随机森林理论及其在水文地质领域的研究进展

A review on the progresses in random forests theory and its applications in hydrogeology

随机森林理论是近年来快速发展的一种人工智能集成学习算法,由于其对数据系列中异常值的容忍度较高,且预测结果准确度显著高于其他常用算法,在以水文地质领域为代表的自然科学研究中的应用越来越广泛.本文在介绍随机森林算法理论和应用方法的基础上,结合国外内已有研究成果,分析其在地下水潜力评估、地表水-地下水转化、地下水水质评价和地下水污染预测等水文地质领域的应用效果,对随机森林理论在水文地质领域的应用前景和进一步发展的方向进行了讨论.结果表明,随机森林理论可以有效解决水文地质领域研究中的参数和过程不确定性问题,在水文地质结构精确刻画、水文地质参数准确反演、水文地质过程的描述均具有广阔的应用前景.

Random Forest Theory is a rapidly developing artificial intelligence integrated learning algorithm and increasingly used in the fields of hydrogeology due to its higher tolerance of outliers in data series and significantly higher accurate prediction than other commonly used algorithms do.Based on the introduction of the theory and applications of the random forest algorithm,this paper reviewed its applications in the hydrogeological fields such as groundwater potential assessment,surface water-groundwater conversion,groundwater quality assessment and groundwater contamination prediction.The results show that the random forest theory can effectively solve the problems related to parameter and process uncertainty in hydrogeological researches,and has broad application prospects in the accurate portrayal of hydrogeological structure,accurate inversion of hydrogeological parameters and description of hydrogeological processes.