probabilistic-forecasting

SimCast-S2S is a generative latent-diffusion framework for probabilistic subseasonal precipitation forecasting that leverages transfer learning from climate simulations to outperform deep learning baselines and compete with operational systems.

This study systematically evaluates TabPFN-TS for zero-shot probabilistic heat load forecasting in district heating networks, comparing it with state-of-the-art time-series foundation models like Chronos-2 and machine-learning baselines.

TinyCast is a compact zero-shot time series foundation model with computed periodicity, enabling efficient probabilistic forecasting on edge devices like Cortex-M7.

This paper proposes DiffDiff, a diffusion framework for probabilistic time series forecasting that embeds predictability asymmetry into the diffusion trajectory, outperforming six diffusion baselines on seven benchmarks across four prediction horizons.

The paper proposes a verifiable label-free reward for training calibrated probabilistic forecasters using reinforcement learning, avoiding the calibration degradation that occurs when rewarding single outcomes. Applied to NFL win probability, a 7B model trained with this reward achieves calibration comparable to the betting market.

This paper introduces Explanation Quality Markers (EQMs), a set of 60 reasoning patterns scored by LLMs to measure the quality of natural-language explanations in forecasting tournaments. Analyzing over 55,000 forecast-rationale pairs, EQMs predict accuracy at both forecast and forecaster levels, outperforming previous methods.

Otter Weather is a computationally efficient AI model for medium-range weather forecasting that outperforms numerical weather prediction baselines and frontier AI models while requiring significantly less training compute, aiming to democratize high-performance weather prediction.

This paper introduces regime-stratified evaluation for time series foundation models, revealing that aggregate metrics hide severe failures during traffic regime transitions, and proposes bimodal mixture augmentation to improve coverage while preserving overall accuracy.

SAGA introduces a decoder-only transformer for multi-horizon probabilistic forecasting of lifetime earnings, paired with adaptive conformal prediction to provide reliable prediction intervals. Trained on a large Swedish register dataset, it achieves significant improvements over traditional parametric and baseline models.