Satellite remote sensing and deep learning for aerosols prediction
Introduction/purpose: The paper presents a new state-of-the-art method that involves NASA satellite imagery with the latest deep learning model for a spatiotemporal sequence forecasting problem. Satellite-retrieved aerosol information is very useful in many fields such as PM prediction or COVID-...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Defence in Belgrade
2023-01-01
|
| Series: | Vojnotehnički Glasnik |
| Subjects: | |
| Online Access: | https://scindeks.ceon.rs/article.aspx?artid=0042-84692301066M |
| _version_ | 1811171892593164288 |
|---|---|
| author | Nikola S. Mirkov Dušan S. Radivojević Ivan M. Lazović Uzahir R. Ramadani Dušan P. Nikezić |
| author_facet | Nikola S. Mirkov Dušan S. Radivojević Ivan M. Lazović Uzahir R. Ramadani Dušan P. Nikezić |
| author_sort | Nikola S. Mirkov |
| collection | DOAJ |
| description | Introduction/purpose: The paper presents a new state-of-the-art method
that involves NASA satellite imagery with the latest deep learning model
for a spatiotemporal sequence forecasting problem. Satellite-retrieved
aerosol information is very useful in many fields such as PM prediction or
COVID-19 transmission. The input data set was MODAL2_E_AER_OD
which presents global AOT for every 8 days from Terra/MODIS. The implemented machine learning algorithm was built with ConvLSTM2D layers in Keras. The obtained results were compared with the new CNN
LSTM model.
Methods: Computational methods of Machine Learning, Artificial Neural
Networks, Deep Learning.
Results: The results show global AOT prediction obtained using satellite
digital imagery as an input.
Conclusion: The results show that the ConvLSTM developed model
could be used for global AOT prediction, as well as for PM and COVID-19
transmission.
|
| first_indexed | 2024-04-10T17:21:45Z |
| format | Article |
| id | doaj.art-8f93b03bd288458393038b868a407009 |
| institution | Directory Open Access Journal |
| issn | 0042-8469 2217-4753 |
| language | English |
| last_indexed | 2024-04-10T17:21:45Z |
| publishDate | 2023-01-01 |
| publisher | University of Defence in Belgrade |
| record_format | Article |
| series | Vojnotehnički Glasnik |
| spelling | doaj.art-8f93b03bd288458393038b868a4070092023-02-05T11:11:48ZengUniversity of Defence in BelgradeVojnotehnički Glasnik0042-84692217-47532023-01-01711668310.5937/vojtehg71-40391Satellite remote sensing and deep learning for aerosols predictionNikola S. Mirkov0https://orcid.org/0000-0002-3057-9784Dušan S. Radivojević1https://orcid.org/0000-0003-1959-3152Ivan M. Lazović2https://orcid.org/0000-0002-3877-5157Uzahir R. Ramadani3https://orcid.org/0000-0002-3702-0094Dušan P. Nikezić4https://orcid.org/0000-0002-8885-2683University of Belgrade, “Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of SerbiaUniversity of Belgrade, “Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of SerbiaUniversity of Belgrade, “Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of SerbiaUniversity of Belgrade, “Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of SerbiaUniversity of Belgrade, “Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of SerbiaIntroduction/purpose: The paper presents a new state-of-the-art method that involves NASA satellite imagery with the latest deep learning model for a spatiotemporal sequence forecasting problem. Satellite-retrieved aerosol information is very useful in many fields such as PM prediction or COVID-19 transmission. The input data set was MODAL2_E_AER_OD which presents global AOT for every 8 days from Terra/MODIS. The implemented machine learning algorithm was built with ConvLSTM2D layers in Keras. The obtained results were compared with the new CNN LSTM model. Methods: Computational methods of Machine Learning, Artificial Neural Networks, Deep Learning. Results: The results show global AOT prediction obtained using satellite digital imagery as an input. Conclusion: The results show that the ConvLSTM developed model could be used for global AOT prediction, as well as for PM and COVID-19 transmission. https://scindeks.ceon.rs/article.aspx?artid=0042-84692301066Maerosol optical thicknessnasa earth observationsconvlstm2dcovid-19particulate matter dispersion |
| spellingShingle | Nikola S. Mirkov Dušan S. Radivojević Ivan M. Lazović Uzahir R. Ramadani Dušan P. Nikezić Satellite remote sensing and deep learning for aerosols prediction Vojnotehnički Glasnik aerosol optical thickness nasa earth observations convlstm2d covid-19 particulate matter dispersion |
| title | Satellite remote sensing and deep learning for aerosols prediction |
| title_full | Satellite remote sensing and deep learning for aerosols prediction |
| title_fullStr | Satellite remote sensing and deep learning for aerosols prediction |
| title_full_unstemmed | Satellite remote sensing and deep learning for aerosols prediction |
| title_short | Satellite remote sensing and deep learning for aerosols prediction |
| title_sort | satellite remote sensing and deep learning for aerosols prediction |
| topic | aerosol optical thickness nasa earth observations convlstm2d covid-19 particulate matter dispersion |
| url | https://scindeks.ceon.rs/article.aspx?artid=0042-84692301066M |
| work_keys_str_mv | AT nikolasmirkov satelliteremotesensinganddeeplearningforaerosolsprediction AT dusansradivojevic satelliteremotesensinganddeeplearningforaerosolsprediction AT ivanmlazovic satelliteremotesensinganddeeplearningforaerosolsprediction AT uzahirrramadani satelliteremotesensinganddeeplearningforaerosolsprediction AT dusanpnikezic satelliteremotesensinganddeeplearningforaerosolsprediction |