journal article·2025-07-14Open access

An Adapter and Segmentation Network-Based Approach for Automated Atmospheric Front Detection

Xinya Ding, Xuan Peng, Yanguang Xue, Liang Zhang, Tianying Wang, Yunpeng Zhang

Applied Sciences· Volume 15· Issue 14

Abstract

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.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Meteorological Phenomena and Simulations · Wind and Air Flow Studies · Air Quality Monitoring and Forecasting

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Key Laboratory of Smart Earth, Beijing 100029, China

The College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410005, China

High Impact Weather Key Laboratory of CMA, Changsha 410005, China

Sichuan Meteorological Disaster Defense Technology Center, Chengdu 610072, China

Heavy Rain and Drought-Flood Disaster in Plateau and Basin Key Laboratory of Sichuan Province, Chengdu 610072, China

Institute of Meteorological Sciences of Hunan Province, Changsha 410118, China

Funding

National Natural Science Foundation of China · Open Fund of Key Laboratory of Smart Earth · China Postdoctoral Science Foundation · Hunan Province Natural Science Foundation · Fengyun Application Pioneering Project · Key Laboratory of Heavy Rain and Drought Flood

References (33)

Show source-provided references
1. A study of synoptic-scale tornado regimes
2. The importance of fronts for extreme precipitation10.1002/jgrd.50852 ↗
3. Experiments in numerical objective frontal analysis10.1175/1520-0493(1965)093<0547:EINOFA>2.3.CO;2 ↗
4. Dowdy, A., and Catto, J. (2017). Extreme weather caused by concurrent cyclone, front and thunderstorm occurrences. Sci. Rep., 7.10.1038/srep40359 ↗
5. The U.S. Navy numerical frontal analysis scheme: Further development and a limited evaluation10.1175/1520-0450(1966)005<0764:TUSNNF>2.0.CO;2 ↗
6. Objective identification, typing and tracking of the complete life-cycles of cyclonic features at high spatial resolution10.1002/met.204 ↗
7. Identification and climatology of Southern Hemisphere mobile fronts in a modern reanalysis10.1175/JCLI-D-11-00100.1 ↗
8. Contribution to the theory of frontogenesis
9. A simple diagnostic for the detection of atmospheric fronts10.1002/2017GL073662 ↗
10. What are the best thermodynamic quantity and function to define a front in gridded model output?10.1175/BAMS-D-18-0137.1 ↗
11. Climatology and variability of warm and cold fronts over North America from 1979 to 201810.1175/JCLI-D-19-0680.1 ↗
12. Extratropical fronts in the lower troposphere—Global perspectives obtained from two automated methods10.1002/qj.2471 ↗
13. Laura, M., Annette, R., and Peter, N. (2022). Identifying atmospheric fronts based on diabatic processes using the dynamic state index (DSI). arXiv.
14. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position10.1007/BF00344251 ↗
15. Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position10.1016/0031-3203(82)90024-3 ↗
16. Automated detection and classification of synoptic-scale fronts from atmospheric data grids10.5194/wcd-3-113-2022 ↗
17. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer International Publishing.10.1007/978-3-319-24574-4_28 ↗
18. Making the black box more transparent: Understanding the physical implications of machine learning10.1175/BAMS-D-18-0195.1 ↗
19. Automated detection of weather fronts using a deep learning neural network. Advances in Statistical Climatology
20. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2016.90 ↗
21. Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De Laroussilhe, Q., Gesmundo, A., Attariyan, M., and Gelly, S. (2019). Parameter-Efficient Transfer Learning for NLP. International Conference on Machine Learning, PMLR.
22. Rebuffi, S.A., Bilen, H., and Vedaldi, A. (2017). Learning multiple visual domains with residual adapters. arXiv.
23. Objective fronts10.1017/S1350482798000553 ↗
24. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2017.106 ↗
25. Tang, Y., Bai, W., Li, G., Liu, X., and Zhang, Y. (2022, January 17–21). CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems. Proceedings of the CIKM ‘22: The 31st ACM International Conference on Information and Knowledge Management, Atlanta, GA, USA.10.1145/3511808.3557274 ↗
26. Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25–28). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.10.1109/3DV.2016.79 ↗
27. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2015.123 ↗
28. Li, M., Zhang, T., Chen, Y., and Smola, A.J. (2014, January 24–27). Efficient minibatch training for stochastic optimization. Proceedings of the KDD ‘14: The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623612 ↗
29. Smith, L.N. (2017, January 24–31). Cyclical learning rates for training neural networks. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.10.1109/WACV.2017.58 ↗
30. A systematic analysis of performance measures for classification tasks
31. Powers, D.M. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv.
32. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (ECCV), IEEE.10.1007/978-3-030-01234-2_49 ↗
33. Classification assessment methods10.1016/j.aci.2018.08.003 ↗