# Deep learning for spatio-temporal forecasting -- application to solar energy

arXiv: https://arxiv.org/abs/2205.03571 · HTML: https://mlsanity.com/paper/2205.03571/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2022.

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

- [WindDragon: Enhancing wind power forecasting with Automated Deep Learning](https://mlsanity.com/paper/2402.14385/) (2024)

## Abstract (arXiv)

This thesis tackles the subject of spatio-temporal forecasting with deep learning. The motivating application at Electricity de France (EDF) is short-term solar energy forecasting with fisheye images. We explore two main research directions for improving deep forecasting methods by injecting external physical knowledge. The first direction concerns the role of the training loss function. We show that differentiable shape and temporal criteria can be leveraged to improve the performances of existing models. We address both the deterministic context with the proposed DILATE loss function and the probabilistic context with the STRIPE model. Our second direction is to augment incomplete physical models with deep data-driven networks for accurate forecasting. For video prediction, we introduce the PhyDNet model that disentangles physical dynamics from residual information necessary for prediction, such as texture or details. We further propose a learning framework (APHYNITY) that ensures a principled and unique linear decomposition between physical and data-driven components under mild assumptions, leading to better forecasting performances and parameter identification.