AI and machine learning for risk analysis, taught twice over: as the working methods of the field and as its frontier since 2024, with labs on the Academy's tools, open data and the Nexus Standards.
AI and machine learning for risk analysis: foundations and practice
This area covers the machine-learning methods risk analysts now use: classification and regression of risk outcomes, emulators of slow physical models, anomaly detection and the quantification of uncertainty in model outputs.
AI and machine learning for risk analysis: foundations and practice
Inqanaba
L2 Intermediate
Study time
about 24 hours (planning estimate)
Imeko
Planned
Prerequisites
An L1 course in the area, or an entry review
Why now
Machine learning weather models (GraphCast, 2023; GenCast, 2024) now match or beat physics ensembles on many scores, ECMWF runs its AIFS operationally since 2025, and AI flood forecasting reaches ungauged basins, so risk analysts must know when to trust these models.
Define emulator and the other key terms of the discipline and use them correctly in a written case
Explain supervised learning for risk outcomes and emulators and surrogates of physical and catastrophe models with a worked example and its source
Apply the discipline's method to a documented case and explain each result with its source
Analyse a named case against uncertainty quantification in machine learning, stating evidence, date and limits
Modules
01
Supervised learning for risk outcomes
Supervised learning for risk outcomes
Emulators and surrogates of physical and catastrophe models
Uncertainty quantification in machine learning
02
Conformal prediction and distribution-free coverage
Conformal prediction and distribution-free coverage
Anomaly detection and change detection
Geospatial foundation models and satellite embeddings
03
Causal inference and machine learning
Causal inference and machine learning
Validation, drift monitoring and model risk for machine learning
Fairness and bias in risk models
04
Lab: the discipline's method
A learned model gives a point prediction with no promise attached; holding out a calibration set, ranking its residuals and taking a quantile wraps the prediction in an interval whose coverage is assured without any assumption about the model, and the size of the calibration set sets how tight that guarantee is.
Work the method through a documented case and explain each result
AI and machine learning for risk analysis: frontier methods
The methods, data, tools and studies that changed AI and machine learning for risk analysis between 2024 and 2026, taught by reproducing them on open data.
AI and machine learning for risk analysis: frontier methods
Inqanaba
L3 Advanced
Study time
about 28 hours (planning estimate)
Imeko
Planned
Prerequisites
AI and machine learning for risk analysis: foundations and practice; Working knowledge of a scripting language (Python or R) for the labs
Why now
Machine learning weather models (GraphCast, 2023; GenCast, 2024) now match or beat physics ensembles on many scores, ECMWF runs its AIFS operationally since 2025, and AI flood forecasting reaches ungauged basins, so risk analysts must know when to trust these models.
The Academy proposes how each discipline teaches toward the Nexus Standards; the mapping is open for public review. Bodies and standards are named so learners can find and apply their published work; the Academy teaches their use and links to the publisher, and no affiliation is implied.
04Imaphu ephilayo
Connected activity in South Africa
Night-time lights and population density, the footprint of electrified, connected activity, over South Africa.
Satellite image. Satellite or model raster as the provider publishes it. Clouds, swath gaps and retrieval error leave gaps and noise; values are indicators, not measurements at a place.
Connected activity, framed on South Africa.Satellite and model products as NASA publishes them, each with its own date. They are indicators, not assessments of any place.
Siyavuma ukusebenzisa imifanekiso enikwe ziinkonzo ze-NASA's Global Imagery Browse Services (GIBS), eyinxalenye ye-NASA's Earth Science Data and Information System (ESDIS). Imibala izotywe ngokutsha ukusuka kwimephu yemibala epapashiweyo; amaxabiso afakwe umndilili kwiiseli ze-H3 apho aboniswa khona (iguqulwe). Idatha evulekileyo ye-NASA
Siyavuma ukusebenzisa imifanekiso enikwe ziinkonzo ze-NASA's Global Imagery Browse Services (GIBS), eyinxalenye ye-NASA's Earth Science Data and Information System (ESDIS). Imibala izotywe ngokutsha ukusuka kwimephu yemibala epapashiweyo; amaxabiso afakwe umndilili kwiiseli ze-H3 apho aboniswa khona (iguqulwe). Idatha evulekileyo ye-NASA
Izibane zasebusuku ze-VIIRS Black Marble, NASA Goddard Space Flight Center; zisasazwa yi-NASA Level-1 and Atmosphere Archive and Distribution System (LAADS DAAC); imifanekiso ivela kwi-NASA GIBS. Imibala izotywe ngokutsha ukusuka kwimephu yemibala epapashiweyo; amaxabiso afakwe umndilili kwiiseli ze-H3 apho aboniswa khona (iguqulwe). Idatha evulekileyo ye-NASA
Center for International Earth Science Information Network (CIESIN), Columbia University. 2018. Gridded Population of the World, Version 4 (GPWv4): Population Density, Revision 11. NASA Socioeconomic Data and Applications Center (SEDAC). Licensed under CC BY 4.0. Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). doi:10.7927/H49C6VHW. CC BY 4.0
Iziganeko ezenzeka ngoku: NASA Earth Observatory Natural Event Tracker (EONET); iziganeko zingumqondiso nje kwaye zigcina amakhonkco azo emithombo yokuqala.
NASA GIBS: Siyavuma ukusebenzisa imifanekiso enikwe ziinkonzo ze-NASA's Global Imagery Browse Services (GIBS), eyinxalenye ye-NASA's Earth Science Data and Information System (ESDIS).
Independent reviewers for the families of the hazard atlas, three from at least two regions for each family (NHS2-R19), priority families first CALL-ATLAS-REVIEW
University, student and national chapter teams. Open
A cell acts within its host's rules and never replaces an authority. A CERT works alongside the local emergency services, follows their direction and is not an emergency service.
How a cell forms
01
Gather the cell
Bring together three to seven people with complementary skills: data, field practice, policy and communication.
02
Choose a type
Pick the kind of cell that fits the work, from the gallery below. A cell can add a second focus later. See the types
03
Register it
Name the cell, its members, area and region, and who hosts it. You receive a reference and a contact. Form a cell
04
Learn together
Follow shared study paths at Risk Academy, with practice and a record of every course completed. Hazards and resilience
05
Lead and report
Hold regular sessions. Publish what the cell learns through Reports. Bring findings to the working groups. Working groups
Isalathiso
What a national team or a local community can do on The Global Risks Index (NXS-GRX) today.
NXS-GRX
Your country's profile
Open risk profiles for 195 countries, with sources and licences on every value. Open the Index
NXS-GRX
Correct or reply
Correct a value or reply for your country. The change is logged with its effect. Open the Index
NXS-GRX
Offer data
Offer a dataset. It enters through the licence gate, with your credit. Open the Index
NXS-GRX
Use the open data
Layers, profiles and tiles through the open API. Open the Index
A completion record: the course, its version, the date and what was assessed, private by default and shared by you. It stacks into discipline, department and programme achievements. A record states what was studied and assessed and does not certify competence; it is not a licence, a professional title or an employment status.
Idatha neendawo zivela phi?
Every faculty teaches on a twin of a real place built from open data; each layer carries its provider, licence and date, and every result on the Academy states its source. Maps and figures are indicators for teaching, never an assessment of a place.
How do I take part beyond the course?
Form a competence cell of three to seven people, study a shared pathway, take a supervised assignment in the National Working Groups, or bring a cohort from your institution. For organisations.
Amagama aphambili
Emulator
A fast statistical or machine-learning model trained to reproduce the outputs of a slower physical or catastrophe model.
Conformal prediction
A method that wraps any model to give prediction sets with a stated coverage under exchangeability.
Distribution shift
A change between the data a model was trained on and the data it is used on, which can invalidate its accuracy.
Calibrated classifier
A classifier whose predicted probabilities match observed frequencies.
IingxeloYiba negalelo
Faka ubungqina obuvela kweli phepha.
Reports is the Consortium's quarterly publication, written by six desks. This page sits with the Academy Capability desk. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work. Sent to the wrong desk, it is forwarded, not refused.
Never send personal data, sensitive infrastructure detail or anything you have no right to share. A contribution is reviewed before use; sending it confers no authorship or editorial rights, and sponsorship never buys a finding.
Okunxulumeneyo
Around AI and machine learning for risk analysis: courses