Physics-informed Blind Reconstruction of Dense Fields from Sparse Measurements using Neural Networks with a Differentiable Simulator
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917227407605760 |
|---|---|
| author | Aloni, Ofek Fishbain, Barak |
| author_facet | Aloni, Ofek Fishbain, Barak |
| contents | Generating dense physical fields from sparse measurements is a fundamental question in sampling, signal processing, and many other applications. State-of-the-art methods either use spatial statistics or rely on examples of dense fields in the training phase, which often are not available, and thus rely on synthetic data. Here, we present a reconstruction method that generates dense fields from sparse measurements, without assuming availability of the spatial statistics, nor of examples of the dense fields. This is made possible through the introduction of an automatically differentiable numerical simulator into the training phase of the method. The method is shown to have superior results over statistical and neural network based methods on a set of three standard problems from fluid mechanics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20496 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Physics-informed Blind Reconstruction of Dense Fields from Sparse Measurements using Neural Networks with a Differentiable Simulator Aloni, Ofek Fishbain, Barak Machine Learning Generating dense physical fields from sparse measurements is a fundamental question in sampling, signal processing, and many other applications. State-of-the-art methods either use spatial statistics or rely on examples of dense fields in the training phase, which often are not available, and thus rely on synthetic data. Here, we present a reconstruction method that generates dense fields from sparse measurements, without assuming availability of the spatial statistics, nor of examples of the dense fields. This is made possible through the introduction of an automatically differentiable numerical simulator into the training phase of the method. The method is shown to have superior results over statistical and neural network based methods on a set of three standard problems from fluid mechanics. |
| title | Physics-informed Blind Reconstruction of Dense Fields from Sparse Measurements using Neural Networks with a Differentiable Simulator |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.20496 |