Social sciences · OECD FoS 3.3 · China MoE 0403 体育学
Sports science
体育学
L1Assistive → Steady ↓ from L2 Score 1.45 · Last reviewed 2026-10-22 · Next review 2027-01-19
BIGGEST BREAKTHROUGH 2024-03-19 AI · majorField · major
TacticAI: AI assistant for football tactics (Nat. Commun.) ↗
Liverpool collaboration; experts preferred suggestions 90% of the time
Why this level
Lowered to L1: AI in sport is mainly tracking, video analysis and officiating aids (e.g. semi-automated offside at the 2022 World Cup); AI-key research is limited to a few tools such as TacticAI (Nat. Commun. 2024).
↓ L2 → L1
S = 0.30·method + 0.35·discovery + 0.25·adoption + 0.10·education (education scores 0 when there is no evidence; if empty, the other weights are renormalised)
Sources
- nature.com/articles/s41467-024-45965-x
- inside.fifa.com/innovation/media-releases/semi-automated-offside-technology-to-be-used-at-fifa-world-cup-2022-tm
Composite 0.75–1.49: AI is an aid in parts of research or practice, with cases or surveys, but no recognised AI-key result. All levels →
Research directions
Tactical analysisMotion capture & biomechanicsInjury prediction
Papers
- Machine Learning Model Development and Evaluation for Non-contact Lower Limb Injury Risk Prediction in Elite Male Rugby Union: A Multi-team, Multi-season Analysis
AI: GNSS load, wellness and screening data across five model types. Field: a rare multi-team negative result showing AI injury prediction is far from usable — key evidence for keeping sports science at L1
2026-08-26 · Sports Medicine - Open
- TacticAI: an AI assistant for football tactics
Liverpool collaboration; experts preferred suggestions 90% of the time
2024-03-19 · Nature Communications
- Explainable AI for Sport Scientists
A chapter on explainable AI for sport science in performance analysis, injury prevention and athlete management.
2026-10-20 · OpenAlex · Routledge eBooks · Michal Bozděch
- Cross-Platform AI Modeling in Sports Science
Uses neural-network regression on relative performance indicators to model professional tennis prize money.
2026-10-20 · OpenAlex · Routledge eBooks · Michal Bozděch
- Predicting Passing-Play Outcomes in American Football: A Comparative Study of Traditional Machine Learning Algorithms and Fine-Tuned Large Language Models
Compares classic ML and a LoRA-tuned Llama 3 on 100 NFL games; SVM best (MAE ≈ 7 yards).
2026-10-19 · OpenAlex · Applied Science and Innovative Research · Tianjian (Jason) Wang
- AI feedback does not motivate by itself: a motivational-meaning model for university physical education
A model of how university PE learners interpret AI movement feedback.
2026-10-19 · OpenAlex · Frontiers in Psychology · Xiangyu Wang, Yongwei Wang
- Determining the Level of Reaction to a Moving Object in Combat Sports Athletes Using a Composite Index and Machine Learning: A Cross-Sectional Methodological Study
Composite index and ML classification of moving-object reaction in 312 combat-sport athletes.
2026-10-18 · OpenAlex · Journal of Functional Morphology and Kinesiology · Vyacheslav Romanenko, Y. Tropin, Rashid Matkarimov, Georgiy Korobeynikov
- Event Detection in Table Tennis Videos using 2D Keypoints
EventNet detects frame-accurate table-tennis events from 2D keypoints.
2026-10-17 · OpenAlex · ? · Rainer W. Lienhart, Daniel Kienzle, Shin’ichi Satoh, Anastasiia Bilinska
- Machine Learning for Injury Risk Prediction and Prevention in Athletics: A Data Driven Framework Integrating Wearable Sensor Metrics, Neuromuscular Screening, and Ensemble Learning for Prospective Injury Surveillance in Collegiate Athletes
Ensemble ML with wearable and screening data to predict non-contact injuries in collegiate athletes.
2026-10-17 · OpenAlex · Zenodo (CERN European Organization for Nuclear Research) · Sambit Bhattacharjee, Sagnik Bhattacharjee, Pulen Das
- Exploring foot pressure patterns for skiing experience classification in a simulator-based environment
A YOLO11 classifier infers skiing proficiency from plantar pressure in a simulator (27 participants).
2026-10-16 · OpenAlex · Scientific Reports · Shigeharu Ono, Ryosuke Atsumi, Hideaki Kanai, Hideki Koike
- From arXiv, bioRxiv, medRxiv and OpenAlex (last ~30 days); summaries written by AIMap from the abstract.
Milestones 10
Big glowing nodes are leaps: AI leap cool · Field leap warm · double ring = both
-
Deployment
ABA League refereeing department begins using AI to analyse officiating each round, linking key-play assessments with official stats and play-by-playAI: summarises last-two-minute fouls, recurring key-play themes and development priorities. Field: AI extends from assisting calls to reviewing officiating; no individual ratings or sanctions
ABA League -
Deployment
NBA tests Wilson sensor-equipped smart basketballs in preseason to gather data for future real-time officiating (research only), plus referee wrist wearablesAI: paired with Hawk-Eye tracking, aimed at automating objective calls such as out-of-bounds. Field: officiating automation reaches on-court testing, explicitly not used for calls this season
NBA.com (AP) -
Policy
IOC launches its Trustworthy AI Framework for the Olympic Movement with Deloitte: seven principles and a three-step self-assessment checklistAI: turns athlete-data protection, fair play and transparency into a checklist. Field: first common AI-governance tool for the whole Olympic Movement after the 2024 Olympic AI Agenda
Inside The Games / IOC -
Industry
RSC Anderlecht adopts MyGamePlan AI opponent analysisClub-level adoption
MyGamePlanVendor claim -
Paper
Multi-team, multi-season study of 129 elite Irish rugby players: ML injury-risk models perform poorly (best CatBoost ROC AUC 0.66, precision 0.013) (Sports Medicine – Open)AI: GNSS load, wellness and screening data across five model types. Field: a rare multi-team negative result showing AI injury prediction is far from usable — key evidence for keeping sports science at L1
Sports Medicine – Open -
Deployment
FIFA details World Cup 2026 tech: advanced semi-automated offside alerts go straight to on-field officials, AI-enabled 3D player avatars, and the generative-AI assistant Football AI Pro for all 48 teams (pre/post-match only)AI: 16 tracking cameras per stadium; positional offside now flagged directly to on-field officials (interference still human). Field: first time all teams share the same AI match-analysis tool (FIFA’s own account)
FIFAVendor claim -
Deployment
Wimbledon replaces line judges with Hawk-Eye Live electronic line calling from 2025Computer-vision calls fully replace human line judges at a Grand Slam
Reuters -
Policy
IOC launches the Olympic AI Agenda (talent ID, training, judging, athlete protection)Top sports governing body adopts an AI strategy
IOC -
Paper
TacticAI: AI assistant for football tactics (Nat. Commun.)Liverpool collaboration; experts preferred suggestions 90% of the time
Nature Communications -
Deployment
FIFA announces semi-automated offside for the 2022 World Cup (12 cameras, 29 body points, 50 Hz)AI enters officiating at the top tournament
FIFA
No milestones match this filter.
More papers & repos 1
| Type | Title | Date |
|---|---|---|
| Paper | TacticAI: an AI assistant for football tactics | 2024-03-19 |
Latest news 5
- RSC Anderlecht sign with MyGamePlanMyGamePlanen