# Benchmarking of Deep Learning Irradiance Forecasting Models from Sky Images -- an in-depth Analysis

arXiv: https://arxiv.org/abs/2102.00721 · HTML: https://mlsanity.com/paper/2102.00721/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 63 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models](https://mlsanity.com/paper/1909.09020/) (2019)
- [Orientation-aware Semantic Segmentation on Icosahedron Spheres](https://mlsanity.com/paper/1907.12849/) (2019)
- [Deep Photovoltaic Nowcasting](https://mlsanity.com/paper/1810.06327/) (2018)
- [A deep learning approach to solar-irradiance forecasting in sky-videos](https://mlsanity.com/paper/1901.04881/) (2019)

## Built on by (most cited first, 21 of 21)

- [ECLIPSE : Envisioning CLoud Induced Perturbations in Solar Energy](https://mlsanity.com/paper/2104.12419/) (2021)
- [SKIPP'D: a SKy Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting](https://mlsanity.com/paper/2207.00913/) (2022)
- [SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting](https://mlsanity.com/paper/2111.14507/) (2021)
- [LightLLM: A Versatile Large Language Model for Predictive Light Sensing](https://mlsanity.com/paper/2411.15211/) (2024)
- [Lightning UQ Box: A Comprehensive Framework for Uncertainty Quantification in Deep Learning](https://mlsanity.com/paper/2410.03390/) (2024)
- [SolarGAN: Synthetic Annual Solar Irradiance Time Series on Urban Building Facades via Deep Generative Networks](https://mlsanity.com/paper/2206.00747/) (2022)
- [Sky-image-based solar forecasting using deep learning with multi-location data: training models locally, globally or via transfer learning?](https://mlsanity.com/paper/2211.02108/) (2022)
- [Open-Source Ground-based Sky Image Datasets for Very Short-term Solar Forecasting, Cloud Analysis and Modeling: A Comprehensive Survey](https://mlsanity.com/paper/2211.14709/) (2022)
- [SkyGPT: Probabilistic Short-term Solar Forecasting Using Synthetic Sky Videos from Physics-constrained VideoGPT](https://mlsanity.com/paper/2306.11682/) (2023)
- [Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction](https://mlsanity.com/paper/2411.10921/) (2024)
- [SolarCrossFormer: Improving day-ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors](https://mlsanity.com/paper/2509.15827/) (2025)
- [Intraday spatiotemporal PV power prediction at national scale using satellite-based solar forecast models](https://mlsanity.com/paper/2601.04751/) (2026)
- [Omnivision forecasting: combining satellite observations with sky images for improved intra-hour solar energy predictions](https://mlsanity.com/paper/2206.03207/) (2022)
- [A Meta-Analysis of Solar Forecasting Based on Skill Score](https://mlsanity.com/paper/2208.10536/) (2022)
- [Short-Term Solar Irradiance Forecasting Under Data Transmission Constraints](https://mlsanity.com/paper/2403.12873/) (2024)
- [Solar Irradiance Anticipative Transformer](https://mlsanity.com/paper/2305.18487/) (2023)
- [Developing a Thailand solar irradiance map using Himawari-8 satellite imageries and deep learning models](https://mlsanity.com/paper/2409.16320/) (2024)
- [Deep Learning Multi-Horizon Irradiance Nowcasting: A Comparative Evaluation of Three Methods for Leveraging Sky Images](https://mlsanity.com/paper/2603.26704/) (2026)
- [Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks](https://mlsanity.com/paper/2604.13455/) (2026)
- [FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting](https://mlsanity.com/paper/2608.11254/) (2026)
- [SolarBench: A global solar energy nowcasting benchmark](https://mlsanity.com/paper/2609.06187/) (2026)

## Abstract (arXiv)

A number of industrial applications, such as smart grids, power plant operation, hybrid system management or energy trading, could benefit from improved short-term solar forecasting, addressing the intermittent energy production from solar panels. However, current approaches to modelling the cloud cover dynamics from sky images still lack precision regarding the spatial configuration of clouds, their temporal dynamics and physical interactions with solar radiation. Benefiting from a growing number of large datasets, data driven methods are being developed to address these limitations with promising results. In this study, we compare four commonly used Deep Learning architectures trained to forecast solar irradiance from sequences of hemispherical sky images and exogenous variables. To assess the relative performance of each model, we used the Forecast Skill metric based on the smart persistence model, as well as ramp and time distortion metrics. The results show that encoding spatiotemporal aspects of the sequence of sky images greatly improved the predictions with 10 min ahead Forecast Skill reaching 20.4% on the test year. However, based on the experimental data, we conclude that, with a common setup, Deep Learning models tend to behave just as a 'very smart persistence model', temporally aligned with the persistence model while mitigating its most penalising errors. Thus, despite being captured by the sky cameras, models often miss fundamental events causing large irradiance changes such as clouds obscuring the sun. We hope that our work will contribute to a shift of this approach to irradiance forecasting, from reactive to anticipatory.