Checking for non-preferred file/folder path names (may take a long time depending on the number of files/folders) ...

Asynchronous Regime Shifts in Groundwater Pumping in the High Plains Aquifer, 1960–2020


Authors:
Owners: This resource does not have an owner who is an active HydroShare user. Contact CUAHSI (help@cuahsi.org) for information on this resource.
Type: Resource
Storage: The size of this resource is 8.6 MB
Created: May 12, 2026 at 7:17 p.m. (UTC)
Last updated: May 16, 2026 at 8:46 p.m. (UTC) (Metadata update)
Published date: May 16, 2026 at 8:46 p.m. (UTC)
DOI: 10.4211/hs.9067ac2d076d486ea2c9cb78898155d9
Citation: See how to cite this resource
Content types: CSV Content 
Sharing Status: Published
Views: 106
Downloads: 2
+1 Votes: 1 other +1 this
Comments: No comments (yet)

Abstract

Groundwater pumping in agricultural aquifers reflects both hydroclimatic conditions and anthropogenic controls, but their relative importance can change over time. We analyzed annual pumping in the High Plains Aquifer Hydrologic Observatory Area (HPAHOA) from 1960 to 2020 using Deep Temporal Clustering, Bayesian changepoint detection, regime-aware XGBoost, and SHAP attribution. Approximately 13,000 cell-level pumping trajectories separated into three behavioral clusters, with asynchronous changepoints in 1974, 2000, and 2005. Models trained only on pre-changepoint data transferred poorly to post-changepoint periods, while models including post-changepoint information showed the greatest improvement in Cluster 3, indicating regime-dependent predictor–response relationships. SHAP attribution showed that dominant predictors differed across clusters and between full-record and changepoint-year conditions: anthropogenic predictors were more influential in Clusters 1 and 2, whereas precipitation was more influential in Cluster 3. These results show that pumping nonstationarity across the HPAHOA is spatially heterogeneous, asynchronous, and regime-dependent.

Subject Keywords

Coverage

Spatial

Coordinate System/Geographic Projection:
WGS 84 EPSG:4326
Coordinate Units:
Decimal degrees
Place/Area Name:
High Plains Aquifer Hydrologic Observatory Area (HPAHOA)
North Latitude
41.0000°
East Longitude
-98.0000°
South Latitude
39.0000°
West Longitude
-104.0000°

Temporal

Start Date:
End Date:

Content

readme.txt

This repository contains the code and data used to generate the
figures in the paper.


================================================================
Dataset Description
================================================================



1. dtc_latent_features
--------------------------
The latent feature representations learned by the DTC model.
These are the low-dimensional embeddings produced by the temporal
autoencoder component of DTC, which compress each input time series
into a compact feature vector. The clustering step is performed in
this latent space rather than on the raw time series.



2. dtc_cluster_assignments
------------------------------
The cluster labels assigned to each sample by the DTC model. Each
entry corresponds to the cluster index that the DTC model assigned
to the sample at the same position in the input dataset.



3. cluster_mean_annual_pumping_2020
---------------------------------------
The mean annual groundwater pumping rate for the year 2020,
computed per cluster. For each cluster, all samples assigned to
that cluster are aggregated and their annual pumping rates are
averaged.




4. Data_c0, Data_c1, Data_c2
----------------------------------------
Preprocessed climate and anthropogenic feature data for each
cluster, separated by cluster ID:

   - Data_c0 -- samples assigned to cluster 1
   - Data_c1 -- samples assigned to cluster 2
   - Data_c2 -- samples assigned to cluster 3

Each file contains the processed input features (climate variables
and anthropogenic drivers) for the members of that cluster.

How to Cite

Xu, Z., Y. Hu, S. Xi, Z. Fu (2026). Asynchronous Regime Shifts in Groundwater Pumping in the High Plains Aquifer, 1960–2020, HydroShare, https://doi.org/10.4211/hs.9067ac2d076d486ea2c9cb78898155d9

This resource is shared under the Creative Commons Attribution CC BY.

http://creativecommons.org/licenses/by/4.0/
CC-BY

Comments

There are currently no comments

New Comment

required