Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation
Particulate matter smaller than 2.5 microns (PM2.5) is one of the main pollutants that has considerable detrimental effects on human health. Estimating its concentration levels with ground monitors is inefficient for several reasons. In this study, we build a digital twin (DT) of an atmospheric envi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10015739/ |
| _version_ | 1828014637832994816 |
|---|---|
| author | Kudaibergen Abutalip Anas Al-Lahham Abdulmotaleb El Saddik |
| author_facet | Kudaibergen Abutalip Anas Al-Lahham Abdulmotaleb El Saddik |
| author_sort | Kudaibergen Abutalip |
| collection | DOAJ |
| description | Particulate matter smaller than 2.5 microns (PM2.5) is one of the main pollutants that has considerable detrimental effects on human health. Estimating its concentration levels with ground monitors is inefficient for several reasons. In this study, we build a digital twin (DT) of an atmospheric environment by fusing remote sensing and observational data. An integral part of the DT pipeline is the presence of feedback that can influence future input data. Estimated values of PM2.5 obtained from an ensemble of Random Forest and Gradient Boosting are used to provide recommendations for decreasing the agglomeration levels. We formulate a simple optimization problem for suggesting the recommendations and identify possible action policies, such as cloud seeding, scheduling of air filtering, and SMS notifications. The PM2.5 estimation part of the proposed DT pipeline has achieved RMSE and R2 of 38.94 and 0.728 (95%, CI 0.717-0.740). In addition, we investigate different approaches for quantitatively examining the contribution of each independent variable. |
| first_indexed | 2024-04-10T10:05:26Z |
| format | Article |
| id | doaj.art-315c7559444c45678c524aaacb119a1d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T10:05:26Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-315c7559444c45678c524aaacb119a1d2023-02-16T00:00:16ZengIEEEIEEE Access2169-35362023-01-0111144481445710.1109/ACCESS.2023.323641410015739Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies RecommendationKudaibergen Abutalip0https://orcid.org/0000-0002-5706-1950Anas Al-Lahham1https://orcid.org/0000-0001-8413-6957Abdulmotaleb El Saddik2https://orcid.org/0000-0002-7690-8547Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab EmiratesDepartment of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab EmiratesDepartment of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab EmiratesParticulate matter smaller than 2.5 microns (PM2.5) is one of the main pollutants that has considerable detrimental effects on human health. Estimating its concentration levels with ground monitors is inefficient for several reasons. In this study, we build a digital twin (DT) of an atmospheric environment by fusing remote sensing and observational data. An integral part of the DT pipeline is the presence of feedback that can influence future input data. Estimated values of PM2.5 obtained from an ensemble of Random Forest and Gradient Boosting are used to provide recommendations for decreasing the agglomeration levels. We formulate a simple optimization problem for suggesting the recommendations and identify possible action policies, such as cloud seeding, scheduling of air filtering, and SMS notifications. The PM2.5 estimation part of the proposed DT pipeline has achieved RMSE and R2 of 38.94 and 0.728 (95%, CI 0.717-0.740). In addition, we investigate different approaches for quantitatively examining the contribution of each independent variable.https://ieeexplore.ieee.org/document/10015739/PM2.5digital twinssatellite datahealth riskair pollution |
| spellingShingle | Kudaibergen Abutalip Anas Al-Lahham Abdulmotaleb El Saddik Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation IEEE Access PM2.5 digital twins satellite data health risk air pollution |
| title | Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation |
| title_full | Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation |
| title_fullStr | Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation |
| title_full_unstemmed | Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation |
| title_short | Digital Twin of Atmospheric Environment: Sensory Data Fusion for High-Resolution PM<sub>2.5</sub> Estimation and Action Policies Recommendation |
| title_sort | digital twin of atmospheric environment sensory data fusion for high resolution pm sub 2 5 sub estimation and action policies recommendation |
| topic | PM2.5 digital twins satellite data health risk air pollution |
| url | https://ieeexplore.ieee.org/document/10015739/ |
| work_keys_str_mv | AT kudaibergenabutalip digitaltwinofatmosphericenvironmentsensorydatafusionforhighresolutionpmsub25subestimationandactionpoliciesrecommendation AT anasallahham digitaltwinofatmosphericenvironmentsensorydatafusionforhighresolutionpmsub25subestimationandactionpoliciesrecommendation AT abdulmotalebelsaddik digitaltwinofatmosphericenvironmentsensorydatafusionforhighresolutionpmsub25subestimationandactionpoliciesrecommendation |