基于决策树的城市环境空气质量评价模型实证研究
|
摘要
科学地对城市环境空气质量进行评价,并进一步加强空气污染的防治,具有重大的现实意义。选取空气质量6个影响因素为解释变量,量化后的空气质量等级为目标变量,利用分类回归决策树算法构建预测模型,得出空气质量评价解释变量与空气质量等级之间的内在映射关系,并分析目标变量与各影响因子间的重要性关系。选取天津市空气质量历史数据进行评价实验,经实验结果证明,评价训练集和测试集的预测准确率分别为97.76%和96.09%,说明该方法确实可行。
How to scientifically evaluate air quality and further strengthen the prevention and control of air pollution has great practical significance. Six influencing factors of air quality were selected as explanatory variables, and the quantified air quality level was the target variable. The decision tree algorithm-"classification and regression trees" was used to train the internal mapping relationship between the air quality evaluation as explanatory variables and the air quality level. And analyze the importance relationship between the target variable air quality level and each impact factor. The Tianjin air quality historical data was selected for evaluation experiments. The experimental results show that the prediction accuracy of the evaluation training set and the test set are 97.76% and 96.09%, respectively. The method is feasible.
How to scientifically evaluate air quality and further strengthen the prevention and control of air pollution has great practical significance. Six influencing factors of air quality were selected as explanatory variables, and the quantified air quality level was the target variable. The decision tree algorithm-"classification and regression trees" was used to train the internal mapping relationship between the air quality evaluation as explanatory variables and the air quality level. And analyze the importance relationship between the target variable air quality level and each impact factor. The Tianjin air quality historical data was selected for evaluation experiments. The experimental results show that the prediction accuracy of the evaluation training set and the test set are 97.76% and 96.09%, respectively. The method is feasible.
引文
[1] VARDOULAKIS S,FISHER B,PERICLEOUS K,et al.Modelling air quality in street canyons:a review[J].Atmospheric Environment,2003,37(2):155-182.
[2] 江晓晴,鲁明浩,鲁园园,等.基于模糊数学的城市空气质量的分析与评价[J].环境与发展,2015,27(6):56-59.
[3] JOSé JUAN CARBAJAL-HERNáNDEZ,LUIS P SáNCHEZ-FERNáNDEZ,JESúS A CARRASCO-OCHOA,et al.Assessment and prediction of air quality using fuzzy logic and autoregressive models[J].Atmospheric Environment,2012,60:37-50.
[4] 丁卉,刘永红,曹生现.基于模糊-灰色聚类方法的城市空气质量评价研究[J].环境科学与技术,2013,36(S2):374-379.
[5] JINNA LU,HONGPING HU,YANPINGBAI,et al.Radial basis function neural network based on an improved exponential decreasing inertia weight-particle swarm optimization algorithm for AQI prediction[J].Abstract and Applied Analysis,2014,http://dx.doi.org/10.1155/2014/178313.
[6] 杨瑞君,赵楠,凡耀峰,等.基于随机森林模型的城市空气质量评价[J].计算机工程与设计,2017,38(11):3151-3156.
[7] 杭琦,杨敬辉,黄国荣.随机森林算法在空气质量评价中的应用[J].上海第二工业大学学报,2018,35(2):129-133.
[8] 陈峰.基于CART算法的空气质量指数回归预测模型的学习[J].上饶师范学院学报,2016,36(6):16-21.
[9] 江志农,魏东海,王磊,等.基于CART决策树的柴油机故障诊断方法研究[J].北京化工大学学报:自然科学版,2018,45(4):71-75.
[10] 李宏彬,赫光中,程莉莉,等.基于CART决策树的B超影像肝纤维化纹理识别研究[J].中国数字医学,2017,12(11):44-47.
[11] 杨光,马尔丽.决策树模型在2型糖尿病预测中的应用[J].沈阳师范大学学报:自然科学版,2018,36(3):233-236.
[12] UNKELS,FARRINGTON CP,GARTHWAITEP H,et al.Statistical methods for the prospective detection of infectious disease outbreaks:a review[J].Journal of the Royal Statistical Society:Series A(Statistics in Society),2012,175(1):49-82.
[13] 谭中明,谢坤,彭耀鹏.基于梯度提升决策树模型的P2P网贷借款人信用风险评测研究[J].软科学,2018(12):136-140.
[14] 李立,李红,李彦.基于改进C5.0的元胞自动机模型研究——以土地利用问题为例[J].科技和产业,2017,17(11):103-107.
[15] 徐婕,贺美美.基于马氏抽样的SVM非平衡数据分类算法的泛化性能研究[J].电子学报,2018,46(11):2660-2670.
[16] 谢涛,蒯圣宇,朱晓虎,等.基于改进遗传算法的配电网故障定位方法[J].沈阳工业大学学报,2019(2):126-131.
[17] LIU XIANG LAN.Digital construction of coal mine big data for different platforms based on life cycle[C]//IEEE Beijing Section、Xi’an Jiaotong-Liverpool University.Proceedings of 2017 IEEE 2nd International Conference on Big Data Analysis(ICBDA 2017).IEEE Beijing Section、Xi’an Jiaotong-Liverpool University:IEEE BEIJING SECTION,2017:4.
[18] QUINLANJR.Induction of decision trees[J].Machine Learning,1986,1(1):81-106.
[19] ROBERT T,JEROME F.统计学习基础——数据挖掘、推理与预测[M].范明,等,译.北京:电子工业出版社,2004.
[20] 张恒昕.基于决策树模型的多因子量化投资策略研究[D].沈阳:东北大学,2015.
[2] 江晓晴,鲁明浩,鲁园园,等.基于模糊数学的城市空气质量的分析与评价[J].环境与发展,2015,27(6):56-59.
[3] JOSé JUAN CARBAJAL-HERNáNDEZ,LUIS P SáNCHEZ-FERNáNDEZ,JESúS A CARRASCO-OCHOA,et al.Assessment and prediction of air quality using fuzzy logic and autoregressive models[J].Atmospheric Environment,2012,60:37-50.
[4] 丁卉,刘永红,曹生现.基于模糊-灰色聚类方法的城市空气质量评价研究[J].环境科学与技术,2013,36(S2):374-379.
[5] JINNA LU,HONGPING HU,YANPINGBAI,et al.Radial basis function neural network based on an improved exponential decreasing inertia weight-particle swarm optimization algorithm for AQI prediction[J].Abstract and Applied Analysis,2014,http://dx.doi.org/10.1155/2014/178313.
[6] 杨瑞君,赵楠,凡耀峰,等.基于随机森林模型的城市空气质量评价[J].计算机工程与设计,2017,38(11):3151-3156.
[7] 杭琦,杨敬辉,黄国荣.随机森林算法在空气质量评价中的应用[J].上海第二工业大学学报,2018,35(2):129-133.
[8] 陈峰.基于CART算法的空气质量指数回归预测模型的学习[J].上饶师范学院学报,2016,36(6):16-21.
[9] 江志农,魏东海,王磊,等.基于CART决策树的柴油机故障诊断方法研究[J].北京化工大学学报:自然科学版,2018,45(4):71-75.
[10] 李宏彬,赫光中,程莉莉,等.基于CART决策树的B超影像肝纤维化纹理识别研究[J].中国数字医学,2017,12(11):44-47.
[11] 杨光,马尔丽.决策树模型在2型糖尿病预测中的应用[J].沈阳师范大学学报:自然科学版,2018,36(3):233-236.
[12] UNKELS,FARRINGTON CP,GARTHWAITEP H,et al.Statistical methods for the prospective detection of infectious disease outbreaks:a review[J].Journal of the Royal Statistical Society:Series A(Statistics in Society),2012,175(1):49-82.
[13] 谭中明,谢坤,彭耀鹏.基于梯度提升决策树模型的P2P网贷借款人信用风险评测研究[J].软科学,2018(12):136-140.
[14] 李立,李红,李彦.基于改进C5.0的元胞自动机模型研究——以土地利用问题为例[J].科技和产业,2017,17(11):103-107.
[15] 徐婕,贺美美.基于马氏抽样的SVM非平衡数据分类算法的泛化性能研究[J].电子学报,2018,46(11):2660-2670.
[16] 谢涛,蒯圣宇,朱晓虎,等.基于改进遗传算法的配电网故障定位方法[J].沈阳工业大学学报,2019(2):126-131.
[17] LIU XIANG LAN.Digital construction of coal mine big data for different platforms based on life cycle[C]//IEEE Beijing Section、Xi’an Jiaotong-Liverpool University.Proceedings of 2017 IEEE 2nd International Conference on Big Data Analysis(ICBDA 2017).IEEE Beijing Section、Xi’an Jiaotong-Liverpool University:IEEE BEIJING SECTION,2017:4.
[18] QUINLANJR.Induction of decision trees[J].Machine Learning,1986,1(1):81-106.
[19] ROBERT T,JEROME F.统计学习基础——数据挖掘、推理与预测[M].范明,等,译.北京:电子工业出版社,2004.
[20] 张恒昕.基于决策树模型的多因子量化投资策略研究[D].沈阳:东北大学,2015.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |