Simulation of regional groundwater levels in arid regions using interpretable machine learning models
Qi Liu1, Dongwei Gui2, Lei Zhang2
1State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Urumqi, Xinjiang, China; College of Life Science and Technology, Jinan University, Guangzhou, Guangdong, China.
The Science of the Total Environment
|April 1, 2022
Summary
Accurate groundwater level forecasting in arid regions is crucial for water management. Machine learning models effectively predict groundwater changes influenced by flow volume and proximity to water sources, aiding ecosystem stability.
Area of Science:
- Hydrology and Water Resource Management
- Machine Learning and Artificial Intelligence
- Environmental Science and Ecology
Background:
- Effective groundwater management is vital for arid regions to sustain human and ecosystem needs.
- The lower Tarim River basin (LTRB), an extreme dryland, faces challenges in managing its groundwater resources.
- Spatiotemporally inconsistent groundwater monitoring data complicates accurate forecasting in such environments.
Purpose of the Study:
- To simulate and predict groundwater levels in the LTRB using Machine Learning and Deep Learning approaches.
- To identify key meteorological, hydrological, and environmental variables influencing groundwater dynamics.
- To provide a scientific basis for sustainable water resource management in arid regions with intermittent flow.
Main Methods:
- Employed various Machine Learning and Deep Learning models: Support Vector Machine, Generalized Regression Neural Network, Decision Tree, Random Forest (RF), Convolutional Neural Network, Long Short Term Memory, and Gated Recurrent Network.
- Utilized easily accessible input data: relative humidity, flow volume, and distance to the riverbank.
- Applied the Shapley Additive Explanations (SHAP) method to interpret the Random Forest model's predictions and variable importance.
Main Results:
- Machine learning models successfully predicted spatiotemporal groundwater variations using inconsistent data.
- Flow volume and distance to the river channel/reservoir were identified as critical factors influencing groundwater levels.
- Predictions indicated a potential average groundwater decline to -6.4 m by 2021-2023, limiting suitable vegetation areas to 39% without water conveyance.
Conclusions:
- Annual water conveyance is necessary to maintain ecosystem stability in the LTRB.
- The study provides a robust framework for spatiotemporal groundwater level prediction in arid regions with intermittent recharge.
- Findings support informed, sustainable water resource management strategies for drought-prone areas.
Keywords:
Arid regionsDeep learningEcological water conveyanceGroundwater levelMachine learningShapely additive explanationsMore Related Videos
Related Concept Videos
01:12Modeling and Similitude
360
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
360
01:03Precipitation Gravimetry
7.8K
Precipitation gravimetry is based on converting an analyte into a sparingly soluble precipitate, which is separated by filtration and weighed. An ideal precipitate should be pure, insoluble, of known composition, and easily filtered from the reaction mixture.
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
7.8K
01:29Levels of Use of a GIS
111
Geographic Information Systems (GIS) operate across three levels of application, each representing an increasing degree of complexity: data management, analysis, and prediction. These levels reflect the expanding functionality and versatility of GIS technology in handling spatial data for diverse purposes.Data ManagementAt its foundational level, GIS serves as a tool for data management, enabling the input, storage, retrieval, and organization of spatial data. This level is often employed in...
111
01:30Typical Model Studies
453
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
453
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
128
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
128
01:18Steps in Outbreak Investigation
236
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
236