An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection
This study presents AD-MRCNN, an advanced deep learning framework for automated atmospheric front detection that addresses two critical limitations in existing methods. First, current approaches directly input raw meteorological data without optimizing feature compatibility, potentially hindering mo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714477785677824 |
|---|---|
| author | Xinya Ding Xuan Peng Yanguang Xue Liang Zhang Tianying Wang Yunpeng Zhang |
| author_facet | Xinya Ding Xuan Peng Yanguang Xue Liang Zhang Tianying Wang Yunpeng Zhang |
| author_sort | Xinya Ding |
| collection | DOAJ |
| description | This study presents AD-MRCNN, an advanced deep learning framework for automated atmospheric front detection that addresses two critical limitations in existing methods. First, current approaches directly input raw meteorological data without optimizing feature compatibility, potentially hindering model performance. Second, they typically only provide frontal category information without identifying individual frontal systems. Our solution integrates two key innovations: 1. An intelligent adapter module that performs adaptive feature fusion, automatically weighting and combining multi-source meteorological inputs (including temperature, wind fields, and humidity data) to maximize their synergistic effects while minimizing feature conflicts; the utilized network achieves an average improvement of over 4% across various metrics. 2. An enhanced instance segmentation network based on Mask R-CNN architecture that simultaneously achieves (1) precise frontal type classification (cold/warm/stationary/occluded), (2) accurate spatial localization, and (3) identification of distinct frontal systems. Comprehensive evaluation using ERA5 reanalysis data (2009–2018) demonstrates significant improvements, including an 85.1% F1-score, outperforming traditional methods (TFP: 63.1%) and deep learning approaches (Unet: 83.3%), and a 31% reduction in false alarms compared to semantic segmentation methods. The framework’s modular design allows for potential application to other meteorological feature detection tasks. Future work will focus on incorporating temporal dynamics for frontal evolution prediction. |
| format | Article |
| id | doaj-art-21a256eb864b488caae950fe9aaab933 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-21a256eb864b488caae950fe9aaab9332025-08-20T03:13:42ZengMDPI AGApplied Sciences2076-34172025-07-011514785510.3390/app15147855An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front DetectionXinya Ding0Xuan Peng1Yanguang Xue2Liang Zhang3Tianying Wang4Yunpeng Zhang5Key Laboratory of Smart Earth, Beijing 100029, ChinaKey Laboratory of Smart Earth, Beijing 100029, ChinaKey Laboratory of Smart Earth, Beijing 100029, ChinaThe College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410005, ChinaInstitute of Meteorological Sciences of Hunan Province, Changsha 410118, ChinaThe College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410005, ChinaThis study presents AD-MRCNN, an advanced deep learning framework for automated atmospheric front detection that addresses two critical limitations in existing methods. First, current approaches directly input raw meteorological data without optimizing feature compatibility, potentially hindering model performance. Second, they typically only provide frontal category information without identifying individual frontal systems. Our solution integrates two key innovations: 1. An intelligent adapter module that performs adaptive feature fusion, automatically weighting and combining multi-source meteorological inputs (including temperature, wind fields, and humidity data) to maximize their synergistic effects while minimizing feature conflicts; the utilized network achieves an average improvement of over 4% across various metrics. 2. An enhanced instance segmentation network based on Mask R-CNN architecture that simultaneously achieves (1) precise frontal type classification (cold/warm/stationary/occluded), (2) accurate spatial localization, and (3) identification of distinct frontal systems. Comprehensive evaluation using ERA5 reanalysis data (2009–2018) demonstrates significant improvements, including an 85.1% F1-score, outperforming traditional methods (TFP: 63.1%) and deep learning approaches (Unet: 83.3%), and a 31% reduction in false alarms compared to semantic segmentation methods. The framework’s modular design allows for potential application to other meteorological feature detection tasks. Future work will focus on incorporating temporal dynamics for frontal evolution prediction.https://www.mdpi.com/2076-3417/15/14/7855atmospheric frontautomatic identificationadaptersegmentation networkAD-MRCNN model |
| spellingShingle | Xinya Ding Xuan Peng Yanguang Xue Liang Zhang Tianying Wang Yunpeng Zhang An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection Applied Sciences atmospheric front automatic identification adapter segmentation network AD-MRCNN model |
| title | An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection |
| title_full | An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection |
| title_fullStr | An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection |
| title_full_unstemmed | An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection |
| title_short | An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection |
| title_sort | adapter and segmentation network based approach for automated atmospheric front detection |
| topic | atmospheric front automatic identification adapter segmentation network AD-MRCNN model |
| url | https://www.mdpi.com/2076-3417/15/14/7855 |
| work_keys_str_mv | AT xinyading anadapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT xuanpeng anadapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT yanguangxue anadapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT liangzhang anadapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT tianyingwang anadapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT yunpengzhang anadapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT xinyading adapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT xuanpeng adapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT yanguangxue adapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT liangzhang adapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT tianyingwang adapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection AT yunpengzhang adapterandsegmentationnetworkbasedapproachforautomatedatmosphericfrontdetection |