Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.03133 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910907289829376 |
|---|---|
| author | Tushar, Zahid Hassan Ademakinwa, Adeleke Wang, Jianwu Zhang, Zhibo Purushotham, Sanjay |
| author_facet | Tushar, Zahid Hassan Ademakinwa, Adeleke Wang, Jianwu Zhang, Zhibo Purushotham, Sanjay |
| contents | Accurate cloud property retrieval is vital for understanding cloud behavior and its impact on climate, including applications in weather forecasting, climate modeling, and estimating Earth's radiation balance. The Independent Pixel Approximation (IPA), a widely used physics-based approach, simplifies radiative transfer calculations by assuming each pixel is independent of its neighbors. While computationally efficient, IPA has significant limitations, such as inaccuracies from 3D radiative effects, errors at cloud edges, and ineffectiveness for overlapping or heterogeneous cloud fields. Recent AI/ML-based deep learning models have improved retrieval accuracy by leveraging spatial relationships across pixels. However, these models are often memory-intensive, retrieve only a single cloud property, or struggle with joint property retrievals. To overcome these challenges, we introduce CloudUNet with Attention Module (CAM), a compact UNet-based model that employs attention mechanisms to reduce errors in thick, overlapping cloud regions and a specialized loss function for joint retrieval of Cloud Optical Thickness (COT) and Cloud Effective Radius (CER). Experiments on a Large Eddy Simulation (LES) dataset show that our CAM model outperforms state-of-the-art deep learning methods, reducing mean absolute errors (MAE) by 34% for COT and 42% for CER, and achieving 76% and 86% lower MAE for COT and CER retrievals compared to the IPA method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03133 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Joint Retrieval of Cloud properties using Attention-based Deep Learning Models Tushar, Zahid Hassan Ademakinwa, Adeleke Wang, Jianwu Zhang, Zhibo Purushotham, Sanjay Computer Vision and Pattern Recognition Accurate cloud property retrieval is vital for understanding cloud behavior and its impact on climate, including applications in weather forecasting, climate modeling, and estimating Earth's radiation balance. The Independent Pixel Approximation (IPA), a widely used physics-based approach, simplifies radiative transfer calculations by assuming each pixel is independent of its neighbors. While computationally efficient, IPA has significant limitations, such as inaccuracies from 3D radiative effects, errors at cloud edges, and ineffectiveness for overlapping or heterogeneous cloud fields. Recent AI/ML-based deep learning models have improved retrieval accuracy by leveraging spatial relationships across pixels. However, these models are often memory-intensive, retrieve only a single cloud property, or struggle with joint property retrievals. To overcome these challenges, we introduce CloudUNet with Attention Module (CAM), a compact UNet-based model that employs attention mechanisms to reduce errors in thick, overlapping cloud regions and a specialized loss function for joint retrieval of Cloud Optical Thickness (COT) and Cloud Effective Radius (CER). Experiments on a Large Eddy Simulation (LES) dataset show that our CAM model outperforms state-of-the-art deep learning methods, reducing mean absolute errors (MAE) by 34% for COT and 42% for CER, and achieving 76% and 86% lower MAE for COT and CER retrievals compared to the IPA method. |
| title | Joint Retrieval of Cloud properties using Attention-based Deep Learning Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.03133 |