# Nearest-Neighbor Neural Networks for Geostatistics

arXiv: https://arxiv.org/abs/1903.12125 · HTML: https://mlsanity.com/paper/1903.12125/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 6 of 6)

- [Statistical Deep Learning for Spatial and Spatio-Temporal Data](https://mlsanity.com/paper/2206.02218/) (2022)
- [Bivariate DeepKriging for Large-scale Spatial Interpolation of Wind Fields](https://mlsanity.com/paper/2307.08038/) (2023)
- [A Hybrid Framework for Spatial Interpolation: Merging Data-driven with Domain Knowledge](https://mlsanity.com/paper/2409.00125/) (2024)
- [Spatial Transfer Learning with Simple MLP](https://mlsanity.com/paper/2405.03720/) (2024)
- [Reservoir Static Property Estimation Using Nearest-Neighbor Neural Network](https://mlsanity.com/paper/2409.15295/) (2024)
- [A comparison between geostatistical and machine learning models for spatio-temporal prediction of PM2.5 data](https://mlsanity.com/paper/2509.12051/) (2025)

## Abstract (arXiv)

Kriging is the predominant method used for spatial prediction, but relies on the assumption that predictions are linear combinations of the observations. Kriging often also relies on additional assumptions such as normality and stationarity. We propose a more flexible spatial prediction method based on the Nearest-Neighbor Neural Network (4N) process that embeds deep learning into a geostatistical model. We show that the 4N process is a valid stochastic process and propose a series of new ways to construct features to be used as inputs to the deep learning model based on neighboring information. Our model framework outperforms some existing state-of-art geostatistical modelling methods for simulated non-Gaussian data and is applied to a massive forestry dataset.