Skip to main content

Unfortunately we don't fully support your browser. If you have the option to, please upgrade to a newer version or use Mozilla Firefox, Microsoft Edge, Google Chrome, or Safari 14 or newer. If you are unable to, and need support, please send us your feedback.

Publish with us


Submit abstract

The deadline for submission of abstracts has passed.

You can submit as many abstracts to the conference for review as you would like. If, after the review by the committee, you have more than one paper accepted for the conference, you will need to register to attend, and pay an additional paper fee for each additional paper (i.e., for the 2nd, 3rd, 4th papers – not the 1st).    Please note this is for papers that you are the presenting author of, not papers that you are co-author of.

Successfully submitted abstracts will be acknowledged with an electronic receipt including an abstract reference number, which should be quoted in all correspondence. Allow at least 2 hours for your receipt to be returned to you. Once the paper is accepted, at least one of the authors must register for the conference and present the paper at the conference.

Abstracts of all accepted contributions will be included within the online abstract system which will be distributed to all registered conference participants.

For revisions or queries regarding papers already submitted:

If you do not receive acknowledgement for your abstract submission or you wish to make any essential revisions to an abstract already submitted, please DO NOT RESUBMIT your abstract, as this may lead to duplication. Please contact the Conference Content Executiveopens in new tab/window (Please do not email credit card information under any circumstances) with details of any revisions or queries. Please quote your reference number if you have one.

Conference topics


  • Space-time statistics, e.g. geostatistics, point patterns, estimation methods, large dimensions

  • Spatial deep learning

  • Inverse modeling

  • Modeling of extremes

  • Stochastic geometry, tesselation, point processes, random sets

  • Causal statistical modeling

  • Trajectory/movement modeling


  • Climate system modeling and observations

  • Spatially-Explicit Ecological Models

  • Health e.g. epidemiology, geohealth and global health

  • Air, Water and Soil spatio-temporal variability

  • Plant and animal epidemiology

  • Quantifying the spatial extent of hazards and risk

  • Crime and poverty mapping

  • Space/time econometrics

  • Interface of Neural Computing and Spatial/Spatio-Temporal Statistics

  • Inferring Movement and Behavior from Telemetry

Pre-conference workshops

Workshop 1

An introduction to modern challenges in spatial statistics

William Kleiber, University of Colorado, USA Douglas Nychka, Colorado School of Mines, Golden, USA Christopher K. Wikle, University of Missouri (MU), USA

Half-day workshop Date: Tuesday July 18, 2023 Time: 8:30–12:30

This half-day workshop covers three topics of great importance to the current practice of spatial statistics: computation for large spatial datasets, multivariate spatial data, and spatio-temporal data.

Some of the most interesting and important spatial data sets are large. Their size makes analysis challenging because standard spatial methods “break” when confronted with numbers of spatial locations beyond several thousand. An alternative is to consider approximate spatial models that reduce the dimension of the computation. This can be done in the simplest way through fixed rank Kriging (FRK) or more model-based with a predictive process approach. However, by exploiting sparsity in the precision matrix of a spatial process one can fit Gaussian processes without reducing the degrees of freedom in the predictions. Moreover, these methods can be paired with strategies for fast prediction and conditional simulation on regular grids to create practical tools for data analysis. This workshop will develop these ideas with a view towards their accuracy in approximating the exact spatial analysis and are useful from either a likelihood or Bayesian perspective. Examples will be given using several R packages that showcase how these apply to some large environmental data sets.

The cost of the workshop is as follows:

Half-day workshop registration - Student


Half-day workshop registration - Standard


Please register for the workshop via the conference registration system.

Workshop 2

spmodel: Spatial statistical modelling and prediction in R

Matt Higham, Assistant Professor of Statistics, St. Lawrence University Michael Dumelle, United States Environmental Protection Agency, USA 

Half-day workshop Date: Tuesday July 18, 2023 Time: 13:00–17:00

The spmodel R package can be used to fit, summarize, and predict for a variety of spatial statistical models for both point-referenced and areal spatial data. What distinguishes spmodel from many other R packages for modelling spatial data is (1) a syntactic structure similar to the syntactic structure of base R functions lm() and glm() that makes spmodel relatively easy to learn, (2) the breadth of options that give the user a high amount of control over the model being fit, and (3) compatibility with other modern R packages like broom and sf. By the end of this workshop, participants can expect to be able to use spmodel to fit spatial linear models for point-referenced and areal (lattice) data, make predictions for unobserved spatial locations, fit anisotropic models for point-referenced data, fit spatial models with additional non-spatial random effects, fit generalized linear models for spatial data, and use big data methods to analyse large spatial data sets.

More information on spmodel can be found at in new tab/window.

The cost of the workshop is as follows:

Half-day workshop registration - Student


Half-day workshop registration - Standard


Please register for the workshop via the conference registration system.

Workshop 3

Towards cloud-native spatial statistics

Miguel Alvarez Garcia, Carto, Spain  Giulia Carella, Carto, Spain

Half-day workshop Date: Tuesday July 18, 2023 Time: 8:30–12:30

In the cloud-native era Spatial Data Science at scale still represents a big challenge. Although leading data warehouses already offer some level of support for spatial data, they lack some of the advanced analytical capabilities required for many geospatial use cases. CARTO Analytics Toolboxopens in new tab/window extends the geospatial capabilities of the most popular cloud data warehouses using spatial SQL with more than 130 advanced spatial functions. In this workshop we will guide you through the key developments in our toolbox: from how you can use spatial indexes to combine spatial data at scale, to analyze and model spatial patterns and processes, and to visualize interactively large data volumes both from vector and raster sources.  Specifically, you will learn, using our trial account, to:

  • Analyze the spatial patterns of simulated forest fires in California by identifying spatial clusters and outliers and assess overall patterns of clustering or dispersion

  • Select the relevant covariates from CARTO Spatial Data Catalogopens in new tab/window and generate smoothed fields using a Markov Random Field smoothing

  • Model the burned area from a set of both environmental and human-related covariates by assessing for spatial non-stationarity in their relationship with the burned area, by comparing different models and estimating the degree of spatial dependence in the residuals

  • Derive a spatial mapping of the burned area by estimating the area of applicability of the model for different future scenarios of the climate-related covariates

The cost of the workshop is as follows:

Half-day workshop registration - Student


Half-day workshop registration - Standard


Please register for the workshop via the conference registration system.

Workshop 4

Poisson Cokriging: Geostatistical Modelling of Correlated Diseases

David Payares Garcia and Frank Osei University of Twente, the Netherlands

Half-day workshop 13:00-17:00pm

Co-occurrence of diseases in populations is a commonly observed pattern in epidemiological studies. Infections rarely occur in isolation, and given their multifactorial nature, two or more distinct conditions can affect the same population simultaneously. However, understanding the mechanisms that drive these scenarios are challenging, especially in health population-level analysis as data collection, anonymisation and processing steps results in noisy, sparse and scarce spatial data. Geostatistics provides an attractive framework for modelling spatial disease data, offering capabilities such as interpolation, high-resolution mapping, and denoising. This workshop aims to provide participants with a comprehensive understanding of Poisson cokriging as a geostatistical method for predicting and denoising correlated disease counts, using the R programming language. Participants will gain insights into the following key questions:

  1. How can we spatially model the interaction between two diseases using aggregated spatial count data?

  2. How can we predict disease rates at unsampled locations by leveraging auxiliary data from a correlated disease?

  3. How can we filter disease rates based on spatial autocorrelation and cross-correlation to better understand underlying disease risk within a population?

  4. How can we generate and interpret smoothed maps of bivariate disease risks using Poisson cokriging?

  5. How can we effectively utilize R to leverage the capabilities of the Poisson cokriging model in disease analysis?

Throughout the workshop, participants will engage in practical exercises, working with real-world datasets to gain hands-on experience in implementing Poisson cokriging. The workshop will cover various aspects, including data pre-processing, model specification, parameter estimation, prediction, and interpretation of results. Emphasis will be placed on understanding the geostatistical concepts underlying Poisson cokriging and its practical application in studying correlated diseases.

By the end of the workshop, participants will be equipped with the knowledge and skills to apply Poisson cokriging in their own research or public health practice. The workshop aims to empower participants to effectively model and analyse the spatial interaction of diseases, ultimately contributing to enhanced understanding and informed decision-making in disease surveillance and control efforts.

The cost of the workshop is as follows:

Half-day workshop registration - Student


Half-day workshop registration - Standard


Please register for the workshop via the conference registration system.