Chapter 17: Further Reading

Foundational Papers

Taki, T., & Hasegawa, J. (2000). Visualization of dominant region in team games and its application to teamwork analysis. Proceedings of Computer Graphics International, pp. 227--235. The pioneering paper applying Voronoi tessellations to team sports. Introduces the concept of dominant regions and demonstrates their utility for understanding team structure.
Kim, S. (2004). Voronoi Analysis of a Soccer Game. Nonlinear Analysis: Modelling and Control, 9(3), 233--240. Extends Voronoi analysis to full match data and introduces area-based metrics for evaluating territorial control.
Aurenhammer, F. (1991). Voronoi diagrams --- a survey of a fundamental geometric data structure. ACM Computing Surveys, 23(3), 345--405. The definitive survey of Voronoi diagram theory. Essential reading for understanding the mathematical foundations.

Fernandez, J., & Bornn, L. (2018). Wide Open Spaces: A statistical technique for measuring space creation in professional soccer. MIT Sloan Sports Analytics Conference. Introduces the Gaussian influence function and the concept of pitch control as a continuous probability surface. One of the most cited papers in modern soccer analytics.
Spearman, W. (2017). Beyond Expected Goals. MIT Sloan Sports Analytics Conference. Presents a physics-based model of pitch control using time-to- intercept calculations. The foundation of much of Liverpool FC's (via Second Spectrum) analytical framework.
Spearman, W. (2018). Physics-Based Modeling of Pass Probabilities in Soccer. MIT Sloan Sports Analytics Conference. Extends the time-to-intercept framework to model pass completion probability, integrating pitch control with event-level analysis.
Fernandez, J., & Bornn, L. (2021). SoccerMap: A Deep Learning Architecture for Visuo-Spatial Analysis in Soccer. ECML PKDD 2021. Uses convolutional neural networks to learn pitch control surfaces directly from tracking data, bypassing the need for hand-crafted influence functions.

Fernandez, J., Bornn, L., & Cervone, D. (2019). Decomposing the Immeasurable Sport: A deep learning expected possession value framework for soccer. MIT Sloan Sports Analytics Conference. Introduces expected possession value (EPV), which builds on pitch control to assign a goal-scoring probability to every moment of possession.
Power, P., Ruiz, H., Wei, X., & Lucey, P. (2017). Not All Passes Are Created Equal: Objectively Measuring the Risk and Reward of Passes in Soccer from Tracking Data. KDD. Demonstrates how spatial context (pitch control at origin and destination) affects pass value, providing a framework for evaluating passing in the context of spatial dominance.
Link, D., Lang, S., & Seidenschwarz, P. (2016). Real Time Quantification of Dangerousity in Football Using Spatiotemporal Tracking Data. PLOS ONE, 11(12), e0168768. One of the first papers to combine positional data with danger metrics, introducing the concept of "dangerousity" as a spatial measure.

Singh, K. (2019). Introducing Expected Threat (xT). Blog post, karun.in. The original formulation of expected threat as a Markov-chain-based positional value model. Foundational for understanding how spatial location translates to goal-scoring probability.
Rudd, S. (2011). A Framework for Tactical Analysis and Individual Offensive Production Assessment in Soccer Using Markov Chains. New England Symposium on Statistics in Sports. An early Markov chain approach to valuing pitch zones, predating the xT formulation but sharing the core insight.

Mead, T. (2023). Friends of Tracking: Data Science for Soccer. A practical guide to soccer analytics with extensive coverage of tracking data, pitch control, and spatial metrics. Companion code available on GitHub.
Sumpter, D. (2016). Soccermatics: Mathematical Adventures in the Beautiful Game. Bloomsbury. An accessible introduction to mathematical modelling in soccer, including spatial patterns, Voronoi diagrams, and network theory.
Anderson, C., & Sally, D. (2013). The Numbers Game: Why Everything You Know About Football Is Wrong. Penguin. A popular introduction to soccer analytics that covers spatial concepts at a high level.

Friends of Tracking GitHub --- github.com/Friends-of-Tracking-Data-Science Open-source implementations of pitch control models, Voronoi diagrams, and other spatial analytics tools. Includes Jupyter notebooks with step-by-step explanations.
Laurie Shaw's Pitch Control Tutorial --- github.com/Friends-of-Tracking-Data-Science/LaurieOnTracking A detailed Python implementation of Spearman's pitch control model with synthetic tracking data.
mplsoccer Documentation --- mplsoccer.readthedocs.io The standard Python library for soccer visualisation. Includes pitch plotting, heat-maps, Voronoi overlays, and arrow plots.
StatsBomb Open Data --- github.com/statsbomb/open-data Free event data with freeze-frame information (player positions at the moment of each event). Useful for approximating spatial analysis without full tracking data.

Javier Fernandez, "Wide Open Spaces" --- MIT SSAC 2018. The original conference presentation of the Gaussian influence model. Available on YouTube via the MIT Sloan Sports Analytics Conference channel.
William Spearman, "Beyond Expected Goals" --- MIT SSAC 2017. Spearman's presentation of the physics-based pitch control model. Available on YouTube.
Friends of Tracking Lecture Series --- YouTube playlist. A multi-part lecture series covering tracking data analysis, including Voronoi diagrams, pitch control, and expected possession value. Presented by Laurie Shaw, David Sumpter, and others.

Karun Singh, "Introducing Expected Threat (xT)" --- karun.in. The original blog post introducing the xT framework, with code and visualisations.
Sam Gregory, "Pitch Control and Off-Ball Scoring Opportunities" --- samgregory.dev. A practical walkthrough of implementing pitch control in Python and using it to evaluate off-ball positioning.
McKay Johns, "Voronoi Diagrams in Football" --- YouTube. A visual introduction to Voronoi diagrams in soccer with Python code examples.

For cutting-edge research, monitor these journals and conferences: