Correction of CAMS PM<sub>10</sub> Reanalysis Improves AI-Based Dust Event Forecast
High dust loading significantly impacts air quality, climate, and public health. Early warning is crucial for mitigating short-term effects, and accurate dust field estimates are needed for forecasting. The Copernicus Atmosphere Monitoring Service (CAMS) offers global reanalysis datasets and forecas...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/222 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | High dust loading significantly impacts air quality, climate, and public health. Early warning is crucial for mitigating short-term effects, and accurate dust field estimates are needed for forecasting. The Copernicus Atmosphere Monitoring Service (CAMS) offers global reanalysis datasets and forecasts of particulate matter with a diameter of under 10 μm (PM<sub>10</sub>), which approximate dust, but recent studies highlight discrepancies between CAMS data and ground <i>in-situ</i> measurements. Since CAMS is often used for forecasting, errors in PM<sub>10</sub> fields can hinder accurate dust event forecasts, which is particularly challenging for models that use <i>artificial intelligence</i> (AI) due to the scarcity of dust events and limited training data. This study proposes a machine-learning approach to correct CAMS PM<sub>10</sub> fields using <i>in-situ</i> data to enhance AI-based dust event forecasting. A correction model that links pixel-wise errors with atmospheric and meteorological variables was taught using gradient-boosting algorithms. This model is then utilized to predict CAMS error in previously unobserved pixels across the Eastern Mediterranean, generating CAMS error fields. Our bias-corrected PM<sub>10</sub> fields are, on average, 12 μg m<sup>−3</sup> more accurate, often reducing CAMS errors by significant percentages. To evaluate the contribution, we train a deep neural network to predict city-scale dust events (0–72 h) over the Balkans using PM<sub>10</sub> fields. Comparing the network’s performance when trained on both original and bias-corrected CAMS PM<sub>10</sub> fields, we show that the correction improves AI-based forecasting performance across all metrics. |
|---|---|
| ISSN: | 2072-4292 |