An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies
Extreme weather patterns can affect ground and satellite sensors before and after their occur. This study focused on tornadoes that occurred on December 10 and 11, 2021 in the state of Kentucky. The main goal of this research was to develop a deep learning algorithm based on history to predict this...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Results in Earth Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S221171482400027X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850250599272022016 |
|---|---|
| author | Omid Memarian Sorkhabi |
| author_facet | Omid Memarian Sorkhabi |
| author_sort | Omid Memarian Sorkhabi |
| collection | DOAJ |
| description | Extreme weather patterns can affect ground and satellite sensors before and after their occur. This study focused on tornadoes that occurred on December 10 and 11, 2021 in the state of Kentucky. The main goal of this research was to develop a deep learning algorithm based on history to predict this phenomenon. Four scenarios were created based on temperature, air pressure, wind speed and their combination. The temperature-based scenario shows high accuracy and shows the time series of temperature rise several degrees before the tornado. In the second step, the normalized difference vegetation index (NDVI) anomaly was calculated and classified for Mayfield city. Severe NDVI anomalies showed high consistency with enhanced Fujita scale and ultra-high-resolution satellite imagery, with a correlation greater than 0.9. |
| format | Article |
| id | doaj-art-6d46ffbdeeb44013b3ea414b20238a2b |
| institution | OA Journals |
| issn | 2211-7148 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Earth Sciences |
| spelling | doaj-art-6d46ffbdeeb44013b3ea414b20238a2b2025-08-20T01:58:08ZengElsevierResults in Earth Sciences2211-71482024-12-01210004010.1016/j.rines.2024.100040An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomaliesOmid Memarian Sorkhabi0CeADAR - Ireland’s Centre for Applied AI, University College Dublin, IrelandExtreme weather patterns can affect ground and satellite sensors before and after their occur. This study focused on tornadoes that occurred on December 10 and 11, 2021 in the state of Kentucky. The main goal of this research was to develop a deep learning algorithm based on history to predict this phenomenon. Four scenarios were created based on temperature, air pressure, wind speed and their combination. The temperature-based scenario shows high accuracy and shows the time series of temperature rise several degrees before the tornado. In the second step, the normalized difference vegetation index (NDVI) anomaly was calculated and classified for Mayfield city. Severe NDVI anomalies showed high consistency with enhanced Fujita scale and ultra-high-resolution satellite imagery, with a correlation greater than 0.9.http://www.sciencedirect.com/science/article/pii/S221171482400027XDeep learningNDVI anomalyExtreme weatherKentucky tornado |
| spellingShingle | Omid Memarian Sorkhabi An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies Results in Earth Sciences Deep learning NDVI anomaly Extreme weather Kentucky tornado |
| title | An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies |
| title_full | An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies |
| title_fullStr | An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies |
| title_full_unstemmed | An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies |
| title_short | An LSTM deep learning framework for history-based tornado prediction using meteorological data and damage assessment using NDVI anomalies |
| title_sort | lstm deep learning framework for history based tornado prediction using meteorological data and damage assessment using ndvi anomalies |
| topic | Deep learning NDVI anomaly Extreme weather Kentucky tornado |
| url | http://www.sciencedirect.com/science/article/pii/S221171482400027X |
| work_keys_str_mv | AT omidmemariansorkhabi anlstmdeeplearningframeworkforhistorybasedtornadopredictionusingmeteorologicaldataanddamageassessmentusingndvianomalies AT omidmemariansorkhabi lstmdeeplearningframeworkforhistorybasedtornadopredictionusingmeteorologicaldataanddamageassessmentusingndvianomalies |