Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks
Air pollution is becoming a rising and serious environmental problem, especially in urban areas affected by an increasing migration rate. The large availability of sensor data enables the adoption of analytical tools to provide decision support capabilities. Employing sensors facilitates air polluti...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/24/4142 |
| _version_ | 1797544299978555392 |
|---|---|
| author | Jovan Kalajdjieski Eftim Zdravevski Roberto Corizzo Petre Lameski Slobodan Kalajdziski Ivan Miguel Pires Nuno M. Garcia Vladimir Trajkovik |
| author_facet | Jovan Kalajdjieski Eftim Zdravevski Roberto Corizzo Petre Lameski Slobodan Kalajdziski Ivan Miguel Pires Nuno M. Garcia Vladimir Trajkovik |
| author_sort | Jovan Kalajdjieski |
| collection | DOAJ |
| description | Air pollution is becoming a rising and serious environmental problem, especially in urban areas affected by an increasing migration rate. The large availability of sensor data enables the adoption of analytical tools to provide decision support capabilities. Employing sensors facilitates air pollution monitoring, but the lack of predictive capability limits such systems’ potential in practical scenarios. On the other hand, forecasting methods offer the opportunity to predict the future pollution in specific areas, potentially suggesting useful preventive measures. To date, many works tackled the problem of air pollution forecasting, most of which are based on sequence models. These models are trained with raw pollution data and are subsequently utilized to make predictions. This paper proposes a novel approach evaluating four different architectures that utilize camera images to estimate the air pollution in those areas. These images are further enhanced with weather data to boost the classification accuracy. The proposed approach exploits generative adversarial networks combined with data augmentation techniques to mitigate the class imbalance problem. The experiments show that the proposed method achieves robust accuracy of up to 0.88, which is comparable to sequence models and conventional models that utilize air pollution data. This is a remarkable result considering that the historic air pollution data is directly related to the output—future air pollution data, whereas the proposed architecture uses camera images to recognize the air pollution—which is an inherently much more difficult problem. |
| first_indexed | 2024-03-10T13:58:19Z |
| format | Article |
| id | doaj.art-96ecfd94614845fca70412d78121c2e3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T13:58:19Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-96ecfd94614845fca70412d78121c2e32023-11-21T01:25:16ZengMDPI AGRemote Sensing2072-42922020-12-011224414210.3390/rs12244142Air Pollution Prediction with Multi-Modal Data and Deep Neural NetworksJovan Kalajdjieski0Eftim Zdravevski1Roberto Corizzo2Petre Lameski3Slobodan Kalajdziski4Ivan Miguel Pires5Nuno M. Garcia6Vladimir Trajkovik7Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Rugjer Boshkovik 16, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Rugjer Boshkovik 16, 1000 Skopje, North MacedoniaDepartment of Computer Science, American University, Washington, DC 20016, USAFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Rugjer Boshkovik 16, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Rugjer Boshkovik 16, 1000 Skopje, North MacedoniaInstituto de Telecomunicações, Universidade da Beira Interior, 6201001 Covilhã, PortugalInstituto de Telecomunicações, Universidade da Beira Interior, 6201001 Covilhã, PortugalFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Rugjer Boshkovik 16, 1000 Skopje, North MacedoniaAir pollution is becoming a rising and serious environmental problem, especially in urban areas affected by an increasing migration rate. The large availability of sensor data enables the adoption of analytical tools to provide decision support capabilities. Employing sensors facilitates air pollution monitoring, but the lack of predictive capability limits such systems’ potential in practical scenarios. On the other hand, forecasting methods offer the opportunity to predict the future pollution in specific areas, potentially suggesting useful preventive measures. To date, many works tackled the problem of air pollution forecasting, most of which are based on sequence models. These models are trained with raw pollution data and are subsequently utilized to make predictions. This paper proposes a novel approach evaluating four different architectures that utilize camera images to estimate the air pollution in those areas. These images are further enhanced with weather data to boost the classification accuracy. The proposed approach exploits generative adversarial networks combined with data augmentation techniques to mitigate the class imbalance problem. The experiments show that the proposed method achieves robust accuracy of up to 0.88, which is comparable to sequence models and conventional models that utilize air pollution data. This is a remarkable result considering that the historic air pollution data is directly related to the output—future air pollution data, whereas the proposed architecture uses camera images to recognize the air pollution—which is an inherently much more difficult problem.https://www.mdpi.com/2072-4292/12/24/4142air pollution predictionsmart citydeep learningconvolutional neural networksgenerative adversarial networks |
| spellingShingle | Jovan Kalajdjieski Eftim Zdravevski Roberto Corizzo Petre Lameski Slobodan Kalajdziski Ivan Miguel Pires Nuno M. Garcia Vladimir Trajkovik Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks Remote Sensing air pollution prediction smart city deep learning convolutional neural networks generative adversarial networks |
| title | Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks |
| title_full | Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks |
| title_fullStr | Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks |
| title_full_unstemmed | Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks |
| title_short | Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks |
| title_sort | air pollution prediction with multi modal data and deep neural networks |
| topic | air pollution prediction smart city deep learning convolutional neural networks generative adversarial networks |
| url | https://www.mdpi.com/2072-4292/12/24/4142 |
| work_keys_str_mv | AT jovankalajdjieski airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT eftimzdravevski airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT robertocorizzo airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT petrelameski airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT slobodankalajdziski airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT ivanmiguelpires airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT nunomgarcia airpollutionpredictionwithmultimodaldataanddeepneuralnetworks AT vladimirtrajkovik airpollutionpredictionwithmultimodaldataanddeepneuralnetworks |