# ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting

arXiv: https://arxiv.org/abs/2510.09734 · HTML: https://mlsanity.com/paper/2510.09734/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 69 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [Forecasting Global Weather with Graph Neural Networks](https://mlsanity.com/paper/2202.07575/) (2022)
- [UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting](https://mlsanity.com/paper/2310.09751/) (2023)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning](https://mlsanity.com/paper/2403.07300/) (2024)
- [Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere](https://mlsanity.com/paper/2003.11927/) (2020)
- [ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs](https://mlsanity.com/paper/2404.10024/) (2024)
- [AirFormer: Predicting Nationwide Air Quality in China with Transformers](https://mlsanity.com/paper/2211.15979/) (2022)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2410.11802/) (2024)
- [PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting](https://mlsanity.com/paper/2002.12898/) (2020)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)
- [Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks](https://mlsanity.com/paper/2406.04759/) (2024)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction](https://mlsanity.com/paper/2402.03784/) (2024)
- [Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2405.14252/) (2024)
- [Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems](https://mlsanity.com/paper/2410.19892/) (2024)
- [Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting](https://mlsanity.com/paper/2211.16126/) (2022)
- [MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrast](https://mlsanity.com/paper/2410.15997/) (2024)
- [BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models](https://mlsanity.com/paper/2505.17871/) (2025)
- [CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control](https://mlsanity.com/paper/2503.11739/) (2025)
- [MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version](https://mlsanity.com/paper/2411.18428/) (2024)
- [Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework](https://mlsanity.com/paper/2410.10524/) (2024)
- [Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation](https://mlsanity.com/paper/2503.21200/) (2025)

## Built on by (most cited first, 8 of 8)

- [GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2603.08032/) (2026)
- [Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction](https://mlsanity.com/paper/2603.21612/) (2026)
- [TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching](https://mlsanity.com/paper/2606.03121/) (2026)
- [VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting](https://mlsanity.com/paper/2608.09286/) (2026)
- [TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control](https://mlsanity.com/paper/2604.17456/) (2026)
- [Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance](https://mlsanity.com/paper/2608.03521/) (2026)
- [POEM: Phase-Aware SO(2) Feature Rotation for Time Series Forecasting Under Periodicity Drift](https://mlsanity.com/paper/2608.03630/) (2026)
- [Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Queries](https://mlsanity.com/paper/2608.25823/) (2026)

## Abstract (arXiv)

Weather forecasting is a fundamental task in spatiotemporal data analysis, with broad applications across a wide range of domains. Existing data-driven forecasting methods typically model atmospheric dynamics over a fixed short time interval, e.g., 6 hours, and rely on naive autoregression-based rollout for long-term forecasting, e.g., 5 days. However, this paradigm suffers from two key limitations: (1) it often inadequately models the spatial and multi-scale temporal dependencies inherent in global weather systems, and (2) the rollout strategy struggles to balance error accumulation with the capture of fine-grained atmospheric variations. In this study, we propose ARROW, an Adaptive-Rollout Multi-scale temporal Routing method for Global Weather Forecasting. To contend with the first limitation, we construct a multi-interval forecasting model that forecasts weather across different time intervals. Within the model, the Shared-Private Mixture-of-Experts captures both shared patterns and specific characteristics of atmospheric dynamics across different time scales, while Ring Positional Encoding accurately encodes the circular latitude structure of the Earth when representing spatial information. For the second limitation, we develop an adaptive rollout scheduler based on reinforcement learning, which selects the most suitable time interval to forecast according to the current weather state. Experimental results demonstrate that ARROW achieves state-of-the-art performance in global weather forecasting, establishing a promising paradigm in this field.