Spatial and Temporal Patterns of Groundwater Levels: A Case Study of Alluvial Aquifers in the Murray–Darling Basin, Australia

Guobin Fu (), Stephanie R. Clark, Dennis Gonzalez, Rodrigo Rojas and Sreekanth Janardhanan
Additional contact information
Guobin Fu: CSIRO Environment, Floreat, WA 6014, Australia
Stephanie R. Clark: CSIRO Environment, Eveleigh, NSW 2015, Australia
Dennis Gonzalez: CSIRO Environment, Adelaide, SA 5000, Australia
Rodrigo Rojas: CSIRO Environment, Dutton Park, Brisbane, QLD 4102, Australia
Sreekanth Janardhanan: CSIRO Environment, Dutton Park, Brisbane, QLD 4102, Australia

Sustainability, 2023, vol. 15, issue 23, 1-18

Abstract: Understanding the temporal patterns in groundwater levels and their spatial distributions is essential for quantifying the natural and anthropogenic impacts on groundwater resources for better management and planning decisions. The two most popular clustering analysis methods in the literature, hierarchical clustering analysis and self-organizing maps, were used in this study to investigate the temporal patterns of groundwater levels from a dataset with 910 observation bores in the largest river system in Australia. Results showed the following: (1) Six dominant cluster patterns were found that could explain the temporal groundwater trends in the Murray–Darling Basin. Interpretation of each of these patterns indicated how groundwater in each cluster behaved before, during, and after the Millennium Drought. (2) The two methods produced similar results, indicating the robustness of the six dominant patterns that were identified. (3) The Millennium Drought, from 1997 to 2009, had a clear impact on groundwater level temporal variability and trends. An example causal attribution analysis based on the clustering results (using a neural network model to represent groundwater level dynamics) is introduced and will be expanded in future work to identify drivers of temporal and spatial changes in groundwater level for each of the dominant patterns, leading to possibilities for better water resource understanding and management.

Keywords: clustering; groundwater; machine learning; Murray–Darling Basin; neural networks; trend analysis; unsupervised learning (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/23/16295/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/23/16295/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:23:p:16295-:d:1287409

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().