• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    Spatial Statistics

    Spatial Statistics

    JournalISSN 2211-6753eISSN 2211-6753中科院 数学 2区

    年发文量

    研究主题

    论文(948)

    排序
    1Nonstationary Spatial Modeling and Estimation Using a Divide-and-conquer Approach
    Yung-Huei Chiou,Chun-Shu Chen,Hsin-Cheng Huang
    2026
    引用
    AI阅读
    加入学术空间
    2Structure Identification and Estimation of Geographically and Temporally Weighted Autoregressive Models Based on Neural Networks and Regularization Methods
    Geng Chen, Zhanjie Song, Shuo Zhang
    2026
    引用
    AI阅读
    加入学术空间
    3A Hierarchical Bayesian Geostatistical Model for Zero-Inflated and Extreme Spatial Data: Analysing Sardine Egg Density in Portugal
    Soraia Pereira,Raquel Menezes,Maria Manuel Angélico,Tiago Marques

    Modelling spatial datasets characterized by zero-inflation and extreme values presents significant challenges in statistical analysis. Such data structures frequently arise in ecological research, particularly in marine biology, and, if neglected in the modelling process, can yield biased estimates with potentially strong consequences for population management strategies. In this study, we analyse sardine egg density data collected during an annual campaign conducted by the Portuguese Institute for the Ocean and Atmosphere (IPMA), aiming to understand the spatial distribution of sardine egg density along the Portuguese coast. Our primary objectives include identifying the environmental variables that best explain egg presence, density, and extreme values, as well as making spatial prediction. To address these complexities, we propose a hierarchical Bayesian geostatistical Gamma-GP hurdle model that accommodates zero-inflation and heavy tails by combining a Bernoulli component for zeros, a truncated Gamma component for the central part of the distribution and, if supported by diagnostics, a Bernoulli component for the presence of extremes and a Generalized Pareto component for threshold exceedances. We implement this approach using the Stochastic Partial Differential Equation (SPDE) framework alongside Integrated Nested Laplace Approximation (INLA) for efficient Bayesian inference. Our results highlight how this integrated modelling strategy effectively accounts for the many zeros and extreme values in the data, and it is broadly applicable to similar ecological problems and other contexts involving zero-inflated or heavy-tailed spatial data.

    2026
    引用
    AI阅读
    加入学术空间
    4A Generalized Spatial Correlated Mean Component Model: Theory and Application to U.S. County Voting Data
    N.A. Cruz, J.D. Toloza-Delgado, O.O. Melo

    This paper introduces the generalized spatial correlated inverse mean component (GSCIMC), a flexible and computationally efficient framework for modeling spatial dependence in non-Gaussian data from the exponential family. We establish asymptotic properties of the proposed estimators, including consistency, asymptotic normality, and efficiency, and derive robust variance expressions that enable valid inference under heteroskedasticity or partial model misspecification. Through extensive simulation studies, we show that the GSCIMC estimator provides stable estimation, accurate inference, and reliable coverage across a wide range of spatial dependence structures and response distributions. An empirical analysis of U.S. county-level voting patterns in the 2020 presidential election illustrates the model’s ability to identify spatial spillover effects while maintaining an interpretable regression framework, the proposed framework provides a practical and theoretically grounded tool for analyzing binary, count, or skewed continuous spatial responses. An open-source implementation is available in the spatemR package, facilitating the application of GSCIMC across disciplines such as environmental science, epidemiology, and regional economics.

    2026
    引用
    AI阅读
    加入学术空间
    5A Recursive Framework for Online Changepoint Detection in Spatio-Temporal Processes
    Masoud Majidizadeh

    The detection of structural breaks in spatio-temporal processes is a fundamental task in fields ranging from climate science to epidemiology. State-of-the-art methods have demonstrated significant success in identifying such changepoints from complete historical datasets. However, these approaches are inherently offline (or retrospective), making them unsuitable for real-time monitoring where data arrives sequentially and timely detection is critical. This paper bridges this gap by introducing a computationally efficient online framework for temporal changepoint detection in complex spatio-temporal processes. Building upon a recently proposed Markovian likelihood approximation, a recursive updating scheme is derived for the likelihood ratio test statistic, augmented with a sliding window approximation to bound computational costs and enable constant-time updates per time step. Comprehensive simulation studies evaluate the framework’s in-control performance (via threshold calibration for target ARL0), out-of-control detection power (TPR and MDD for mean and covariance shifts), and scalability, showing statistical performance comparable to the offline counterpart and superior to baselines like multivariate CUSUM, with linear computational complexity. The practical utility of the proposed framework is showcased through an application to hourly PM2.5 air quality data from a network of 25 sensors in Northern California during 2020, successfully detecting near-real-time changes associated with COVID-19 lockdowns and wildfires, with low detection delays and efficient processing.

    2026
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 948 篇论文

    高被引作者

    作者引用发文
    Linna Li8761
    Michael Goodchild8761
    Yong Ge6949
    Alfred Stein59028
    Jinfeng Wang5153
    Finn Lindgren4906
    Binbo Gao4401
    Håvard Rue4226
    Jorge Mateu34528
    Daniel Simpson3343

    高产作者

    作者引用发文
    Alfred Stein59028
    Alan E. Gelfand29917
    Yunquan Song3714
    Denis Allard14112
    D'Urso Pierpaolo20412
    Christopher K. Wikle18710
    Inger Fabris-Rotelli179
    Daniel A. Griffith2239
    Marc G. Genton1819
    Vincenzina Vitale1149

    相关期刊

    Journal of applied statistics
    Journal of the Royal Statistical Society. Series C, Applied statistics
    Computational Statistics & Data Analysis
    Environmental and Ecological Statistics
    The annals of applied statistics
    International Statistical Review
    Environmetrics
    Journal of Agricultural, Biological and Environmental Statistics
    arXiv: Methodology
    arXiv: Applications