Machine Learning Course Applied to Nuclear Physics
Online 300-hour course in Machine Learning applied to nuclear physics. 6 modules covering ISO/IEC 23053 (framework for machine learning-based AI systems), ISO/IEC 22989 (AI concepts and terminology) and ROOT (CERN). Assigned tutor and open enrolment.
Take the controls.
Run a real engineering trade-off from this programme. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Describe the sources and formats of experimental and theoretical nuclear physics data.
Apply supervised learning algorithms to nuclear regression and classification problems.
Quantify uncertainties using Bayesian methods.
Use deep neural networks for the analysis of detector signals.
Employ machine learning emulators for nuclear theoretical models.
Evaluate the robustness and reproducibility of trained models.
Develop a machine learning project using nuclear physics data.
Who it's for
- Researcher in computational nuclear physics who wishes to specialise in Machine Learning applied to nuclear physics.
- Scientific data scientist who wishes to specialise in Machine Learning applied to nuclear physics.
- Machine learning engineer who wishes to specialise in Machine Learning applied to nuclear physics.
- Detector data analyst who wishes to specialise in Machine Learning applied to nuclear physics.
- Nuclear data evaluator who wishes to specialise in Machine Learning applied to nuclear physics.
- Scientific software developer who wishes to specialise in Machine Learning applied to nuclear physics.
- Graduates in engineering or sciences seeking to enter large scientific facilities.
What you'll work with
- ISO/IEC 23053 (framework for machine learning-based AI systems)
- ISO/IEC 22989 (AI concepts and terminology)
- JCGM 100 (Guide to the expression of uncertainty in measurement, GUM)
- JCGM 101 (propagation of distributions using a Monte Carlo method)
- ENDF-6 format (evaluated nuclear data)
- ISO/IEC 23894 (AI risk management)
6 modules · 300 h
1.1Experimental nuclear physics and its data1.2Databases: ENSDF, EXFOR and AME1.3Nuclear masses and binding energies1.4Cross sections and evaluations1.5Detector and event data1.6Scientific Python: NumPy, pandas and SciPy1.7Visualisation of nuclear data1.8Statistics and propagation of uncertainties1.9Machine learning: an overview1.10Practical: exploring the AME2020 mass table
2.1Linear regression and regularisation2.2Trees and gradient boosting2.3Support vector machines2.4Multilayer neural networks2.5Predicting nuclear masses with ML2.6Predicting beta half-lives2.7Charge radii and nuclear observables2.8Cross-validation and overfitting2.9Extrapolation towards the neutron drip line2.10Laboratory: neural network for mass residuals
3.1Bayesian inference and MCMC3.2Gaussian processes3.3Bayesian neural networks3.4Calibration of density functional models3.5Bayesian model mixing3.6Emulators of expensive models3.7Uncertainty quantification in predictions3.8Optimal experimental design3.9Evaluation of nuclear data with ML3.10Laboratory: emulator with Gaussian processes
4.1Convolutional networks for detector images4.2Particle identification4.3Track reconstruction in TPCs4.4Graph networks for events4.5Pulse shape discrimination4.6Anomaly detection in accelerator data4.7Accelerator control with reinforcement learning4.8Experience at FRIB, GSI and CERN4.9GPU acceleration4.10Practical: pulse classification in a scintillation detector
5.1Neural networks as wave functions5.2Variational Monte Carlo with networks5.3Chiral nuclear interactions and emulators5.4Basis reduction and emulation5.5Reactor physics and ML5.6ML on nuclear reaction data5.7Interpretability and scientific discovery5.8Physics-informed ML5.9Reproducibility and open source5.10Case study: emulation of a shell-model calculation
6.1Definition of the physics problem6.2Data acquisition and cleaning6.3Model selection6.4Training and tuning6.5Uncertainty quantification6.6Physical interpretation of results6.7Comparison with theoretical models6.8Synthesis of results6.9Report and presentation6.10Final review with the tutor
How you'll learn
100% online training on the SEIUM Institute campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetable: students progress at their own pace within the intake, which makes it compatible with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROOT (CERN), PyTorch, scikit-learn, PyMC, Jupyter, in free, academic or evaluation versions. Assessments are based on real data-analysis procedures from nuclear physics experiments, Bayesian fitting of theoretical models and event classification in detectors. Assessment is continuous per module plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Describe the sources and formats of experimental and theoretical nuclear physics data.
Apply supervised learning algorithms to nuclear regression and classification problems.
Quantify uncertainties using Bayesian methods.
Use deep neural networks for the analysis of detector signals.
Use machine learning emulators for nuclear theoretical models.
Where this takes you
Requirements
- No prior degree is required.
- Internet connection and a computer capable of running the programme's software.
- A sufficient level of Spanish to follow technical regulatory reading.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 300 hours spread over 3 to 5 months. That is between 10 and 15 hours per week on average, compatible with a full-time job.
Work is carried out with ROOT (CERN), PyTorch, scikit-learn, PyMC and Jupyter. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
A SEIUM Institute own diploma upon passing the continuous assessment and the final integrative project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a course or Postgraduate Diploma in the same area are recognised towards the advanced programme. Check the recognition policy when you enrol.
Related programmes
Course in Standards for Environmental Dosimetry
Online 300-hour course in standards for environmental dosimetry. 6 modules covering IEC 62387 (passive integrating dosimetry systems), IEC 61017 (equipment for photon measurement in environmental monitoring)…
Cabin pressurization systems course
Cabin Pressurization Systems Course Explore the design, operation, and maintenance of systems critical to flight safety and comfort. It covers the principles of pressurization and depressurization,…
Road Safety Audits in Cities Course
The Road Safety Audits in Cities course trains participants in the application of methodologies to evaluate and improve urban road safety. It focuses on risk identification,…
More in Off-Road, Special Vehicles & Machinery
All Off-Road, Special Vehicles & Machinery programmes → · How to apply · Fees & financing · Scholarships