The WeatherPod AI

Shruti’s research is about using data-driven, Artificial Intelligence or AI techniques for improving weather forecasts – and rainfall forecasts in particular.

The emphasis of her work is very much on linking research to action. A key part of this is collaboration with local meteorological departments in the Greater Horn of Africa on the development of operational AI-based post-processing techniques.

Our discussion was wide ranging and shed much new light on the potential value of AI in weather forecasting.

The areas we covered ranged from from the pros and cons of using AI-based post-processing techniques for raw weather data, to AI’s potential role in generating much larger ensembles than are currently possible.

We examined the massive step change cloud computing could bring to local forecasting capabilities by enabling weather services in developing countries to train and develop their own AI models.

We also looked at the influence AI could have in coming years on the way weather information is used by weather affected end users.

Finally, we took a gaze into the future. How did Shruti think the global weather enterprise might evolve in future years in the light of the emerging AI tools she’s been working with?

The growing use of Artificial Intelligence in the field of weather prediction and forecasting is likely to have profound implications for national meteorological services in the coming years.

In this fifth episode in our special WeatherPod series on AI, we’ve invited Dr. Alan Hally into the studio to examine how one met service – Met Éireann – is approaching the use of AI in its operations.

Alan is the Scientific Lead in Met Éireann’s recently formed AI Transformation Team. This team’s primary aim is to optimise the services Met Éireann provides to Irish citizens through the targeted application of AI or machine learning technologies.

Irina Sandu is the Director of Destination Earth (DestinE) at ECMWF, a flagship initiative of the European Union to develop a digital twin of planet Earth. Prior to taking the lead of ECMWF’s involvement in DestinE in summer 2023, she was Science Lead for the initiative from January 2022.
Irina joined ECMWF in 2010 as a scientist working on the representation of turbulent processes and then lead the Physical Processes team for several years. Through the work carried out at ECMWF, Irina played an instrumental role in improving understanding of the impact of surface drag, as well as the representation of both stable and cloudy boundary layers in the Integrated Forecasting System (IFS).

Irina has also coordinated polar prediction related activities at ECMWF for several years, most prominently in the context of the ongoing WMO Year of Polar Prediction and the H2020 project APPLICATE. Irina is also the co-lead of the H2020 nextGEMS project, which develops the next generation of storm and eddy resolving models which underpin the DestinE climate digital twin.

More recently, Irina has helped shaping the science plan for DestinE and led the DestinE science activities at ECMWF. Irina is now leading the implementation of the activities ECMWF is responsible for delivering in DestinE by working closely with partners throughout Europe, related to the first two high priority digital twins and digital twin engine.

Hosts David Rogers and Alan Thorpe delve into the ECMWF’s use of AI and how this may impact it’s future products and services, especially when it comes to their use in the developing countries by meteorological services and other customers.

Florian leads the ECMWF’s Forecast Department which is responsible for the production of weather forecasts, forecast quality control, and the development of novel forecast products.

ECMWF has for a while been experimenting with using deep learning to produce a data-based AI weather prediction model and last October Florian played a key role in the launch of the Artificial Intelligence / Integrated Forecasting System. This is the ECMWF’s first forecasting system incorporating a machine learning prediction module.

Amy is Director of the National Science Foundation AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography – or AI2ES for short.

She’s also a Professor at Oklahoma University’s School of Computer Science and School of Meteorology.

Working under the University of Oklahoma’s leadership, AI2ES brings together researchers in AI, atmospheric science, ocean science, and risk communication. The thinking is that accelerated AI research in the environmental sciences can improve understanding of the rapid changes taking place in weather patterns, oceans, sea level rise, and disaster risk.

Amy’s research focuses on developing and applying machine learning and data mining methods for real-world applications, with a specific interest in high-impact weather.

Much of this work involves weather analytics or physical data science and she and her students are developing physics-based trustworthy AI methods as well as explainable AI. Their aim is to apply their work to high-impact weather phenomena, including tornadoes, hail, severe wind events, flooding, drought, and aircraft turbulence.

A key aim is to help build a diverse and flexible science, technology, engineering, and mathematics workforce. Amy’s thinking is that diversity will bring new ideas to the forefront, while flexibility is crucial to dealing with rapid changes in technology. To help this process, Amy and her team have developed outreach projects to encourage students to pursue STEM careers.

This work aside, Amy also directs the Interaction, Discovery, Exploration and Adaptation – or IDEA – Lab at Oklahoma University. The Lab’s focus is on developing and applying data science, AI and machine learning techniques for high-impact real-world applications.

Kirstine is the Met Office’s Chief AI Officer (CAIO) and Principal Fellow for Data Science. As CAIO she is charged with embedding AI in the Met Office’s core business – initially focusing on the use of AI in weather forecasting through leadership of the ‘AI for Numerical Weather Prediction’ (AI4NWP) programme.

As Principal Fellow, Kirstine plays a leading role in shaping the future of Data Science (including Artificial Intelligence and Machine Learning) in the Met Office.

Kirstine is also Co-Director of the Natural Environment Theme of the Turing Research and Innovation Cluster on Digital Twins (TRIC-DT) and an Honorary Professor at the University of Exeter.