# A Distributed Neural Network Architecture for Robust Non-Linear Spatio-Temporal Prediction

arXiv: https://arxiv.org/abs/1912.11141 · HTML: https://mlsanity.com/paper/1912.11141/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Composing Partial Differential Equations with Physics-Aware Neural Networks](https://mlsanity.com/paper/2111.11798/) (2021)
- [Finite Volume Neural Network: Modeling Subsurface Contaminant Transport](https://mlsanity.com/paper/2104.06010/) (2021)
- [NeuralPDE: Modelling Dynamical Systems from Data](https://mlsanity.com/paper/2111.07671/) (2021)
- [DynaBench: A benchmark dataset for learning dynamical systems from low-resolution data](https://mlsanity.com/paper/2306.05805/) (2023)
- [TaylorPDENet: Learning PDEs from non-grid Data](https://mlsanity.com/paper/2306.14511/) (2023)
- [Inferring Underwater Topography with FINN](https://mlsanity.com/paper/2408.10649/) (2024)
- [Minimal Convolutional RNNs Accelerate Spatiotemporal Learning](https://mlsanity.com/paper/2508.03614/) (2025)

## Abstract (arXiv)

We introduce a distributed spatio-temporal artificial neural network architecture (DISTANA). It encodes mesh nodes using recurrent, neural prediction kernels (PKs), while neural transition kernels (TKs) transfer information between neighboring PKs, together modeling and predicting spatio-temporal time series dynamics. As a consequence, DISTANA assumes that generally applicable causes, which may be locally modified, generate the observed data. DISTANA learns in a parallel, spatially distributed manner, scales to large problem spaces, is capable of approximating complex dynamics, and is particularly robust to overfitting when compared to other competitive ANN models. Moreover, it is applicable to heterogeneously structured meshes.