SCENT统一处理科学数据的插值、重建与预测，高效且可扩展。
SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
- 基于Transformer架构，用可学习查询捕捉多尺度时空依赖。
- 在真实与模拟数据上实现领先性能，支持任意分辨率输出。
- 适合处理高维、不规则、大规模科学数据的研究者使用。
时空学习因空间与时间依赖关系复杂、数据维度高及可扩展性限制而困难重重。这一挑战在科学领域尤为突出：数据常呈不规则分布（如传感器故障导致缺失），且体量巨大（如高保真模拟），带来额外计算与建模难题。本文提出SCENT框架，实现可扩展且连续性感知的时空表征学习。该框架统一了插值、重建与预测任务，采用基于Transformer的编码器-处理器-解码器结构，引入可学习查询以增强泛化能力，并设计查询级交叉注意力机制有效捕捉多尺度依赖。为保障数据规模与模型复杂度下的可扩展性，采用稀疏注意力机制，支持灵活输出表示并实现任意分辨率下的高效评估。通过大量仿真与真实世界实验验证，SCENT在多项挑战性任务中表现领先，同时具备优异可扩展性。
原文摘要 · Abstract (English)
Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains, where data is often irregularly distributed (e.g., missing values from sensor failures) and high-volume (e.g., high-fidelity simulations), posing additional computational and modeling difficulties. In this paper, we present SCENT, a novel framework for scalable and continuity-informed spatiotemporal representation learning. SCENT unifies interpolation, reconstruction, and forecasting within a single architecture. Built on a transformer-based encoder-processor-decoder backbone, SCENT introduces learnable queries to enhance generalization and a query-wise cross-attention mechanism to effectively capture multi-scale dependencies. To ensure scalability in both data size and model complexity, we incorporate a sparse attention mechanism, enabling flexible output representations and efficient evaluation at arbitrary resolutions. We validate SCENT through extensive simulations and real-world experiments, demonstrating state-of-the-art performance across multiple challenging tasks while achieving superior scalability.
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。