DeepAI AI Chat
Log In Sign Up

High Performance Multivariate Spatial Modeling for Geostatistical Data on Manycore Systems

by   Mary Lai O. Salvaña, et al.

Modeling and inferring spatial relationships and predicting missing values of environmental data are some of the main tasks of geospatial statisticians. These routine tasks are accomplished using multivariate geospatial models and the cokriging technique. The latter requires the evaluation of the expensive Gaussian log-likelihood function, which has impeded the adoption of multivariate geospatial models for large multivariate spatial datasets. However, this large-scale cokriging challenge provides a fertile ground for supercomputing implementations for the geospatial statistics community as it is paramount to scale computational capability to match the growth in environmental data coming from the widespread use of different data collection technologies. In this paper, we develop and deploy large-scale multivariate spatial modeling and inference on parallel hardware architectures. To tackle the increasing complexity in matrix operations and the massive concurrency in parallel systems, we leverage low-rank matrix approximation techniques with task-based programming models and schedule the asynchronous computational tasks using a dynamic runtime system. The proposed framework provides both the dense and the approximated computations of the Gaussian log-likelihood function. It demonstrates accuracy robustness and performance scalability on a variety of computer systems. Using both synthetic and real datasets, the low-rank matrix approximation shows better performance compared to exact computation, while preserving the application requirements in both parameter estimation and prediction accuracy. We also propose a novel algorithm to assess the prediction accuracy after the online parameter estimation. The algorithm quantifies prediction performance and provides a benchmark for measuring the efficiency and accuracy of several approximation techniques in multivariate spatial modeling.


Tile Low-Rank Approximation of Large-Scale Maximum Likelihood Estimation on Manycore Architectures

Maximum likelihood estimation is an important statistical technique for ...

ExaGeoStatR: A Package for Large-Scale Geostatistics in R

Parallel computing in Gaussian process calculation becomes a necessity f...

Multivariate Hawkes Processes for Large-scale Inference

In this paper, we present a framework for fitting multivariate Hawkes pr...

Regularized estimation for highly multivariate log Gaussian Cox processes

Statistical inference for highly multivariate point pattern data is chal...

Low-rank matrix denoising for count data using unbiased Kullback-Leibler risk estimation

This paper is concerned by the analysis of observations organized in a m...

A multi-resolution approximation via linear projection for large spatial datasets

Recent technical advances in collecting spatial data have been increasin...