基于决策树算法的长沙市空气质量研究
Research on Air Quality in Changsha City Based on Decision Tree Algorithm
摘要: 本文针对长沙市空气质量问题，运用k近邻算法和决策树算法的理论方法，构建了空气质量预测模型。建立模型并进行求解，通过算法得到空气污染的主要影响因素并且从精准预测了长沙市的空气质量。最后，对模型进行了分析和评价。
Abstract:
Aiming at the air quality problem of Changsha City, this paper constructs the air quality prediction model by using the theoretical methods of the k-Nearest Neighbors (k-NN) and Decision Tree Al-gorithm. The model was established and solved, the main influencing factors of air pollution were obtained through the algorithm, and the air quality of Changsha City was accurately predicted. Fi-nally, the model is analyzed and evaluated.
参考文献
|
[1]
|
陈珊子. 灰色系统理论在环境空气质量变化趋势预测研究中的应用——以广东省潮州市区为例[J]. 环境, 2006(S2): 189-190
|
|
[2]
|
程承旗, 何华伟. 厦门市2001-2002年PM10浓度时间序列变化分析[J]. 水土保持研究, 2005, (6): 15-17.
|
|
[3]
|
刘萍. 基于主成分分析和多元线性回归模型的空气质量评价方法研究[D]: [硕士学位论文]. 昆明: 云南大学, 2015.
|
|
[4]
|
王克玲. 基于人工神经网络的城市空气质量评价与预测[D]: [硕士学位论文]. 乌鲁木齐: 新疆大学, 2021.
|
|
[5]
|
Navares, R. and Aznarte, J.L. (2020) Predicting Air Quality with Deep Learning LSTM: Towards Comprehensive Models. Ecological Informatics, 55, 101019. [Google Scholar] [CrossRef]
|
|
[6]
|
吕昊芝. k近邻算法在空气质量测定方面的应用——臭氧日判断[J]. 电子制作, 2019(04): 65-67.
|
|
[7]
|
Cover, T. and Hart, P. (1967) Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, 13, 21-27. [Google Scholar] [CrossRef]
|
|
[8]
|
孔宇, 王海起, 张浩然, 夏可. 基于集成学习算法的PM_(2.5)浓度值预测[J]. 环境保护科学, 2021, 47(4): 17-23.
|
|
[9]
|
任晨曦, 王黎明, 韩星程, 叶泽甫, 朱竹君. 基于联合神经网络的水声目标识别方法[J]. 舰船科学技术, 2022, 44(1): 136-141.
|
|
[10]
|
李航. 统计学习方法[M]. 北京: 清华大学出版社, 2019: 67-89.
|