Scholarlink

In recent years, machine learningMachine learning is more and more extensively applied to hydrogeological research for its reliability, efficiencyEfficiency and feasibility. This chapter presents a review on applicationApplication of machine learningMachine learning in hydrogeologyHydrogeology, or groundwater scienceScience and summarizes the associated challenges and prospects. In this chapter, commonly used machine learningMachine learning methodsMethod were firstly introduced, including naïve Bayes, artificial neural networkNetwork, support vector machine, decision tree and random forest. Then, overview of applying machine learningMachine learning to four main hydrogeological fields, including predicting groundwater variablesVariables, mapping hydrogeological variablesVariables, identifying groundwater contamination sourcesSource and assessing groundwater contamination risk, were summarized and presented. Finally, challenges and prospects of utilizing machine learningMachine learning to hydrogeologyHydrogeology were summarized. This chapter deepens understandingUnderstanding of applicationApplication of machine learningMachine learning to hydrogeologyHydrogeology, and provides further insights for international scholars.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning Techniques in Hydrogeological Research

  • 章节

  • 发表日期：

    2025年

查看全文
  • Song He,
  • Xiaoping Zhou,
  • Yuan Liu,
  • Xiaoguang Zhao,
  • Zilong Guan,
  • Yujie Ji,
  • Peiyue Li

摘要

In recent years, machine learningMachine learning is more and more extensively applied to hydrogeological research for its reliability, efficiencyEfficiency and feasibility. This chapter presents a review on applicationApplication of machine learningMachine learning in hydrogeologyHydrogeology, or groundwater scienceScience and summarizes the associated challenges and prospects. In this chapter, commonly used machine learningMachine learning methodsMethod were firstly introduced, including naïve Bayes, artificial neural networkNetwork, support vector machine, decision tree and random forest. Then, overview of applying machine learningMachine learning to four main hydrogeological fields, including predicting groundwater variablesVariables, mapping hydrogeological variablesVariables, identifying groundwater contamination sourcesSource and assessing groundwater contamination risk, were summarized and presented. Finally, challenges and prospects of utilizing machine learningMachine learning to hydrogeologyHydrogeology were summarized. This chapter deepens understandingUnderstanding of applicationApplication of machine learningMachine learning to hydrogeologyHydrogeology, and provides further insights for international scholars.