Skip to content
Preprint

Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Queries

Aug 2026 · 0 citations · 30 references
Computer Science

TL;DR

The Continuous Spatiotemporal Temperature Forecaster (CSTF) is proposed, a neural field that turns forecast lead time and output resolution into explicit queries when evaluating 2-m temperature (T2M) and achieves the best aggregate deterministic skill.

Abstract

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.

View source

Similar papers

Book Open access Aug 2026

RainCast: A High-Resolution 72-Hour Short-Term Precipitation Forecasting Model

RainCast is proposed, a high-resolution framework for hourly precipitation forecasting over China up to 72 hours ahead at 0.05° resolution that incorporates a physics-guided feature extractor and a multi-head output design that supports both deterministic forecasts with a regression head and probabilistic multi-member...

Guanlong Ma, Weiqiu Chen, Yang Zhao et al. · 0 citations

From Nowcasting to Forecasting: Adapting a Reanalysis-Trained

Results show that observation-initialized machine-learning forecasts can extend beyond the usual 1-3-hour nowcasting range while retaining spatial detail from satellite cloud fields, and overtake CloudCast v1 in fractions skill score, a neighborhood-based measure of spatial agreement, after approximately 3-6 h, dependi...

Mikko Partio, Leila Hieta, Ossi Laine · 0 citations
Preprint Aug 2026

Tropical Cyclone Forecasting via Latent Rectified Flow using Satellite Imagery and Atmospheric Fields

This work presents a single-pass model that jointly forecasts GRIDSAT-B1 infrared imagery and four ERA5 atmospheric fields out to nine hours and reward-fine-tuned against a differentiable track error derived from the predicted winds through a steering-flow calculation.

M. Zannat, Sk. Md. Masudul Ahsan · 0 citations
#machine learning Preprint Sep 2026

WeatherNext 3: Increasing resolution and performance of global weather models with raw observations

Together, WeatherNext 3's capabilities move operational AI-based weather forecasting beyond emulating the traditionally distinct stages of data assimilation, forecasting and post-processing, which helps to further push the frontier of performance and granularity for global weather prediction.

S. Rasp, B. Babenko, Dominic Masters et al. · 3 citations
Preprint Aug 2026

Bridging short- and medium-range weather forecasting with machine learning

Nested-EAGLE (Experimental Artificial intelligence Global and Limited-area Ensemble) is presented, showing that the skill gains for near-surface fields stem from incorporating high-resolution regional analysis data into training through the nesting process, and provides the most accurate forecasts of storm locations at...

Timothy A. Smith, Mariah Pope, Sergey Frolov et al. · 2 citations
Preprint Aug 2026

Timestep-Conditioned Transformers for Global Weather Forecasting

GEM-3, a probabilistic global weather model that addresses this trade-off through explicit multi-timestep inference, is presented, a practical forecasting system that couples near-SOTA medium-range probabilistic skill, stable extended-range rollouts, efficient training and inference, and decision-relevant diagnostics.

Sam Levang, Fran Bartolić, Ty A. Dickinson et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.