TY  - JOUR
AU  - Nikezić, Dušan P.
AU  - Ramadani, Uzahir
AU  - Radivojević, Dušan
AU  - Lazović, Ivan
AU  - Mirkov, Nikola S.
PY  - 2022
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/10446
AB  - Mathematical methods are the basis of most models that describe the natural phenomena around us. However, the well-known conventional mathematical models for atmospheric modeling have some limitations. Machine learning with Big Data is also based on mathematics but offers a new approach for modeling. There are two methodologies to develop deep learning models for spatio-temporal image prediction. On these bases, two models were built—ConvLSTM and CNN-LSTM—with two types of predictions, i.e., sequence-to-sequence and sequence-to-one, in order to forecast Aerosol Optical Thickness sequences. The input dataset for training was NASA satellite imagery MODAL2_E_AER_OD from Terra/MODIS satellites, which presents global Aerosol Optical Thickness with an 8 day temporal resolution from 2000 to the present. The obtained results show that the ConvLSTM sequence-to-one model had the lowest RMSE error and the highest Cosine Similarity value. The advantages of the developed DL models are that they can be executed in milliseconds on a PC, can be used for global-scale Earth observations, and can serve as tracers to study how the Earth’s atmosphere moves. The developed models can be used as transfer learning for similar image time-series forecasting models.
T2  - Mathematics
T1  - Deep Learning Model for Global Spatio-Temporal Image Prediction
VL  - 10
IS  - 18
SP  - 3392
DO  - 10.3390/math10183392
ER  - 

@article{
author = "Nikezić, Dušan P. and Ramadani, Uzahir and Radivojević, Dušan and Lazović, Ivan and Mirkov, Nikola S.",
year = "2022",
abstract = "Mathematical methods are the basis of most models that describe the natural phenomena around us. However, the well-known conventional mathematical models for atmospheric modeling have some limitations. Machine learning with Big Data is also based on mathematics but offers a new approach for modeling. There are two methodologies to develop deep learning models for spatio-temporal image prediction. On these bases, two models were built—ConvLSTM and CNN-LSTM—with two types of predictions, i.e., sequence-to-sequence and sequence-to-one, in order to forecast Aerosol Optical Thickness sequences. The input dataset for training was NASA satellite imagery MODAL2_E_AER_OD from Terra/MODIS satellites, which presents global Aerosol Optical Thickness with an 8 day temporal resolution from 2000 to the present. The obtained results show that the ConvLSTM sequence-to-one model had the lowest RMSE error and the highest Cosine Similarity value. The advantages of the developed DL models are that they can be executed in milliseconds on a PC, can be used for global-scale Earth observations, and can serve as tracers to study how the Earth’s atmosphere moves. The developed models can be used as transfer learning for similar image time-series forecasting models.",
journal = "Mathematics",
title = "Deep Learning Model for Global Spatio-Temporal Image Prediction",
volume = "10",
number = "18",
pages = "3392",
doi = "10.3390/math10183392"
}

Nikezić, D. P., Ramadani, U., Radivojević, D., Lazović, I.,& Mirkov, N. S.. (2022). Deep Learning Model for Global Spatio-Temporal Image Prediction. in Mathematics, 10(18), 3392.
https://doi.org/10.3390/math10183392

Nikezić DP, Ramadani U, Radivojević D, Lazović I, Mirkov NS. Deep Learning Model for Global Spatio-Temporal Image Prediction. in Mathematics. 2022;10(18):3392.
doi:10.3390/math10183392 .

Nikezić, Dušan P., Ramadani, Uzahir, Radivojević, Dušan, Lazović, Ivan, Mirkov, Nikola S., "Deep Learning Model for Global Spatio-Temporal Image Prediction" in Mathematics, 10, no. 18 (2022):3392,
https://doi.org/10.3390/math10183392 . .