Seminar series | Live-streamed
AI, a change in science/technology ... or culture? | 14 July | 11:30 BST
Peter Dueben (ECMWF)
Alberto Arribas is a Met Office and Alan Turing Institute Research Fellow; the Head of Met Office Informatics Lab; and a Professor at the University of Exeter Institute of Data Science and AI.
The Informatics Lab is the major innovation department at the UK Met Office. It combines scientists, technologists and designers to make environmental science and data useful across multiple sectors. The team works with the likes of NASA, Amazon, Microsoft and UK Government Departments to build prototypes and create new approaches and tools to solve problems.
In the past Alberto has led the development of world-leading weather and climate forecasting systems, published over 60 academic papers and been an editor for leading scientific journals, whilst lecturing and being a committee member for organisations such as the World Meteorological Organisation and the USA National Academy of Science.
National Meteorological Services are facing the highest level of uncertainty and change in many decades due to a combination of technological discontinuities and contextual changes.
This creates new organisational challenges, altering existing power and social structures within NMS. Analysis from other industries that have faced similar transformations in the past show that the period of change we are entering could be as long as 30 years and that there is a substantial risk that the foundations of the weather industry could be altered significantly.
Therefore, NMS need to use their resources not only to make best use of the diminishing improvements available within the current technology trajectory but to simultaneously innovate in new technologies to ensure they can generate value in the future.
This talk will analyse the strategic options available to National Meteorological Services using examples of ongoing work at the Met Office Informatics Lab.
Spatiotemporal complexity and time-dependent networks in mid- to late Holocene simulations | 28 July | 11:30 BST
Magdalena Alonso Balmaseda
Dr Annalisa Bracco received her bachelor in Physics at the University of Torino in 1996 and a PhD in geosciences at the University of Genova in 2000.
She is currently a professor in climate dynamics and oceanography in the School of Earth and Atmospheric Sciences at the Georgia Institute of Technology. Her research focuses on the transport of physical, chemical and biological material in the ocean, and on tropical climate teleconnections, often using tools from computer science and applied mathematics.
In 2011 she received the American Meteorological Society’s Nicholas Fofonoff award for her work on ocean turbulence and mesoscale transport.
In climate science regime transitions include abrupt changes in modes of climate variability and shifts in the connectivity of the whole system. While important, their identification remains challenging. In this talk we present a new framework to investigate regime transitions and connectivity patterns in spatiotemporal climate fields. This framework first quantifies local regime shifts by means of information entropy and then infers a weighted, direct and time-dependent network between entropy "domains", i.e. areas formed by grid points that are homogeneous in terms of their entropy.
The spatiotemporal variability in sea surface temperature (SST) in two simulations of the last 6000 years is investigated with this new approach. The largest regional regime shifts emerge as abrupt transitions from low to high-frequency SST oscillations, or vice versa, in both simulations. Generally, rapid and sudden transitions in the degree of connectivity of the system are observed in both simulations but, in most cases, at different times, with few exceptions. We focus, finally, on the relation between ENSO and the Indian Ocean Dipole, looking in more detail at their evolution from the mid- to late Holocene.
Causal Networks as a framework for climate science to improve process understanding | 22 September | 11:30 BST
Inna Polichtchouk (ECMWF)
Marlene Kretschmer is a post doctorate researcher at the University of Reading. Before that she worked at the Potsdam Institute for Climate Impact Research in Germany where she received her PhD in climate physics. Her research focuses on the dynamical Stratosphere-Troposphere coupling and its impacts for winter circulation and especially for extreme weather events. To address these issues, she is particularly interested in applying novel statistical approaches from machine learning such as causal discovery algorithms. Moreover, she is keen on applying these new techniques to evaluate teleconnection processes in climate models and to improve sub-seasonal to seasonal (S2S) forecasts.
In the light of ongoing anthropogenic climate change and associated risks, supporting regional decision making should be a guiding principle of climate research. However, seasonal forecast models only have low skill and climate models often give inconclusive results about regional aspects of climate change. One major source of uncertainty are dynamical drivers in the climate system, such as storm tracks or blocking, which are not well understood theoretically and where models show diverse responses.
The recent hype of machine learning promises data-driven solutions to these issues. While data-centric methods such as deep learning have and certainly will make notable contributions to the earth sciences, their power lies in their ability to efficiently describe complex relationships present in the data. There is reason to doubt whether these methods can, on their own, deal with the sort of epistemic uncertainty described above. Moreover, machine learners and climate scientists often lack a common language, making successful collaboration still difficult. In particular, climate scientists are trained to think in terms of causal relationships, whereas machine learning is mostly descriptive (i.e. correlational) and does not explicitly incorporate domain knowledge.
Here we call for the use of causal networks in climate science as a framework to overcome some of these challenges. We argue that causal networks are a simple yet powerful tool to translate qualitative expert knowledge about physical processes into mathematical objects, to gain quantitative information about the role of these processes through applying the rules of causal inference.
From research to applications – Examples of operational ensemble post-processing using machine learning |1 October | 11:30 BST
Zied Ben Bouallegue (ECMWF)
Maxime Taillardat received a M.Sc. Degree in computer science from the National Institute of Electrical engineering, Electronics, Computer science, Fluid mechanics & Telecommunications and Networks, Toulouse, France, a M.Sc. Degree in meteorology, statistics & machine learning from the National Meteorology School, Toulouse, France, and the Ph.D. degree in meteorology, oceanography and environmental science from Université Paris-Saclay, Versailles, France. He works in the Statistical Forecasting and Verification team in Météo-France, the French Weather Service. He is also affiliated to the National Centre for Meteorological Research – UMR 3589, Toulouse, France. His research interests include among others the use of machine learning algorithms in weather forecasting, especially for the post-processing of numerical weather prediction models, decision sciences, and the verification of ensemble forecasts for extreme events. Since 2018, he is one of the conveners of the session ''Advances in statistical post-processing for deterministic and ensemble forecasts'' at the European Geosciences Union General Assembly.
Statistical post-processing of ensemble forecasts, from simple linear regressions to more sophisticated techniques, is now a well-known procedure in order to correct biased and poorly dispersed ensemble weather predictions. However, practical applications in National Weather Services is still in its infancy compared to deterministic post-processing. We present two different applications of ensemble post-processing using machine learning at an industrial scale. The first is a station-based post-processing of surface temperature in a medium resolution ensemble system. The second is a gridded post-processing of hourly rainfall amounts in a high-resolution ensemble prediction system. The techniques used rely on quantile regression forests (QRF) and ensemble copula coupling (ECC), chosen for their robustness and simplicity of training whatever the variable subject to calibration.
Moreover, some variants of classical techniques used such as QRF or ECC have been developed in order to adjust to operational constraints. A forecast anomaly-based QRF is used for temperature for a better prediction of cold and heat waves. A variant of ECC for hourly rainfall is built, accounting for more realistic longer rainfall accumulations. It is shown that forecast quality as well as forecast value is improved compared to the raw ensemble, which is critical in the context of forecast automation. At last, comments about model size and computation time will be done.
Recordings and slides of past talks
Probabilistic downscaling to detect regional present and future climate hazards | 28 April
Speaker: Sherman Lo (University of Warwick)
Exploring Machine Learning for Data Assimilation | 7 May
Speaker: Alban Farchi (ECMWF)
MetNet: A Neural Weather Model for Precipitation Forecasting | 12 May
Speaker: Nal Kalchbrenner
Other Machine Learning Talks at ECMWF
Title: "ecPoint” - a Post-processing Tool that improves Forecasts and highlights Systematic Model Errors
Speaker: Timothy Hewson
In April 2019 ECMWF introduced a new, experimental, “point rainfall” forecast product onto its ecCharts web display platform, based on the post-processing package “ecPoint”, to give site-specific forecasts for everywhere in the world up to day 10. Prior to this development forecasters had access to just raw ensemble output in ecCharts, which provides gridbox average totals. ecPoint aims to incorporate probabilistically the expected sub-grid variability, and simultaneously apply gridscale bias corrections. Both these adjustments depend critically on “gridbox-weather-type”.
This presentation will describe the meteorology-based calibration rationale that underpins ecPoint, how this is different to pre-existing post-processing methods, and how it can also be applied to other surface variables such as 2m temperature. Numerous benefits will be highlighted.
The conditional verification concepts underpinning the calibration allow one to identify weather-situation-dependant gridscale biases. Examples will illustrate the diagnostic power of this approach, showing where and when rainfall is typically under- and over-forecast, providing pointers for future model improvements. And using an open source GUI one can apply the calibration code to data from other models, and thereby intercompare performance in different weather situations.
The forecast improvements that then arise will be discussed, using both long term global verification up to day 10, and illustrative case studies, with a focus on how extreme localised rainfall, that might lead to flash floods, is better handled. It will be shown how the post-processing can usefully shift the emphasis for warning issue from one region to another, when one compares with raw ensemble output.
There will be brief reference, from collaborative work, to how ecPoint output seems to compare favourably with the post-processed output of convection-resolving limited area ensembles.
The talk will conclude by discussing, in the context of ongoing and potential projects, numerous future applications of ecPoint, such as bias-corrected inputs to hydrological models, point rainfall re-analyses and tests of theories such as city impact on rainfall. Avenues for improving the methodology will also be highlighted.
The links to join the seminars will be published on this page. If you would like to receive the joining instructions for each seminar by email, please complete the registration form.