Spatio-temporal probabilistic forecast using MMAF-guided learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918463868502016 |
|---|---|
| author | Bardi, Leonardo Curato, Imma Valentina Proietti, Lorenzo |
| author_facet | Bardi, Leonardo Curato, Imma Valentina Proietti, Lorenzo |
| contents | We present a theory-guided generalized Bayesian methodology for spatio-temporal raster data, which we use to train an ensemble of stochastic feed-forward neural networks with Gaussian-distributed weights. The methodology incorporates the dependence and causal structure of a spatio-temporal Ornstein-Uhlenbeck process into training and inference by enforcing constraints on the design of the data embedding and the related optimization routine. In inference mode, the networks are employed to generate causal ensemble forecasts by applying different initial conditions at different horizons. We call this workflow MMAF-guided learning. Experiments conducted on both synthetic and real data demonstrate that our forecasts remain calibrated across multiple time horizons. Moreover, we show that on such data, shallow feed-forward architectures can achieve performance comparable to, and in some cases better than, convolutional or diffusion deep learning architectures used in probabilistic forecasting tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15055 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spatio-temporal probabilistic forecast using MMAF-guided learning Bardi, Leonardo Curato, Imma Valentina Proietti, Lorenzo Machine Learning Statistics Theory 60E07, 62M20, 60G60, 62C10, 65K10, 68T07 We present a theory-guided generalized Bayesian methodology for spatio-temporal raster data, which we use to train an ensemble of stochastic feed-forward neural networks with Gaussian-distributed weights. The methodology incorporates the dependence and causal structure of a spatio-temporal Ornstein-Uhlenbeck process into training and inference by enforcing constraints on the design of the data embedding and the related optimization routine. In inference mode, the networks are employed to generate causal ensemble forecasts by applying different initial conditions at different horizons. We call this workflow MMAF-guided learning. Experiments conducted on both synthetic and real data demonstrate that our forecasts remain calibrated across multiple time horizons. Moreover, we show that on such data, shallow feed-forward architectures can achieve performance comparable to, and in some cases better than, convolutional or diffusion deep learning architectures used in probabilistic forecasting tasks. |
| title | Spatio-temporal probabilistic forecast using MMAF-guided learning |
| topic | Machine Learning Statistics Theory 60E07, 62M20, 60G60, 62C10, 65K10, 68T07 |
| url | https://arxiv.org/abs/2603.15055 |