FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting

arXiv cs.LG Papers
solar-forecasting generative-models latent-diffusion renewable-energy deep-learning all-sky-imagery

Summary

FarSky is a generative forecasting framework using task-aware latent-space coupling with latent diffusion to produce deterministic and probabilistic intra-hour solar irradiance forecasts, achieving up to 11 percentage points improvement in skill and better ramp event detection.

arXiv:2608.11254v1 Announce Type: new Abstract: Accurate solar irradiance forecasting is essential for the reliable integration of photovoltaic power into modern electricity grids. All-sky imagers (ASI) provide high-resolution observations of clouds, making them well suited for intra-hour forecasting. Recent deep learning approaches have substantially improved forecast accuracy but are often limited by deterministic predictions and a reduced capability to anticipate ramp events. This work proposes FarSky, a generative forecasting framework that leverages latent-space coupling to learn task-aware representations of sky images. A multi-task autoencoder first learns a shared latent representation for image reconstruction and irradiance estimation. A latent diffusion model then generates future latent states conditioned on recent observations, from which irradiance forecasts are directly decoded. Probabilistic forecasts are inherently obtained through stochastic sampling. The framework is developed using a multi-year ASI dataset acquired at the Plataforma Solar de Almer\'ia, Spain, and evaluated on two independent test datasets against persistence, state-of-the-art end-to-end, and generative forecasting approaches. FarSky achieves the best overall deterministic and probabilistic forecasting performance, improving forecast skill by up to 11 percentage points. Furthermore, it substantially improves ramp event detection over existing methods, achieving F1-scores above 60%. These results demonstrate the potential of combining generative models with task-aware latent-space coupling for solar forecasting.
Original Article
View Cached Full Text

Cached at: 08/13/26, 03:33 PM 

# FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
Source: [https://arxiv.org/abs/2608.11254](https://arxiv.org/abs/2608.11254)
[View PDF](https://arxiv.org/pdf/2608.11254)

> Abstract:Accurate solar irradiance forecasting is essential for the reliable integration of photovoltaic power into modern electricity grids\. All\-sky imagers \(ASI\) provide high\-resolution observations of clouds, making them well suited for intra\-hour forecasting\. Recent deep learning approaches have substantially improved forecast accuracy but are often limited by deterministic predictions and a reduced capability to anticipate ramp events\. This work proposes FarSky, a generative forecasting framework that leverages latent\-space coupling to learn task\-aware representations of sky images\. A multi\-task autoencoder first learns a shared latent representation for image reconstruction and irradiance estimation\. A latent diffusion model then generates future latent states conditioned on recent observations, from which irradiance forecasts are directly decoded\. Probabilistic forecasts are inherently obtained through stochastic sampling\. The framework is developed using a multi\-year ASI dataset acquired at the Plataforma Solar de Almería, Spain, and evaluated on two independent test datasets against persistence, state\-of\-the\-art end\-to\-end, and generative forecasting approaches\. FarSky achieves the best overall deterministic and probabilistic forecasting performance, improving forecast skill by up to 11 percentage points\. Furthermore, it substantially improves ramp event detection over existing methods, achieving F1\-scores above 60%\. These results demonstrate the potential of combining generative models with task\-aware latent\-space coupling for solar forecasting\.

## Submission history

From: Yann Fabel \[[view email](https://arxiv.org/show-email/95486da9/2608.11254)\] **\[v1\]**Thu, 6 Aug 2026 08:32:56 UTC \(13,695 KB\)

Similar Articles

LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting

arXiv cs.LG

This paper proposes Task-Semantic Field Factorization (TSF), an LLM-guided framework that uses offline semantic construction from process documents to enhance time-series forecasting and soft sensing in industrial processes. TSF reduces MAE by 6.4% on average with nearly negligible added parameters and inference overhead.

Ensemble Score Filtering for Real-Data Energy Consumption Forecast Correction

arXiv cs.LG

This paper proposes using the Ensemble Score Filter (EnSF), a score-based diffusion data assimilation method, to correct forecasts from a pretrained spatio-temporal energy consumption model using noisy partial observations. Numerical experiments show EnSF significantly improves state estimation over open-loop propagation and outperforms the Ensemble Kalman Filter under nonlinear observations.

Nested Spatio-Temporal Time Series Forecasting

arXiv cs.LG

This paper proposes a nested spatiotemporal forecasting framework that uses spectral clustering to construct semantically coherent macro-level regions, which provide top-down guidance for fine-grained micro-level predictions. Experiments on high-dimensional datasets show consistent improvements over state-of-the-art baselines.