Spatial Statistics 2027: At the core of analytical intelligence

During the Spatial Statistics 2027 conference in Beijing (China), specific attention is given to the important and unprecented bridge between spatial statistics and analytical intelligence. It embeds predictive modelling, artificial intelligence, real-time decision support systems and many more.

We live in an era often described as the age of data. Every day, billions of observations are recorded from satellites, environmental sensors, mobile devices, social networks, transportation systems, healthcare infrastructures, and digital platforms. Much information from these data is inherently spatial, while every decision ultimately affects places, communities, and environments. Spatial statistics provides the scientific foundation and means for our understanding and interpretation. It equips us with rigorous methods to model spatial dependence, quantify uncertainty, detect patterns, predict future scenarios, and distinguish genuine signals from random variation. In the end, it transforms geographic information into analytical intelligence—the capacity to support decisions that are both data-driven, context-aware and scientifically sound.

Analytical intelligence encompasses predictive modelling, machine learning, artificial intelligence, digital twins, and real-time decision support systems. These technologies reach their full potential when grounded in robust statistical principles. Spatial statistics bridges between sophisticated algorithms and reliable inference, ensuring that increasingly powerful computational methods remain interpretable, reproducible, and trustworthy. The integration of spatial statistics with artificial intelligence represents one of the most exciting frontiers in contemporary analytical intelligence. Machine learning excels at discovering complex patterns, while spatial statistical models provide principled approaches for incorporating spatial dependence, quantifying uncertainty, and producing interpretable results. Together, they enable a new generation of intelligent analytical systems capable of addressing challenges that are simultaneously scientific, societal, and strategic.

Comments from delegates of the 6^th Spatial Statistics Conference

“High quality of content and well thought out schedule and time for discussion through on-site lunches with poster sessions.”

“Great atmosphere, very collaborative and collegial.”

“I got the opportunity to meet and interact with some renowned experts in spatial statistics whom I have read and referenced during my Ph.D. study.”

Our society, atmosphere and environment are dynamic, and are continuously changing at many scales of time and space. A recent rapid development in society concerns the emergence of AI.

AI is supported by large numbers of available data, requiring statistical methods to handle these. Simultaneously, in the spatial domain, a large and important collection of spatial statistical methods and domain knowledge are being developed to help address the demands of society. The number and variety of data sources are increasing with the advent of more and more satellite and aircraft sensors, ground stations, surveys, mobile devices, and internet sources, recording human, climatic and environmental processes. These spatial and spatio-temporal data require to be transformed into meaningful information and both spatial statistics and AI are complementary in achieving this.

Artificial Intelligence has its roots in computer science. In the past, it has resulted in artificial neural networks including the multi-layer perceptron, while more recently, we recognize how deep learning has resulted in the development of convolutional neural networks and the transformer. Now, natural language processing has brought about a profound shift in thinking and opened great opportunities for research.

Spatial statistics, with its roots in probability theory and stochastic processes, has much to bring to the AI table. Moreover, the development of Statistical Learning in a spatial context has built a bridge towards spatial big data.

At the dawn of AI, therefore, spatial statistics should play a major role in the development and application of AI and, at the same time, AI can benefit the development of spatial statistics.

Conference topics

Methods

Predictive modelling

• Space-time statistics: geostatistics, point patterns, estimation methods, large dimensions

• Causality in space and time

• Modeling and predicting of extremes

• Digital twins and spatial analytics

• Hierarchical spatial models

Artificial intelligence

• Hybrid AI and statistical models

• Spatial deep learning

• Spatial statistical learning

• Spatial machine learning

• Reinforcement learning in spatial systems

• Natural language processing for spatial challenges

• Neural networks in space

• Geospatial Artificial Intelligence (GeoAI)

Decision support systems

• Explainable AI for spatial decision-making

And more…

• Spatio/temporal modeling of points and objects

• Discrete spatial variation

• Spatial and spatio/temporal variability and dependence

• Stochastic geometry, tessellation, point processes, random sets

• Change-of-support problems

• Measurement error in spatial data

• Functional spatial data analysis

• Spatial compositional data analysis

• High-performance computing for large spatial datasets

Applications

Environment

• Environmental and climate applications

• Climate change modelling

• Environmental risk assessment

• Air pollution mapping

• Water resources management

• Forest monitoring

• Biodiversity and ecological modelling

• Wildfire prediction

• Coastal and marine spatial analysis

• Natural hazard assessment

• Disaster risk reduction and resilience

Health

• Spatial epidemiology

• Disease mapping

• Infectious disease surveillance

• Public health analytics

• Environmental health

• Pandemic modelling

Urban and Transport

• Smart cities

• Urban growth modelling

• Sustainable urban development

• Transportation and mobility analytics

• Traffic forecasting

And more…

• Land use and land cover modelling

• Housing market analysis

• Energy systems modelling

Deadlines

Abstract Submission Deadline: 29 January 2027

Author Notification Deadline: 25 March 2027

Author Registration Deadline: 23 April 2027

Early bird Registration Deadline: 23 April 2027

Supporting publication

Special Issue

More information coming soon.

Organizers

Co-Organizers

Related Conference

https://rss.org.uk/training-events/conference-2025/opens in new tab/window

Marketing Material

Spatial Statistics 2025 Conference 2pp A5 Flyer HRopens in new tab/window

Spatial Statistics 2025 Conference PPT Slidesopens in new tab/window

Spatial-Statistics-2025-ATTENDING-Banner-1200x628opens in new tab/window

Spatial-Statistics-2025-Banner-1200x628opens in new tab/window

Spatial-Statistics-2025-Email-Banner-619x88opens in new tab/window

Spatial-Statistics-2025-ERD-Banner-1200x628opens in new tab/window

Spatial-Statistics-2025-PRESENTING-Banner-1200x628opens in new tab/window

Spatial-Statistics-2025-REG-Banner-1200x628opens in new tab/window

Spatial-Statistics-2025-SPEAKING-Banner-1200x628opens in new tab/window

Previous Events

Spatial Statistics 2025: At the Dawn of AI

15-18 July 2025 | NH Leeuwenhoorst, Noordwijk, The Netherlands

Conference topics

Methods

Spatial deep learning

Spatial statistical learning

Neural networks in space

Large language models in space

Natural language processing for spatial challenges

Spatio/temporal modeling of points and objects

Causality in space and time

Modeling and predicting of extremes

Space-time statistics: geostatistics, point patterns, estimation methods, large dimensions

Discrete spatial variation

Spatial and spatio/temporal variability and dependence

Stochastic geometry, tessellation, point processes, random sets

Applications

Environment: soil, water, atmosphere

Interface of neural computing and spatial/spatio-temporal statistics

Climate system modeling and observations

Health e.g. epidemiology, geohealth and global health

Spatially-explicit ecological models

Plant and animal epidemiology

Quantifying the spatial extent of hazards and risk

Crime, poverty, liveability mapping

Spatial Statistics 2023: Climate and the Environment 18 - 21 July 2023 | University of Colorado, Boulder, USA

Conference topics

Methods

• 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

Applications

• 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

Spatial Statistics 2019: Towards Spatial Data Science 10 – 13 July 2019 | Sitges, Spain

Conference Topics

Methods

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

• New spatial data sources, e.g. social media, Google, citizen science, crowd source maps

• Stochastic geometry, tesselation, point processes, random sets

• Causal statistical modeling

• Trajectory/movement modeling

• Predictive modelling

• Spatial data quality and uncertainty

With these methods being applied in a range of relevant domains. For the theme of the conference, we particularly invite contributions in:

Applications

• Image analyses, e.g. satellite images

• Traffic and transport

• Global change

• Ecology, e.g. dispersion, migration, colonisation and invasion of species

• Plant and animal epidemiology, e.g. emerging epidemics

• Hazards, disasters and risks, e.g. outbreaks, risk mapping

• Crime and poverty mapping

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

• Spatial econometrics

Spatial Statistics: One world, one health 4-7 July 2017 | Lancaster University, UK

Conference Topics

• Space-time statistics

• Models for point processes

• Lattice models

• Geostatistics

• Copulas in space and time

• Spatial extremes

• Change-point analysis

• Estimation methods

• Issues of scale: upscaling and downscaling methodology

• Stochastic geometry, random sets and stereology

• Causal statistical modeling

• Image analysis (e.g. satellite sensor image time-series, DNA data, brain imaging)

• Predictive modelling

• Spatial data quality and uncertainty

• New spatial data sources (e.g. social media, Google, citizen science, crowd sourced data)

• Large dimensional big spatial data

With these methods being applied in a range of relevant domains. For the theme of the conference, we particularly invite contributions in:

• Statistical aspects of epidemiology

• Geo-Health and One Health

• Plant and animal diseases

• Health and Global change

• Zoonotic and vector-borne diseases (e.g. emerging epidemics)

• Hazards, disasters and risks (e.g. outbreaks, risk mapping)

• Ecology (e.g. dispersion, migration, colonisation and invasion of species)

• Spatial econometrics

Spatial Statistics Avignon: Emerging Patterns 9-12 June 2015 | Avignon, France

Conference Topics

• Space-time statistics (e.g. point patterns models, estimation methods, large dimensions, scale issues)

• Spatial data quality and uncertainty

• Parameter estimation in PDEs

• Stochastic geometry, tesselation, point processes, random sets

• Spatial econometrics

• New spatial data sources (e.g. big, data, social media, Google, citizen science, crowd source maps)

• Image analyses (e.g. satellite images time series, DNA data, nano particles, nervous systems)

• Predictive modelling

• Tipping points (e.g. sea-level rise, socio-economic shifts)

• Hazards, disasters and risks (e.g. tsunamis, earthquakes, landslides, air pollution levels)

• Global change (e.g. stochastic weather generators)

• Health, medical and epidemiology

• Plant and animal epidemiology (emerging epidemics)

• Ecology (e.g. dispersion, migration, colonisation and invasion of species)

Spatial Statistics 2013 Conference

Spatial Statistics for Mapping the Environment (2011)