用轻量模型精准预测印度次大陆6小时颗粒物浓度，兼顾速度与精度。
A Comparison of Lightweight Deep Learning Models for Particulate-Matter Nowcasting in the Indian Subcontinent & Surrounding Regions
- 基于CAMS气象数据设计轻量神经网络，聚焦印度区域短时预报。
- 在2024年测试数据上，均方根误差降低30%以上，系统偏差显著减少。
- 适合需要快速部署的空气质量实时预警系统使用。
本文为Weather4Cast~2025污染任务的提交成果，提出一种高效框架，实现对印度次大陆及周边地区PM₁、PM₂.₅和PM₁₀的6小时前瞻性预测。模型输入为0.4度分辨率的哥白尼大气监测服务（CAMS）分析场，空间范围为28.4S–73.6N、32E–134.0E，预测区域为中心128x128像素的2.8S–48N、57.6E–108.4E，确保以印度为中心并包含大尺度气象背景。模型在2021–2023年CAMS数据上训练，采用随机90/10划分，并在2024年数据上独立评估。设计三种参数精简的轻量级架构，提升准确性、降低系统偏差并实现快速推理。通过RMSE、MAE、Bias和SSIM评估显示，相比Aurora基础模型性能显著提升，验证了紧凑且专用的深度学习模型在小范围短时预报中的有效性。
原文摘要 · Abstract (English)
This paper is a submission for the Weather4Cast~2025 complementary Pollution Task and presents an efficient framework for 6-hour lead-time nowcasting of PM$_1$, PM$_{2.5}$, and PM$_{10}$ across the Indian subcontinent and surrounding regions. The proposed approach leverages analysis fields from the Copernicus Atmosphere Monitoring Service (CAMS) Global Atmospheric Composition Forecasts at 0.4 degree resolution. A 256x256 spatial region, covering 28.4S-73.6N and 32E-134.0E, is used as the model input, while predictions are generated for the central 128x128 area spanning 2.8S-48N and 57.6E-108.4E, ensuring an India-centric forecast domain with sufficient synoptic-scale context. Models are trained on CAMS analyses from 2021-2023 using a shuffled 90/10 split and independently evaluated on 2024 data. Three lightweight parameter-specific architectures are developed to improve accuracy, minimize systematic bias, and enable rapid inference. Evaluation using RMSE, MAE, Bias, and SSIM demonstrates substantial performance gains over the Aurora foundation model, underscoring the effectiveness of compact & specialized deep learning models for short-range forecasts on limited spatial domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。