Iacovos Ioannou, Prabagarane Nagaradjane, Ala Khalifeh, Vasos Vassiliou, Janardhan M, Kaavya S, Vibish Kashyap B, Andreas Pitsillides
{"title":"基于航空图像中的多种气体,精确的两阶段深度机器学习辅助空气质量估计","authors":"Iacovos Ioannou, Prabagarane Nagaradjane, Ala Khalifeh, Vasos Vassiliou, Janardhan M, Kaavya S, Vibish Kashyap B, Andreas Pitsillides","doi":"10.1007/s11869-025-01710-x","DOIUrl":null,"url":null,"abstract":"<div><p>Currently, industry-related environmental factors negatively affect human health. The Air Quality Index (AQI), a measurement of air pollution, is worsening and affecting our daily life. Increasing air pollution, concerns about climate change, evolving technologies, and environmental research estimate air quality as increasingly important. Air pollution management has become crucial, and environmental monitoring conditions and air quality in daily life are necessary. The latest research on AQI does not focus on aerial images or specific pollutants. Additionally, avoid tackling the issue of having a high level of some specific weather elements, such as temperature and humidity. In the proposed research, we tackle the issues mentioned above by splitting our investigation into two phases. Thus, in this paper, an image-based high-accuracy air quality monitoring system is realized in two stages. In the first stage of our examination, popular deep machine learning prediction algorithms, including Artificial Neural Networks (ANN), Convolution Neural Networks (CNN), CNN-Long Short Term Memory (CNN-LSTM), and MobileNetv2 networks, for the assignment into different categories of the AQI, targeting the AQI prediction with the utilization of aerial images. Next, the second stage utilizes ANN, Recurrent Neural Networks (RNNs), LSTM, and RNN-B-LSTM popular deep machine learning techniques to develop a regression prediction system trained with the features and the resulting classification of air quality results from the highest accuracy approach of the first stage (which is the ANN approach with 99.14% accuracy). To tackle the issue of overfitting/underfitting, the oversampling technique (SMOTE) is used. The proposed method considers the contribution of each significant pollutant gas (i.e., PM2.5, PM10, NOx, NH<sub>3</sub>, SO<sub>2</sub>, O<sub>3</sub>) to the overall air quality index (AQI). The weather elements such as temperature and humidity impact air quality; they are also considered in our examination, resulting in a more accurate forecast. In addition, a comparison study is performed to identify the best model architecture for the proposed prediction system. Finally, the results show that the first stage of image classification should be executed with ANN (99.14 % accuracy), which is a highly accurate approach, and the second stage should be executed with the RNN-B-LSTM approach, again because of its high accuracy (98.73 % accuracy).</p></div>","PeriodicalId":49109,"journal":{"name":"Air Quality Atmosphere and Health","volume":"18 5","pages":"1545 - 1568"},"PeriodicalIF":2.9000,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An accurate two-stage deep machine learning aided air quality estimation based on multiple gases from aerial images\",\"authors\":\"Iacovos Ioannou, Prabagarane Nagaradjane, Ala Khalifeh, Vasos Vassiliou, Janardhan M, Kaavya S, Vibish Kashyap B, Andreas Pitsillides\",\"doi\":\"10.1007/s11869-025-01710-x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Currently, industry-related environmental factors negatively affect human health. The Air Quality Index (AQI), a measurement of air pollution, is worsening and affecting our daily life. Increasing air pollution, concerns about climate change, evolving technologies, and environmental research estimate air quality as increasingly important. Air pollution management has become crucial, and environmental monitoring conditions and air quality in daily life are necessary. The latest research on AQI does not focus on aerial images or specific pollutants. Additionally, avoid tackling the issue of having a high level of some specific weather elements, such as temperature and humidity. In the proposed research, we tackle the issues mentioned above by splitting our investigation into two phases. Thus, in this paper, an image-based high-accuracy air quality monitoring system is realized in two stages. In the first stage of our examination, popular deep machine learning prediction algorithms, including Artificial Neural Networks (ANN), Convolution Neural Networks (CNN), CNN-Long Short Term Memory (CNN-LSTM), and MobileNetv2 networks, for the assignment into different categories of the AQI, targeting the AQI prediction with the utilization of aerial images. Next, the second stage utilizes ANN, Recurrent Neural Networks (RNNs), LSTM, and RNN-B-LSTM popular deep machine learning techniques to develop a regression prediction system trained with the features and the resulting classification of air quality results from the highest accuracy approach of the first stage (which is the ANN approach with 99.14% accuracy). To tackle the issue of overfitting/underfitting, the oversampling technique (SMOTE) is used. The proposed method considers the contribution of each significant pollutant gas (i.e., PM2.5, PM10, NOx, NH<sub>3</sub>, SO<sub>2</sub>, O<sub>3</sub>) to the overall air quality index (AQI). The weather elements such as temperature and humidity impact air quality; they are also considered in our examination, resulting in a more accurate forecast. In addition, a comparison study is performed to identify the best model architecture for the proposed prediction system. Finally, the results show that the first stage of image classification should be executed with ANN (99.14 % accuracy), which is a highly accurate approach, and the second stage should be executed with the RNN-B-LSTM approach, again because of its high accuracy (98.73 % accuracy).</p></div>\",\"PeriodicalId\":49109,\"journal\":{\"name\":\"Air Quality Atmosphere and Health\",\"volume\":\"18 5\",\"pages\":\"1545 - 1568\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2025-03-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Air Quality Atmosphere and Health\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s11869-025-01710-x\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Air Quality Atmosphere and Health","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s11869-025-01710-x","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
An accurate two-stage deep machine learning aided air quality estimation based on multiple gases from aerial images
Currently, industry-related environmental factors negatively affect human health. The Air Quality Index (AQI), a measurement of air pollution, is worsening and affecting our daily life. Increasing air pollution, concerns about climate change, evolving technologies, and environmental research estimate air quality as increasingly important. Air pollution management has become crucial, and environmental monitoring conditions and air quality in daily life are necessary. The latest research on AQI does not focus on aerial images or specific pollutants. Additionally, avoid tackling the issue of having a high level of some specific weather elements, such as temperature and humidity. In the proposed research, we tackle the issues mentioned above by splitting our investigation into two phases. Thus, in this paper, an image-based high-accuracy air quality monitoring system is realized in two stages. In the first stage of our examination, popular deep machine learning prediction algorithms, including Artificial Neural Networks (ANN), Convolution Neural Networks (CNN), CNN-Long Short Term Memory (CNN-LSTM), and MobileNetv2 networks, for the assignment into different categories of the AQI, targeting the AQI prediction with the utilization of aerial images. Next, the second stage utilizes ANN, Recurrent Neural Networks (RNNs), LSTM, and RNN-B-LSTM popular deep machine learning techniques to develop a regression prediction system trained with the features and the resulting classification of air quality results from the highest accuracy approach of the first stage (which is the ANN approach with 99.14% accuracy). To tackle the issue of overfitting/underfitting, the oversampling technique (SMOTE) is used. The proposed method considers the contribution of each significant pollutant gas (i.e., PM2.5, PM10, NOx, NH3, SO2, O3) to the overall air quality index (AQI). The weather elements such as temperature and humidity impact air quality; they are also considered in our examination, resulting in a more accurate forecast. In addition, a comparison study is performed to identify the best model architecture for the proposed prediction system. Finally, the results show that the first stage of image classification should be executed with ANN (99.14 % accuracy), which is a highly accurate approach, and the second stage should be executed with the RNN-B-LSTM approach, again because of its high accuracy (98.73 % accuracy).
期刊介绍:
Air Quality, Atmosphere, and Health is a multidisciplinary journal which, by its very name, illustrates the broad range of work it publishes and which focuses on atmospheric consequences of human activities and their implications for human and ecological health.
It offers research papers, critical literature reviews and commentaries, as well as special issues devoted to topical subjects or themes.
International in scope, the journal presents papers that inform and stimulate a global readership, as the topic addressed are global in their import. Consequently, we do not encourage submission of papers involving local data that relate to local problems. Unless they demonstrate wide applicability, these are better submitted to national or regional journals.
Air Quality, Atmosphere & Health addresses such topics as acid precipitation; airborne particulate matter; air quality monitoring and management; exposure assessment; risk assessment; indoor air quality; atmospheric chemistry; atmospheric modeling and prediction; air pollution climatology; climate change and air quality; air pollution measurement; atmospheric impact assessment; forest-fire emissions; atmospheric science; greenhouse gases; health and ecological effects; clean air technology; regional and global change and satellite measurements.
This journal benefits a diverse audience of researchers, public health officials and policy makers addressing problems that call for solutions based in evidence from atmospheric and exposure assessment scientists, epidemiologists, and risk assessors. Publication in the journal affords the opportunity to reach beyond defined disciplinary niches to this broader readership.