A data science journey through the analysis of spatio-temporal point pattern data. Spatial Data Handling and Modelling Using R.

The main aim of the course is to make students familiar with the challenges of spatio-temporal data analytics. The course is divided into two parts, both taught by esteemed visiting professors. First one will be conducted by prof. Jorge Mateu and will focus on spatio-temporal point pattern data, the second one will be conducted by prof. Chris Brunsdon and will go in depth with the description of variety of tools for spatial data handling in R and modelling. Course will be coordinated by an onsite lecturer – mgr Maria Kubara, while the whole class material will be delivered by the visiting professors.

The course will be taught in an intensive workshop setting in two weeks in November. The students are asked to bring their own laptops with R v.3.3.0+ and RStudio Desktop installed in order to take active part in the practical live code exercises discussed during the class.

---------

The first part of the course:

Instructor:

Prof. Jorge Mateu

Department of Mathematics

University Jaume I of Castellon, Spain

mateu@uji.es

https://www3.uji.es/~mateu/

The list of course topics:

Important: scope of the course will be adapted to the needs and interests of the students.

1. Introduction and motivation. Real data examples with a focus on infectious diseases and crime

2. Some basic technical background. Spatio-temporal point process statistics

3. Non-parametric intensity estimation for spatial point patterns with R

4. Poisson, and mecanistic versus empirical models

5. A deeper look at mechanistic spatio-temporal modeling frameworks

6. Spatio-temporal point process models based on neural kernels

7. Semi-parametric spatio-temporal Hawkes-type point processes with periodic background

8. A deeper look at empirical mdels through log-Gaussian Cox processes

9. Origin-destination point patterns

10. Reducing dimensionality through barycenters

11. Velocities for spatial growth models

12. Stochastic integro-differential equations

13. Detecting focusses and generators

14. Statistical learning for spatio-temporal point processes

---------

The second part of the course:

Instructor:

Prof. Christopher Brunsdon

Director of the National Centre for Geocomputation

Maynooth University, Ireland

Christopher.Brunsdon@mu.ie

The list of course topics:

1. Spatial Data in R

2. Some spatial algorithms

1. Trip modelling

2. Location allocation models

4. Spatial regression in R

5. Markov random field models

6. Bayesian Approaches

7. Real world computing issues

8. Challenges for spatial data analytics

Both parts of the course will be complementary and will provide the students with a broad overview of the spatial data and spatio-temporal data analysis issues and their applications in R.

- own materials

Literature:

a) General theory

- GONZALEZ, J.A., RODRIGUEZ-CORTES, F.J., CRONIE, O. & MATEU, J. (2016). Spatio-temporal point process statistics: A review. Spatial Statistics, 18, 505–544.

- GHORBANI, M., CRONIE, O., MATEU, J. & YU, J. (2021). Functional marked point processes: A natural structure to unify spatio-temporal frameworks and to analyse dependent functional data. Test, 30, 529-568.

- GILARDI, A., MATEU, J., BORGONI, R. & LOVELACE, R. (2022). Multivariate hierarchical analysis of car crashes data considering a spatial network lattice. Journal of the Royal Statistical Society A, 185 (3), 1150-1177.

- ZHUANG, J. & MATEU, J. (2019). A semi-parametric spatiotemporal Hawkes-type point process model with periodic background for crime data. Journal of the Royal Statistical Society A, 182 (3), 919-942.

b) Crime data analysis

- PAYARES-GARCIA, D., PLATERO, J. & MATEU, J. (2023). A dynamic spatio-temporal stochastic modeling approach of emergency calls in an urban context. Mathematics, 11, 1052. doi: 10.3390/math11041052.

- ESCUDERO, I., ANGULO, J.M. & MATEU, J. (2022). A spatially correlated model with autoregressive conditionally heteroskedastic structure for counts of crimes. Entropy, 24, 892.

- BRIZ, A., MATEU, J. & MONTES, F. (2022). Identifying crime generators and spatially overlapping high-risk areas through a non-linear model: a comparison between three cities of the Valencian region (Spain). Statistica Neerlandica, 76 (1), 97-120.

- BRIZ, A., MATEU, J. & MONTES, F. (2022). Modeling the influence of places on crime risk through non-linear effects: a comparison with risk terrain modeling. Applied Spatial Analysis and Policy, 15, 507-527.

- BRIZ, A., MATEU, J. & MONTES, F. (2023). Modeling accident risk at the road level through zero-inflated negative binomial models: a case study of multiple road networks. Spatial Statistics. doi: 10.1016/j.spasta.2021.100503.

- BRIZ, A., IFTIMI, A., MATEU, J. & ROMERO, C. (2023). A mechanistic spatio-temporal modeling of COVID-19 data. Biometrical Journal. doi: 10.1002/bimj.202100318.

- BRIZ, A. & MATEU, J. (2023). A mechanistic bivariate point process model for crime pattern analysis. Stat. doi: 10.1002/sta4.537.

- SOSA, J., BRIZ-REDON, A., FLORES, M., ABRIL, M. & MATEU, J. (2023). A spatio-temporal multinomial model of firearm death in Ecuador. Spatial Statistics. doi: 10.1016/j.spasta.2023.100738.

- SHIROTA, S., GELFAND, A.E. & MATEU, J. (2023). Analyzing car thefts and recoveries with connections to modeling origin-destination point patterns. Spatial Statistics. doi: 10.1016/ j.spasta.2020.100440.

c) Statistical learning for spatio-temporal point processes

- JALILIAN, A. & MATEU, J. (2023). Assessing similarities between spatial point patterns with a Siamese Neural Network discriminant model. Advances in Data Analysis and Classification. doi: 10.1007/s11634-021-00485-0.

- NIRAULA, P., MATEU, J. & CHAUDHURI, S. (2023). A Bayesian machine learning approach for spatio-temporal prediction of COVID-19 cases. Stochastic Environmental Research and Risk Assessment. doi: 10.21203/rs.3.rs-636809/v1.

- MATEU, J. & JALILIAN, A. (2023). Spatial point processes and neural networks: a convenient couple. Spatial Statistics. doi: 10.1016/j.spasta.2022.100644.

- Dong, Z., Zhu, S., Xie, Y., Mateu, J. and Rodriguez-Cortes, F. (2023). Non-stationary spatio-temporal point process modeling forhigh-resolution COVID-19 data. Journal of the Royal Statistical Society C. doi: 10.1093/jrsssc/qlad013.

- MOHLER, G. & MATEU, J. (2023). Second order preserving point process permutations. Stat. doi: 10.1002/sta4.558.

- PAYARES, E., MATEU, J. & SCHICK, W. (2023). Spatially informed Bayesian neural network for neurodegenerative diseases classification. Statistics in Medicine. doi: 10.1002/sim.9604.

- RODRIGUES, A., GONZALEZ, J.A. & MATEU, J. (2023). A conditional machine learning classification approach for spatio-temporal risk assessment of crime data. Stochastic Environmental Research and Risk Assessment. doi: 10.1007/s00477-023-02420-5.

d) Spatial data analysis issues

- BRUNSDON, Chris; COMBER, Lex. An introduction to R for spatial analysis and mapping. Sage, 2014.

- COMBER, Lex; BRUNSDON, Chris. Geographical data science and spatial data analysis: an introduction in R. Sage, 2020.

- https://data.cdrc.ac.uk/dataset/introduction-spatial-data-analysis-and-visualisation-r

After this course the student:

- is familiar with the challenges of spatial point data handlings

- recognizes the challenges of spatio-temporal data analysis

- knows how to process spatial data in R

- can apply a broad set of models for spatial data handling in R

- is aware of the computation issues related with spatio-temporal data handling

K_U02, K_U05

The final grade will be based on the exam result (one assessment for both parts of the course).