BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CESOC - Center for Earth System Observation and Computational Analysis - ECPv6.16.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://cesoc.net
X-WR-CALDESC:Events for CESOC - Center for Earth System Observation and Computational Analysis
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20271031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260519T130000
DTEND;TZID=Europe/Berlin:20260519T140000
DTSTAMP:20260513T164755
CREATED:20260324T221326Z
LAST-MODIFIED:20260505T091704Z
UID:8841-1779195600-1779199200@cesoc.net
SUMMARY:Michael Groom (CSIRO) - Interpretable forecasts of ENSO phase at multi-year lead times using entropic learning
DESCRIPTION:Abstract \nMachine learning\, in particular deep learning\, has shown great potential in outperforming conventional GCMs at predicting ENSO\, providing useful forecast skill beyond the Boreal spring predictability barrier and enabling the possibility of issuing ENSO forecasts at multi-year lead times. However\, despite these advancements in forecast skill\, much less progress has been made on understanding and interpreting why these models are able to make such accurate predictions. In this work\, we show that the recently proposed entropy-optimal Sparse Probabilistic Approximation (eSPA) machine learning algorithm is able to accurately forecast the phase of ENSO (i.e. La Niña\, Neutral or El Niño) at lead times that are competitive with state-of-the-art deep learning methods (e.g. up to 24 months)\, while also being substantially more parsimonious in its formulation. This latter point makes it much easier to obtain important insights into the dynamics of ENSO that are being captured when making successful forecasts at these lead times than would otherwise be possible with a “black-box” deep learning method. The interpretability methods presented include composites of precursor patterns\, feature importance maps and case studies of reconstructed vs. true precursors for a given target date\, all of which provide a complementary picture of the spatio-temporal signals that are being isolated by eSPA in order to make a correct classification of ENSO phase at a particular lead time. \n\nGroom et al. 2025\n\nBio \nMichael Groom is an early career research fellow in the Geophysical Fluid Dynamics team at CSIRO. His research focuses on the application of machine learning methods to the prediction of various key modes of climate variability\, in order to produce forecasts that can be used for assessing transition risk in the climate system. He is also helping to develop a suite of novel methods for machine learning in the small data regime\, where the number of training examples is less than or of similar size to the number of features\, centred around the information-theoretic ideas of entropic regularisation and sparsification.
URL:https://cesoc.net/event/groom/
CATEGORIES:CESOC Colloquium,summer term 2026,Talk
END:VEVENT
END:VCALENDAR