Risk Academy, led by the Nexus Consortium · Course catalogue · Risk Science and Methods
Quantitative Risk Analysis
زیرەکی دەستکرد و فێربوونی ئامێر بۆ شیکاریی مەترسی
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
ئاست
L2 Intermediate
Study time
about 24 hours (planning estimate)
دۆخ
پلاندارێژراو
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
ئاست
L3 پێشکەوتوو
Study time
about 28 hours (planning estimate)
دۆخ
پلاندارێژراو
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.
04نەخشەی زیندوو
Connected activity in South Africa
Night-time lights and population density, the footprint of electrified, connected activity, over South Africa.
نەخشە کارلێککارەکە JavaScript پێویستە؛ لیستی چینەکان و سەرچاوەکان لە خوارەوەن.
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.
سوپاسی بەکارهێنانی ئەو وێنانە دەکەین کە لەلایەن خزمەتگوزارییەکانی NASA's Global Imagery Browse Services (GIBS)ەوە دابین کراون، بەشێک لە NASA's Earth Science Data and Information System (ESDIS). ڕەنگەکان لە نەخشەی ڕەنگی بڵاوکراوە دووبارە کێشراونەتەوە؛ بەهاکان لە خانەکانی H3 دا تێکڕا کراون لەو شوێنەی نیشان دراون (دەستکاریکراو). داتای کراوەی NASA
سوپاسی بەکارهێنانی ئەو وێنانە دەکەین کە لەلایەن خزمەتگوزارییەکانی NASA's Global Imagery Browse Services (GIBS)ەوە دابین کراون، بەشێک لە NASA's Earth Science Data and Information System (ESDIS). ڕەنگەکان لە نەخشەی ڕەنگی بڵاوکراوە دووبارە کێشراونەتەوە؛ بەهاکان لە خانەکانی H3 دا تێکڕا کراون لەو شوێنەی نیشان دراون (دەستکاریکراو). داتای کراوەی NASA
VIIRS Black Marble night-time lights, NASA Goddard Space Flight Center; distributed by the NASA Level-1 and Atmosphere Archive and Distribution System (LAADS DAAC); imagery via NASA GIBS. ڕەنگەکان لە نەخشەی ڕەنگی بڵاوکراوە دووبارە کێشراونەتەوە؛ بەهاکان لە خانەکانی H3 دا تێکڕا کراون لەو شوێنەی نیشان دراون (دەستکاریکراو). داتای کراوەی 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
بەرهەمە نزیک-کاتی-ڕاستەقینەکانی VIIRS (لافاو، پلەی گەرمیی ڕووی زەوی، بەفر، ڕەنگدانەوەی چاککراو)، NASA LANCE؛ imagery via NASA GIBS. ڕەنگەکان لە نەخشەی ڕەنگی بڵاوکراوە دووبارە کێشراونەتەوە؛ بەهاکان لە خانەکانی H3 دا تێکڕا کراون لەو شوێنەی نیشان دراون (دەستکاریکراو). داتای کراوەی NASA
ASTER GDEM بەرهەمی METI و NASA ە (ASTER Global Digital Elevation Model V003, NASA LP DAAC); imagery via NASA GIBS. ڕەنگەکان لە نەخشەی ڕەنگی بڵاوکراوە دووبارە کێشراونەتەوە؛ بەهاکان لە خانەکانی H3 دا تێکڕا کراون لەو شوێنەی نیشان دراون (دەستکاریکراو). Cite as: NASA/METI/AIST/Japan Spacesystems and U.S./Japan ASTER Science Team (2019). ASTER Global Digital Elevation Model V003. doi:10.5067/ASTER/ASTGTM.003. داتای کراوەی NASA
ڕووداوە ڕاستەوخۆکان: NASA Earth Observatory Natural Event Tracker (EONET)؛ ڕووداوەکان نیشانەدەرن و بەستەری سەرچاوەی ڕەسەنی خۆیان دەهێڵنەوە.
NASA GIBS: سوپاسی بەکارهێنانی ئەو وێنانە دەکەین کە لە خزمەتگوزارییەکانی NASA Global Imagery Browse Services (GIBS) وەرگیراون، بەشێک لە NASA Earth Science Data and Information System (ESDIS).
چینە هەڵبژاردەکان (3 سەرچاوە لە لیستی چینەکاندا: زیندوو، پێشبینی، چاودێریکراو و چوارچێوە) کاتێک چالاک دەکرێن، ناوی دابینکەرەکەیان لەسەر نەخشەکە و لێرە چاپ دەکەن؛ پێشبینییەکان دەرهاویشتەی مۆدێلن و نیشاندەرە وەرگیراوەکان خەمڵاندنن.
چین و بەروارەکان
ڕووناکی شەو، ڕۆژانە: VIIRS Black Marble (VNP46A2)، NASA LAADS DAAC · 12ی تشرینی یەکەمی 2026
Population density, 2020: Population: CIESIN, Columbia University, Gridded Population of the World v4.11 (2018), NASA SEDAC, CC BY 4.0 · static
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.
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.
ڕاپۆرتەکانبەشداری بکە
لەم لاپەڕەیەوە بەڵگە پێشکەش بکە.
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.