# SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields Source: [SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:30:26.676Z Authors: David Keetae Park, Xihaier Luo, Guang Zhao, Seungjun Lee, Miruna Oprescu, Shinjae Yoo Published: 2025-04-16T17:17:31.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Spatiotemporal Forecasting on AirDelhi AD-B](): Spatiotemporal forecasting; AirDelhi AD-B; CRPS: 28.467. - [Spatiotemporal Field Reconstruction on Navier-Stokes (Full)](): Spatiotemporal Field Reconstruction; Navier-Stokes (Full); CRPS: 0.5568. - [Spatiotemporal Field Reconstruction on Navier-Stokes 10% Subset](): Spatiotemporal Field Reconstruction; Navier-Stokes 10% Subset; CRPS: 1.2591. ## Original sources and implementation [Original paper]() [PDF]()