用深度学习自动识别太阳暗条磁手性，准确率超70%
Automatic Classification of Magnetic Chirality of Solar Filaments from H-Alpha Observations
- 基于H-Alpha图像和预训练模型，实现太阳暗条磁手性自动分类
- 在1万+样本数据集上，右旋准确率达73%，左旋达69%
- 首个可复现的基准模型，适合太阳物理与机器学习交叉研究者
本研究利用先进的图像分类模型，基于日面光球层的H-Alpha观测数据对太阳暗条的磁手性进行自动分类。我们建立了首个可在MAGFiLO数据集上复现的基准方法。该数据集包含超过10,000个由人工标注的暗条样本，源自GONG H-Alpha观测，是目前最大规模的暗条检测与分类数据集。以往研究依赖更小的数据集，限制了模型的泛化能力与可比性。我们微调了ResNet、WideResNet、ResNeXt和ConvNeXt等多个预训练图像分类架构，并采用数据增强和每类加权损失函数进行优化。最佳模型ConvNeXtBase在左旋暗条分类上达到0.69的单类准确率，在右旋暗条上达到0.73。
原文摘要 · Abstract (English)
In this study, we classify the magnetic chirality of solar filaments from H-Alpha observations using state-of-the-art image classification models. We establish the first reproducible baseline for solar filament chirality classification on the MAGFiLO dataset. The MAGFiLO dataset contains over 10,000 manually-annotated filaments from GONG H-Alpha observations, making it the largest dataset for filament detection and classification to date. Prior studies relied on much smaller datasets, which limited their generalizability and comparability. We fine-tuned several pre-trained, image classification architectures, including ResNet, WideResNet, ResNeXt, and ConvNeXt, and also applied data augmentation and per-class loss weights to optimize the models. Our best model, ConvNeXtBase, achieves a per-class accuracy of 0.69 for left chirality filaments and $0.73$ for right chirality filaments.
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。