Multi-Site Air Pollutant Prediction Using Long Short Term Memory  

作　　者：Chitra Paulpandi Murukesh Chinnasamy Shanker Nagalingam Rajendiran 

机构地区：[1]Anna University,Chennai,600066,Tamil Nadu,India

出　　处：《Computer Systems Science & Engineering》2022年第12期1341-1355,共15页计算机系统科学与工程（英文）

摘　　要：The current pandemic highlights the significance and impact of air pollution on individuals. When it comes to climate sustainability, air pollution is amajor challenge. Because of the distinctive nature, unpredictability, and greatchangeability in the reality of toxins and particulates, detecting air quality is apuzzling task. Simultaneously, the ability to predict or classify and monitor airquality is becoming increasingly important, particularly in urban areas, due tothe well documented negative impact of air pollution on resident’s health andthe environment. To better comprehend the current condition of air quality, thisresearch proposes predicting air pollution levels from real-time data. This studyproposes the use of deep learning techniques to forecast air pollution levels.Layers, activation functions, and a number of epochs were used to create the suggested Long Short-Term Memory (LSTM) network based neural layer design. Theuse of proposed Deep Learning as a structure for high-accuracy air quality prediction is investigated in this research and obtained better accuracy of nearly 82% compared to earlier records. Determining the Air Quality Index (AQI) and danger levelswould assist the government in finding appropriate ways to authorize approaches toreduce pollutants and keep inhabitants informed about the findings.

关 键 词：LSTM epochs deep learning air quality index PARTICULATES neural networks 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]