# SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models

arXiv: https://arxiv.org/abs/2502.10307 · HTML: https://mlsanity.com/paper/2502.10307/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 14 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [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)
- [Enabling Sustainable Clouds: The Case for Virtualizing the Energy System](https://mlsanity.com/paper/2106.08872/) (2021)
- [SKIPP'D: a SKy Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting](https://mlsanity.com/paper/2207.00913/) (2022)
- [A deep learning approach to solar-irradiance forecasting in sky-videos](https://mlsanity.com/paper/1901.04881/) (2019)
- [Open World Object Detection in the Era of Foundation Models](https://mlsanity.com/paper/2312.05745/) (2023)
- [A Comprehensive Study of Vision Transformers on Dense Prediction Tasks](https://mlsanity.com/paper/2201.08683/) (2022)
- [Estimating Solar Irradiance Using Sky Imagers](https://mlsanity.com/paper/1910.04981/) (2019)
- [Short-Term Solar Irradiance Forecasting Under Data Transmission Constraints](https://mlsanity.com/paper/2403.12873/) (2024)

## Built on by (most cited first, 1 of 1)

- [Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting](https://mlsanity.com/paper/2606.07457/) (2026)

## Abstract (arXiv)

Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer photovoltaic farms. As renewable energy is highly intermittent, building accurate solar irradiance forecasting systems is essential for efficient grid management and enabling the ongoing proliferation of solar energy, which is crucial to achieve the United Nations' net zero goals. In this work, we propose SPIRIT, a novel approach leveraging foundation models for solar irradiance forecasting, making it applicable to newer solar installations. Our approach outperforms state-of-the-art models in zero-shot transfer learning by about 70%, enabling effective performance at new locations without relying on any historical data. Further improvements in performance are achieved through fine-tuning, as more location-specific data becomes available. These findings are supported by statistical significance, further validating our approach. SPIRIT represents a pivotal step towards rapid, scalable, and adaptable solar forecasting solutions, advancing the integration of renewable energy into global power systems.