mlsanityData to 14 Oct 2026

An adaptive and evolvable deep reinforcement learning framework for weather prediction

arXiv 2608.09948 ↗First posted 7 Jul 2026physics.ao-ph cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

No single AI weather model excels at all variables, pressure levels, and lead times. Rather than building yet another architecture, we reframe the forecasting problem as one of coordination. Here we present Feitian Adaptive Ensemble Weather (FTAE-Weather), a lightweight framework that learns, through deep reinforcement learning, when and where to trust each member of an open pool of pretrained forecasters. A tactical Weight-Agent reads the current atmospheric state and assigns variable- and horizon-specific fusion weights, while a strategic Evolve-Agent periodically prunes underperforming models and absorbs newly released ones. Asynchronous prediction caching keeps training cost independent of the slowest constituent model. Adding fewer than 0.01 percent extra parameters, FTAE-Weather reduces RMSE by from 17.2 percent to 78.3 percent over the best individual model in 10 atmospheric variables and outperforms conventional ensemble baselines across lead times from 72 to 360 hours. The framework thus converts a growing, fragmented inventory of specialist models into a single prediction system that strengthens as the field of AI weather forecasting releases new architectures-turning model diversity from a coordination challenge into a compounding scientific advantage.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 53 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

20 of 53 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  7. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  8. 2023ClimaX: A foundation model for weather and climatecited by 337
  9. 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 241
  10. 2023Neural General Circulation Models for Weather and Climatecited by 239
  11. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 236
  12. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 233
8 more
  1. 2022FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operatorscited by 188
  2. 2022Forecasting Global Weather with Graph Neural Networkscited by 168
  3. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 110
  4. 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEscited by 82
  5. 2025FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scalecited by 62
  6. 2024Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modelingcited by 32
  7. 2024Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Predictioncited by 15
  8. 2025MoWE : A Mixture of Weather Expertscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling
  2. 2025FedRAIN-Lite: Federated Reinforcement Algorithms for Improving Idealised Numerical Weather and Climate Models
  3. 2024RAIN: Reinforcement Algorithms for Improving Numerical Weather and Climate Models
  4. 2026Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning
  5. 2025Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM
  6. 2024Data Assimilation in Chaotic Systems Using Deep Reinforcement Learning
  7. 2023Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels
  8. 2026ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory