# MATNet: Multi-Level Fusion Transformer-Based Model for Day-Ahead PV Generation Forecasting

arXiv: https://arxiv.org/abs/2306.10356 · HTML: https://mlsanity.com/paper/2306.10356/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 76 references that are in the map.
- First posted on arXiv 17 Jun 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Adaptive Input Representations for Neural Language Modeling](https://mlsanity.com/paper/1809.10853/) (2018)
- [Attend and Diagnose: Clinical Time Series Analysis using Attention Models](https://mlsanity.com/paper/1711.03905/) (2017)
- [Criteria for Classifying Forecasting Methods](https://mlsanity.com/paper/2212.03523/) (2022)
- [Spatio-temporal graph neural networks for multi-site PV power forecasting](https://mlsanity.com/paper/2107.13875/) (2021)
- [RadioPathomics: Multimodal Learning in Non-Small Cell Lung Cancer for Adaptive Radiotherapy](https://mlsanity.com/paper/2204.12423/) (2022)
- [Modeling Order in Neural Word Embeddings at Scale](https://mlsanity.com/paper/1506.02338/) (2015)
- [A TCN-based Hybrid Forecasting Framework for Hours-ahead Utility-scale PV Forecasting](https://mlsanity.com/paper/2111.08809/) (2021)
- [Multi-Resolution, Multi-Horizon Distributed Solar PV Power Forecasting with Forecast Combinations](https://mlsanity.com/paper/2206.10795/) (2022)
- [Energy Forecasting in Smart Grid Systems: A Review of the State-of-the-art Techniques](https://mlsanity.com/paper/2011.12598/) (2020)
- [A VAE-Bayesian Deep Learning Scheme for Solar Generation Forecasting based on Dimensionality Reduction](https://mlsanity.com/paper/2103.12969/) (2021)
- [Day-Ahead and Intra-Day Planning of Integrated BESS-PV Systems providing Frequency Regulation](https://mlsanity.com/paper/2104.07352/) (2021)
- [A Bayesian Deep Learning Technique for Multi-Step Ahead Solar Generation Forecasting](https://mlsanity.com/paper/2203.11379/) (2022)

## Built on by (most cited first, 2 of 2)

- [Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates](https://mlsanity.com/paper/2602.17683/) (2026)
- [Hybrid Quantum Neural Network for Multivariate Clinical Time Series Forecasting](https://mlsanity.com/paper/2603.08072/) (2026)

## Abstract (arXiv)

Accurate forecasting of renewable generation is crucial to facilitate the integration of Renewable Energy Sources into the power system. Focusing on photovoltaic (PV) units, forecasting methods can be divided into two main categories: physics-based and data-based strategies, with Artificial Intelligence (AI)-based models providing state-of-the-art performance. However, while these AI-based models can capture complex patterns and relationships in the data, they ignore the underlying physical prior knowledge of the phenomenon. Therefore, in this paper, we propose MATNet, a novel transformer-based multimodal architecture for multi-step day-ahead PV power generation forecasting. The model is fed with historical PV data and historical and forecast weather data through a multi-level joint fusion approach, employing a soft-attention mechanism at multiple fusion stages. We evaluate the effectiveness of MATNet on the Ausgrid benchmark dataset, where it significantly outperforms various baseline models, achieving an RMSE of 0.0445, corresponding to a relative improvement of approximately 65% compared to the best-performing baseline method. The analysis is further enriched by a comprehensive set of ablation studies, a sensitivity analysis on missing data, which highlights MATNet's resilience to input degradation, a cross-site zero-shot generalization evaluation on five external PV datasets, demonstrating MATNet's robustness under significant domain shifts, and an assessment of the model's computational complexity, confirming its favorable balance between predictive accuracy and computational efficiency. These results highlight MATNet's potential as a reliable and efficient solution to facilitate the integration of PV energy into the power grid. The code is available at https://github.com/arco-group/MATNet.