基于机器学习的农村水质水色分类研究  

Research on classification of rural water quality and color based on machine learning

作　　者：高佳颀 吴芳 Gao Jiaqi;Wu Fang(College of Computer and Information Engineering,Tianjin Agricultural University,Tianjin 300392,China)

机构地区：[1]天津农学院计算机与信息工程学院,天津300392

出　　处：《天津农学院学报》2022年第1期61-65,共5页Journal of Tianjin Agricultural University

基　　金：天津哲学社会科学规划项目(TJGL19-027)。

摘　　要：随着农村经济逐步发展,农村周边工厂排放的工业污水以及农村生产生活过程中产生的污水对农村的水资源造成了极大污染与危害。为帮助改善水资源环境,监测水环境变化,建设美丽乡村,利用图像处理技术和机器学习算法,对农村水质进行分类。对采集的水质图像进行切割并提取图像的颜色矩特征,以此作为样本建立水质分类模型,分别用决策树和支持向量机进行水质水色分类。根据分类结果判断水质是否受到污染,以及时采取措施,为农村水污染的治理提供支持。分类结果表明,支持向量机的模型准确率为96%,决策树的模型准确率为83%,支持向量机的识别准确率要高于决策树。With the gradual development of the rural economy,the industrial sewage discharged from the factories in the surrounding countryside and the sewage generated in the process of rural production and life have caused great pollution to the rural water environment’In order to help improve the water environment,monitor changes in the water environment,and build beautiful villages,this paper classified the water quality in rural areas based on image processing technology and machine learning algorithms’ By cutting the collected water quality images and extracting the color moment features of the images,the water quality classification model was established as a sample,and the water quality and water color classification were performed using decision trees and support vector machines respectively’The classification results was used to judge whether the water quality was polluted,and timely measures were taken to provide support for the treatment of rural water pollution’The classification results showed that the model accuracy of support vector machine was 96%,the model accuracy of decision tree was 83%,and the recognition accuracy of support vector machine was higher than that of decision tree.

关 键 词：智慧农业 水质分类 预测预警 农村水资源 水污染 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]