articles

Metadata
Links
Versions
Statistics
  • Sub-type Journal article
    Author Arshad, Arfan
    Mirchi, Ali
    Vilcaez, Javier
    Umar Akbar, Muhammad
    Madani, Kaveh
    Title Reconstructing high-resolution groundwater level data using a hybrid random forest model to quantify distributed groundwater changes in the Indus Basin
    Appearing in Journal of Hydrology
    Volume 628
    Publication Date 2024-01-01
    Place of Publication N/A
    Publisher Elsevier B.V.
    Start page N/A
    End page N/A
    Language eng
    Abstract High-resolution, continuous groundwater data is important for place-based adaptive aquifer management. This information is unavailable in many areas due to spatial sparsity of and temporal gaps in groundwater monitoring. This study advances the ability to generate high-resolution (1 km2), temporally continuous estimates of groundwater level (GWL) changes by incorporating 1 km2 covariates and existing piezometer observations into predictive modeling. We employed a hybrid machine learning (ML) model, primarily using the geographically weighted random forest (RFgw) model. To assess the performance of the RFgw model, we conducted a comprehensive comparison with the SGS geostatistical method and non-spatial ML models (RF and XGBoost). The framework was implemented across the Indus Basin using biannual (July and Oct) GWL data from piezometers and local covariates from 2003 to 2020. The RFgw model demonstrated superior accuracy in predicting GWLs, improving R2 by 10 %, 17 %, and 22 % compared to SGS, RF, and XGBoost, respectively. Notably, SGS, RF, and XGBoost substantially underestimated the GWL in deeper wells (7–11 m), whereas RFgw showed a much smaller underestimation (up to ∼ 3 m). The 90 % prediction interval revealed that RFgw had less uncertainty (1–3 m) followed by RF (2–5 m), and SGS and XGBoost (up to 8 m) for most testing piezometers. Incorporating high-resolution covariates into RFgw predictive modeling provided reliable estimates of GWL changes for unmonitored sites. Using the reconstructed GWL data, we examined the GWL changes in head (i.e., upstream) and tail (i.e., downstream) farms within canal distributaries, illustrating faster groundwater drawdown in tail farms (e.g., 0.82 m/yr) than head farms (0.02 m/yr in the Hakra canal distributary). Densely populated urban areas (e.g., Lahore, Multan, and Faisalabad) had the highest GWL decline (e.g., up to 0.9 m/yr). The framework can be used in other groundwater-stressed regions to support better aquifer management in the face of limited in-situ observations.
    Copyright Holder Elsevier B. V.
    Copyright Year 2024
    Copyright type All rights reserved
    DOI 10.1016/j.jhydrol.2023.130535
  • Versions
    Version Filter Type
  • Citation counts
    Google Scholar Search Google Scholar
    Access Statistics: 20 Abstract Views  -  Detailed Statistics
    Created: Thu, 26 Sep 2024, 03:14:20 JST by Haideh Beigi on behalf of UNU INWEH