Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes

Multivariate spatio-temporal point patterns have become increasingly common due to the advancement of technology for massive data collection. Parameter estimation is vital for understanding the distributional patterns within such data. However, performing estimation using a parametric approach on mu...

Full description

Saved in:
Bibliographic Details
Main Authors: Achmad Choiruddin, Ekky Rino Fajar Sakti, Tintrim Dwi Ary Widhianingsih, Jorge Mateu, Kartika Fithriasari
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11005449/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467741722902528
author Achmad Choiruddin
Ekky Rino Fajar Sakti
Tintrim Dwi Ary Widhianingsih
Jorge Mateu
Kartika Fithriasari
author_facet Achmad Choiruddin
Ekky Rino Fajar Sakti
Tintrim Dwi Ary Widhianingsih
Jorge Mateu
Kartika Fithriasari
author_sort Achmad Choiruddin
collection DOAJ
description Multivariate spatio-temporal point patterns have become increasingly common due to the advancement of technology for massive data collection. Parameter estimation is vital for understanding the distributional patterns within such data. However, performing estimation using a parametric approach on multivariate spatio-temporal point pattern data is challenging due to the curse of dimensionality, making parametric estimation increasingly difficult as data dimensionality grows. Deep learning offers a promising alternative due to its ability to model complex nonlinear patterns in large datasets. Despite limited applications in multivariate point pattern analysis, this study aims to introduce deep learning as a tool for parameter estimation of the multivariate spatio-temporal log-Gaussian Cox Process (LGCP) model. We employ the concept of probabilistic deep learning, ensuring that each estimated parameter follows a certain distribution that aligns with its assumption. We assess our model performance via a simulation study, and analyze the highly multivariate spatio-temporal point pattern data of Barro Colorado Island (BCI). Both the simulation study and application demonstrate our model effectiveness over previous approaches to handle highly multivariate point pattern data.
format Article
id doaj-art-133b13edfec54fa9816271eb61a7daf5
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-133b13edfec54fa9816271eb61a7daf52025-08-20T03:26:05ZengIEEEIEEE Access2169-35362025-01-0113947619477610.1109/ACCESS.2025.357047611005449Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox ProcessesAchmad Choiruddin0https://orcid.org/0000-0003-2568-2274Ekky Rino Fajar Sakti1https://orcid.org/0009-0006-2777-3566Tintrim Dwi Ary Widhianingsih2https://orcid.org/0000-0003-2585-6895Jorge Mateu3https://orcid.org/0000-0002-2868-7604Kartika Fithriasari4Department of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaDepartment of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaDepartment of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaDepartment of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaDepartment of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaMultivariate spatio-temporal point patterns have become increasingly common due to the advancement of technology for massive data collection. Parameter estimation is vital for understanding the distributional patterns within such data. However, performing estimation using a parametric approach on multivariate spatio-temporal point pattern data is challenging due to the curse of dimensionality, making parametric estimation increasingly difficult as data dimensionality grows. Deep learning offers a promising alternative due to its ability to model complex nonlinear patterns in large datasets. Despite limited applications in multivariate point pattern analysis, this study aims to introduce deep learning as a tool for parameter estimation of the multivariate spatio-temporal log-Gaussian Cox Process (LGCP) model. We employ the concept of probabilistic deep learning, ensuring that each estimated parameter follows a certain distribution that aligns with its assumption. We assess our model performance via a simulation study, and analyze the highly multivariate spatio-temporal point pattern data of Barro Colorado Island (BCI). Both the simulation study and application demonstrate our model effectiveness over previous approaches to handle highly multivariate point pattern data.https://ieeexplore.ieee.org/document/11005449/Big datadeep learningLGCPmultivariate point patternneural network
spellingShingle Achmad Choiruddin
Ekky Rino Fajar Sakti
Tintrim Dwi Ary Widhianingsih
Jorge Mateu
Kartika Fithriasari
Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes
IEEE Access
Big data
deep learning
LGCP
multivariate point pattern
neural network
title Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes
title_full Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes
title_fullStr Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes
title_full_unstemmed Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes
title_short Probabilistic Deep Learning for Highly Multivariate Spatio-Temporal Log-Gaussian Cox Processes
title_sort probabilistic deep learning for highly multivariate spatio temporal log gaussian cox processes
topic Big data
deep learning
LGCP
multivariate point pattern
neural network
url https://ieeexplore.ieee.org/document/11005449/
work_keys_str_mv AT achmadchoiruddin probabilisticdeeplearningforhighlymultivariatespatiotemporalloggaussiancoxprocesses
AT ekkyrinofajarsakti probabilisticdeeplearningforhighlymultivariatespatiotemporalloggaussiancoxprocesses
AT tintrimdwiarywidhianingsih probabilisticdeeplearningforhighlymultivariatespatiotemporalloggaussiancoxprocesses
AT jorgemateu probabilisticdeeplearningforhighlymultivariatespatiotemporalloggaussiancoxprocesses
AT kartikafithriasari probabilisticdeeplearningforhighlymultivariatespatiotemporalloggaussiancoxprocesses