融合二维图像与一维数据，用Transformer提升核聚变能量增益预测精度。
Multi-modal Fusion based Q-distribution Prediction for Controlled Nuclear Fusion
- 用2D图像和1D信号构建双模输入，通过Transformer交互融合特征。
- 实验显示预测误差显著降低，提升聚变能量增益预测准确性。
- 适合关注聚变能源建模与多模态深度学习的科研人员。
Q-distribution预测是可控核聚变研究的关键方向，深度学习成为解决预测挑战的重要手段。本文利用深度学习方法应对Q-distribution预测的复杂性，探索计算机视觉中的多模态融合技术，将二维线图像数据与原始一维数据结合，形成双模态输入。同时，采用Transformer的注意力机制进行特征提取，并实现双模态信息的交互融合。大量实验验证了该方法的有效性，显著降低了Q-distribution的预测误差。
原文摘要 · Abstract (English)
Q-distribution prediction is a crucial research direction in controlled nuclear fusion, with deep learning emerging as a key approach to solving prediction challenges. In this paper, we leverage deep learning techniques to tackle the complexities of Q-distribution prediction. Specifically, we explore multimodal fusion methods in computer vision, integrating 2D line image data with the original 1D data to form a bimodal input. Additionally, we employ the Transformer's attention mechanism for feature extraction and the interactive fusion of bimodal information. Extensive experiments validate the effectiveness of our approach, significantly reducing prediction errors in Q-distribution.
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。