# Deep Compositional Spatial Models.

@article{ZammitMangion2019DeepCS, title={Deep Compositional Spatial Models.}, author={Andrew Zammit‐Mangion and Tin Lok James Ng and Quan H. Vu and Maurizio Filippone}, journal={arXiv: Methodology}, year={2019} }

Spatial processes with nonstationary and anisotropic covariance structure are often used when modelling, analysing and predicting complex environmental phenomena. Such processes may often be expressed as ones that have stationary and isotropic covariance structure on a warped spatial domain. However, the warping function is generally difficult to fit and not constrained to be injective, often resulting in `space-folding.' Here, we propose modelling an injective warping function through a… CONTINUE READING

6 Citations

SXL: Spatially explicit learning of geographic processes with auxiliary tasks

- Computer Science, Mathematics
- 2020

Deep Integro-Difference Equation Models for Spatio-Temporal Forecasting

- Mathematics, Computer Science
- 2019

1

Spatiotemporal Multi-Resolution Approximations for Analyzing Global Environmental Data

- Computer Science, Mathematics
- 2020

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 88 REFERENCES

Hierarchical (Deep) Echo State Networks with Uncertainty Quantification for Spatio-Temporal Forecasting

- Computer Science, Mathematics
- 2018

17

Posterior inference for sparse hierarchical non-stationary models

- Computer Science, Mathematics
- 2020

15

Advances in Modeling and Inference for Environmental Processes with Nonstationary Spatial Covariance

- Computer Science
- 2001

47

Warped Gaussian Processes and Derivative-Based Sequential Designs for Functions with Heterogeneous Variations

- Mathematics, Computer Science
- 2018

9

Bayesian estimation of semi‐parametric non‐stationary spatial covariance structures

- Mathematics
- 2001

117

Doubly Stochastic Variational Inference for Deep Gaussian Processes

- Mathematics, Computer Science
- 2017

143