Abstract

Overexploitation of groundwater resources has caused groundwater-related problems all over the world. Effective groundwater governance is a favorable guarantee for its protection and sustainable utilization. Accurate prediction of groundwater level (GWL) or depth to groundwater (GWD) plays an important role in groundwater resource management. Due to the limitations and complexity of numerical models, this study aims to develop surrogate models that can dually control the GWL (or GWD) and groundwater quantity (GWQ) in each district of the Beijing Plain, China, using the methods of multiple linear regression (MLR) and back propagation artificial neural network (BP-ANN). This study used 180 monthly GWD data records, including the first 168 data records for model development (training) and the remaining 12 data records for model verification. The results indicate that the Nash–Sutcliffe efficiency coefficient (NSE) and correlation coefficient (R) for both the MLR and BP-ANN models are high in most districts and that the MLR models are more appropriate in this study. Fifteen scenarios under different conditions of groundwater use and precipitation are designed to demonstrate the applicability of the developed model in groundwater management. The surrogate models are effective tools that can be used by decision-makers for groundwater management.

Highlights

  • Excluding glacial water, groundwater is the largest fresh water resource in the world

  • China faces a considerable challenge in groundwater management due to the shortage of

  • China faces a considerable challenge in groundwater management due to the shortage of groundwater resources, especially in North China

Read more

Summary

Introduction

Groundwater is the largest fresh water resource in the world. Due to characteristics such as well water quality, strong regulation ability and steady storage, groundwater plays a vital role in agriculture, industry, public supply and ecosystems in many countries [1]. There are many areas throughout the world where aquifers face depletion, such as California’s Central Valley in the United States [4], the North China Plains Aquifers [5], and the Neogene and Dammam Aquifers in eastern Saudi Arabia [6]. The study area is the Beijing Plain, located in the northwest region of the North China Plain. AreaPlain, The study areaofisthe the Beijing located the northwest region thecovers.

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call