Deep Learning Model for Global Spatio-Temporal Image Prediction
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
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.
Кључне речи:
aerosol / climate change / deep learning model / spatio-temporal image predictionИзвор:
Mathematics, 2022, 10, 18, 3392-Финансирање / пројекти:
- Ministry of Education, Science and Technological Development of the Republic of Serbia [Grant No. 1002205]
Институција/група
VinčaTY - 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 . .