Scalable spatio-temporal smoothing via hierarchical sparse Cholesky decomposition

被引:4
|
作者
Jurek, Marcin [1 ]
Katzfuss, Matthias [2 ]
机构
[1] Univ Texas Austin, Dept Stat & Data Sci, Austin, TX 78712 USA
[2] Texas A&M Univ, Dept Stat, College Stn, TX 77843 USA
基金
美国国家航空航天局; 美国国家科学基金会;
关键词
data assimilation; smoothing; spatio-temporal statistics; state-space model; Vecchia approximation;
D O I
10.1002/env.2757
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
We propose an approximation to the forward filter backward sampler (FFBS) algorithm for large-scale spatio-temporal smoothing. FFBS is commonly used in Bayesian statistics when working with linear Gaussian state-space models, but it requires inverting covariance matrices which have the size of the latent state vector. The computational burden associated with this operation effectively prohibits its applications in high-dimensional settings. We propose a scalable spatio-temporal FFBS approach based on the hierarchical Vecchia approximation of Gaussian processes, which has been previously successfully used in spatial statistics. On simulated and real data, our approach outperformed a low-rank FFBS approximation.
引用
收藏
页数:15
相关论文
共 50 条
  • [41] SPATIO-TEMPORAL ALTIMETER WAVEFORM RETRACKING VIA SPARSE REPRESENTATION AND CONDITIONAL RANDOM FIELDS
    Roscher, Ribana
    Uebbing, Bernd
    Kusche, Juergen
    2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 1234 - 1237
  • [42] Sparse Spatio-temporal Inference of Electromagnetic Brain Sources
    Stahlhut, Carsten
    Attias, Hagai T.
    Wipf, David
    Hansen, Lars K.
    Nagarajan, Srikantan S.
    MACHINE LEARNING IN MEDICAL IMAGING, 2010, 6357 : 157 - +
  • [43] Non-parametric smoothing of spatio-temporal point processes
    Grillenzoni, C
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2005, 128 (01) : 61 - 78
  • [44] Smoothing spatio-temporal data with complex missing data patterns
    Arnone, Eleonora
    Sangalli, Laura M.
    Vicini, Andrea
    STATISTICAL MODELLING, 2023, 23 (04) : 327 - 356
  • [45] AN ADDITIVE MODEL FOR SPATIO-TEMPORAL SMOOTHING OF CANCER MORTALITY RATES
    White, Gentry
    Sun, Dongchu
    Schootman, Mario
    IRANIAN JOURNAL OF MATHEMATICAL SCIENCES AND INFORMATICS, 2007, 2 (01): : 55 - 70
  • [46] Adaptive kernel smoothing regression for spatio-temporal environmental datasets
    Pouzols, Federico Montesino
    Lendasse, Amaury
    NEUROCOMPUTING, 2012, 90 : 59 - 65
  • [47] HT-STNet: a hierarchical Tucker decomposition and spatio-temporal LSTM network for accurate and efficient shared mobility demand forecasting on sparse data
    Yan, Hongyu
    Li, Jianbo
    Chu, Benjia
    Xu, Zhihao
    APPLIED INTELLIGENCE, 2025, 55 (07)
  • [48] Estimation of the Covariance Matrix in Hierarchical Bayesian Spatio-Temporal Modeling via Dimension Expansion
    Sun, Bin
    Wu, Yuehua
    ENTROPY, 2022, 24 (04)
  • [49] Assessing the Spatial and Spatio-Temporal Distribution of Forest Species via Bayesian Hierarchical Modeling
    Rodriguez de Rivera, Oscar
    Lopez-Quilez, Antonio
    Blangiardo, Marta
    FORESTS, 2018, 9 (09):
  • [50] Spatio-temporal hierarchical MLP network for traffic forecasting
    Qin, Yanjun
    Luo, Haiyong
    Zhao, Fang
    Fang, Yuchen
    Tao, Xiaoming
    Wang, Chenxing
    INFORMATION SCIENCES, 2023, 632 : 543 - 554