Search papers, labs, and topics across Lattice.
This paper introduces the Continuous Spatiotemporal Temperature Forecaster (CSTF), a neural network designed to forecast regional near-surface temperatures by allowing for query-dependent lead times and output resolutions. By encoding historical meteorological data and decoding temperature fields based on explicit queries, CSTF overcomes the limitations of traditional fixed-output forecasting methods. The results show a significant improvement in forecasting accuracy, achieving a 17% reduction in bias compared to existing benchmarks in the Southeast China 0-6 h ERA5-Land dataset.
Query-conditioned forecasting can reduce temperature prediction bias by 17% while enabling flexible lead times and resolutions.
Accurate regional near-surface temperature forecasting is fundamental to short-range weather services and downstream risk assessment. Existing deep learning-based regional forecasters commonly produce a fixed set of future frames on a prescribed grid, limiting their use when forecast products must be evaluated at query-dependent lead times or display resolutions. To overcome these fixed-output constraints, we formulate regional T2M forecasting as query-conditioned continuous spatiotemporal temperature field evaluation and propose the Continuous Spatiotemporal Temperature Forecaster (CSTF), a neural field that turns forecast lead time and output resolution into explicit queries when evaluating 2-m temperature (T2M). Specifically, CSTF first encodes multivariable ERA5 histories into latent meteorological states and then decodes T2M as a coordinate-based field. Accordingly, spatial location, forecast lead time, and output resolution are introduced as queries, enabling standard hourly forecasts, intermediate lead-time diagnostics, and resolution-controllable outputs within a unified field-evaluation framework. Furthermore, to maintain coherence across flexible field queries, we design spatial-gradient, temporal-difference, and scale-consistency objectives that regularize regional thermal structures, lead-wise evolution, and cross-resolution agreement. Experiments on the Southeast China 0-6 h ERA5-Land benchmark demonstrate that CSTF achieves the best aggregate deterministic skill, including a 17.0 percent reduction in Bias, with global-scope diagnostics further illustrating flexible lead-time and resolution-controllable inference.
