Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
The Second Competition on Spatial Statistics for Large Datasets
Published in Journal of Data Science, 2022
This paper describes the second ExaGeoStat competition on spatial statistics for large datasets and assesses the submitted methods.
Reshaping Geostatistical Modeling and Prediction for Extreme-Scale Environmental Applications
Published in SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, 2022
This paper extends space-time geostatistical modeling using mixed-precision and low-rank algebraic approximations at extreme scale.
Spatio-temporal DeepKriging for interpolation and probabilistic forecasting
Published in Spatial Statistics, 2023
This paper devises a novel nonparametric approach for prediction of complex spatio-temporal phenomena.
Deep Neural Networks for Large-scale Complex Spatial and Spatio-temporal Processes
Published in PhD Dissertation, King Abdullah University of Science and Technology (KAUST), 2024
PhD dissertation developing DNN-based methods for large-scale spatial and spatio-temporal processes.
Unrolled Creative Adversarial Network For Generating Novel Musical Pieces
Published in arXiv preprint arXiv:2501.00452, 2024
This paper extends Creative Adversarial Networks to music generation and introduces unrolled CAN to address mode collapse.
Exploring the Efficacy of Statistical and Deep Learning Methods for Large Spatial Datasets: A Case Study
Published in Journal of Agricultural, Biological and Environmental Statistics (JABES), 2025
This paper compares statistical and deep learning approaches for large spatial datasets, motivated by the KAUST Competition on Large Spatial Datasets 2023.
Efficient Large-scale Nonstationary Spatial Covariance function estimation using Convolutional Neural Networks
Published in Journal of Computational and Graphical Statistics (JCGS), 2025
This paper provides a data driven scalable approach for fitting Nonstationary Matern covariance for large datasets.
Bivariate DeepKriging for Large-scale Spatial Interpolation of Wind Fields
Published in Technometrics, 2025
In this paper DeepKriging has been extended to bivariate spatial processes, incorporating connections to the Linear Model of Coregionalization.
Modeling nonstationary spatial processes with normalizing flows
Published in arXiv preprint arXiv:2509.12884, 2025
This paper models nonstationary, anisotropic spatial processes using neural autoregressive flows as spatial warping functions.
Spatio-temporal DeepKriging in PyTorch: A Supplementary Application to Precipitation Data for Interpolation and Probabilistic Forecasting
Published in arXiv preprint arXiv:2509.12708, 2025
A PyTorch implementation of Spatio-temporal DeepKriging applied to European precipitation data.
Deep classifier kriging for probabilistic spatial prediction of air quality index
Published in arXiv preprint arXiv:2512.23474, 2025
This paper proposes deep classifier kriging (DCK), a distribution-free deep learning framework for probabilistic spatial prediction with data fusion.
Spatio-temporal modeling and forecasting with Fourier neural operators
Published in Technometrics, 2026
This paper uses Fourier neural operators (FNOs) to construct statistical dynamical spatio-temporal models for forecasting.
talks
Presentation on Spatio-temporal DeepKriging for interpolation and probabilistic forecasting
Published:
Spatio-temporal modeling and forecasting with Fourier neural operators
Published:
Authors: Pratik Nag, Andrew Zammit-Mangion, Noel Cressie, Sumeetpal Singh
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.