Characterization of Historical Aerosol Optical Depth Dynamics Using LSTM and Peak Enhancement Techniques
This study addresses the challenges of characterizing aerosol optical depth (AOD) dynamics from satellite observations, which are often hindered by data gaps and variability. A long short-term memory (LSTM) network was trained on an extended AOD dataset from Sicily to capture temporal patterns. The...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/6/743 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study addresses the challenges of characterizing aerosol optical depth (AOD) dynamics from satellite observations, which are often hindered by data gaps and variability. A long short-term memory (LSTM) network was trained on an extended AOD dataset from Sicily to capture temporal patterns. The trained model was then applied to AOD data from distinct geographical regions: Cluj-Napoca and the central Mediterranean Sea. While the LSTM effectively captured general seasonal trends, it tended to smooth extreme AOD events. To mitigate this, a post-processing algorithm was developed to enhance the representation of AOD peaks and valleys. This enhancement method refines the characterization of historical AOD, providing a more accurate representation of observed atmospheric variability, particularly in capturing high and low AOD episodes. The results demonstrate the efficacy of the hybrid approach in improving the characterization of AOD dynamics across different regions. |
|---|---|
| ISSN: | 2073-4433 |