̽��ֱ�� of Cambridge - Microsoft Research

Fully AI driven weather prediction system could start revolution in forecasting

sc604 — Thu, 20 Mar 2025 15:56:54 +0000

̽��ֱ��system, Aardvark Weather, has been supported by the Alan Turing Institute, Microsoft Research and the European Centre for Medium Range Weather Forecasts. It provides a blueprint for a new approach to weather forecasting with the potential to transform current practices. The results are reported in the journal Nature.

“Aardvark reimagines current weather prediction methods offering the potential to make weather forecasts faster, cheaper, more flexible and more accurate than ever before, helping to transform weather prediction in both developed and developing countries,” said Professor Richard Turner from Cambridge’s Department of Engineering, who led the research. “Aardvark is thousands of times faster than all previous weather forecasting methods.”

Current weather forecasts are generated through a complex set of stages, each taking several hours to run on powerful supercomputers. Aside from daily usage, the development, maintenance and use of these systems require significant time and large teams of experts.

More recently, research by Huawei, Google, and Microsoft has shown that one component of the weather forecasting pipeline, the numerical solver (which calculates how weather evolves over time), can be replaced with AI, resulting in faster and more accurate predictions. This combination of AI and traditional approaches is now being used by the European Centre for Medium Range Weather Forecasts (ECMWF).

But with Aardvark, researchers have replaced the entire weather prediction pipeline with a single, simple machine learning model. ̽��ֱ��new model takes in observations from satellites, weather stations and other sensors and outputs both global and local forecasts.

This fully AI driven approach means predictions that were once produced using many models – each requiring a supercomputer and a large support team to run – can now be produced in minutes on a desktop computer.

When using just 10% of the input data of existing systems, Aardvark already outperforms the United States national GFS forecasting system on many variables. It is also competitive with United States Weather Service forecasts that use input from dozens of weather models and analysis by expert human forecasters.

“These results are just the beginning of what Aardvark can achieve,” said first author Anna Allen, from Cambridge’s Department of Computer Science and Technology. “This end-to-end learning approach can be easily applied to other weather forecasting problems, for example hurricanes, wildfires, and tornadoes. Beyond weather, its applications extend to broader Earth system forecasting, including air quality, ocean dynamics, and sea ice prediction.”

̽��ֱ��researchers say that one of the most exciting aspects of Aardvark is its flexibility and simple design. Because it learns directly from data it can be quickly adapted to produce bespoke forecasts for specific industries or locations, whether that's predicting temperatures for African agriculture or wind speeds for a renewable energy company in Europe.

This contrasts to traditional weather prediction systems where creating a customised system takes years of work by large teams of researchers.

“ ̽��ֱ��weather forecasting systems we all rely on have been developed over decades, but in just 18 months, we’ve been able to build something that’s competitive with the best of these systems, using just a tenth of the data on a desktop computer,” said Turner, who is also Lead Researcher for Weather Prediction at the Alan Turing Institute.

This capability has the potential to transform weather prediction in developing countries where access to the expertise and computational resources required to develop conventional systems is not typically available.

“Unleashing AI’s potential will transform decision-making for everyone from policymakers and emergency planners to industries that rely on accurate weather forecasts,” said Dr Scott Hosking from ̽��ֱ��Alan Turing Institute. “Aardvark’s breakthrough is not just about speed, it’s about access. By shifting weather prediction from supercomputers to desktop computers, we can democratise forecasting, making these powerful technologies available to developing nations and data-sparse regions around the world.”

“Aardvark would not have been possible without decades of physical-model development by the community, and we are particularly indebted to ECMWF for their ERA5 dataset which is essential for training Aardvark,” said Turner.

“It is essential that academia and industry work together to address technological challenges and leverage new opportunities that AI offers,” said Matthew Chantry from ECMWF. “Aardvark’s approach combines both modularity with end-to-end forecasting optimisation, ensuring effective use of the available datasets."

“Aardvark represents not only an important achievement in AI weather prediction but it also reflects the power of collaboration and bringing the research community together to improve and apply AI technology in meaningful ways,” said Dr Chris Bishop, from Microsoft Research.

̽��ֱ��next steps for Aardvark include developing a new team within the Alan Turing Institute led by Turner, who will explore the potential to deploy Aardvark in the global south and integrate the technology into the Institute’s wider work to develop high-precision environmental forecasting for weather, oceans and sea ice.

Reference:
Anna Allen, Stratis Markou et al. ‘End-to-end data-driven weather prediction.’ Nature (2025). DOI: 10.1038/s41586-025-08897-0

Adapted from a media release by ̽��ֱ��Alan Turing Institute

A new AI weather prediction system, developed by researchers from the ̽��ֱ�� of Cambridge, can deliver accurate forecasts tens of times faster and using thousands of times less computing power than current AI and physics-based forecasting systems.

̽��ֱ��Alan Turing Institute

Professor Richard Turner using Aardvark Weather

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Strategy unveiled to boost innovation in Cambridge

skbf2 — Mon, 16 Oct 2023 15:55:21 +0000

̽��ֱ��Innovate Cambridge Summit saw over 400 leaders from across the civic, business and academic working communities to support the science and technology cluster to maintain its position as a world leader amid fierce international competition.

Cambridge has evolved into a global innovation hub over the last 30 years, with over 5,500 knowledge-intensive businesses generating revenues exceeding £20bn annually and 23 billion-dollar unicorn companies born in the city. ̽��ֱ�� ̽��ֱ�� of Cambridge is also the number one university in the world for producing successful tech founders, ahead of Harvard and MIT, with over 500 alumni founders raising more than $10 million in funding.

Recognising this, the city and its innovation ecosystem is now presented with a generational opportunity to maximise economic and social return. International benchmarking indicates that Cambridge can do more to enhance its position in the global innovation landscape.

This new home-grown innovation strategy, which has had input from 200 organisations, including Cambridge Enterprise, the ̽��ֱ�� of Cambridge, Cambridge Innovation Capital, AstraZeneca, Microsoft, ARM, Darktrace, Cambridge City Council, and Cambridge County Council and Cambridgeshire and Peterborough Combined Authority will propel the ecosystem towards a groundbreaking future.

In the past twelve months, the Cambridge ecosystem has seen significant collaboration, with over 200 organisations endorsing an Innovation Charter and extensive consultations involving more than 500 individuals to craft an innovation strategy. ̽��ֱ��culmination of these efforts, Innovate Cambridge, seeks to leverage the city's unique position as a driver of Britain’s growth, fostering collaboration, and catalysing innovation for the benefit of local communities and the broader UK.

In pursuit of this vision, Innovate Cambridge has identified three strategic goals:

An innovation ecosystem firing on all cylinders. Innovate Cambridge envisions improved health and social care, optimised energy use, and enhanced agricultural outcomes through world-leading life sciences research and AI applications. ̽��ֱ��focus will be on creating a green growth strategy, fostering economic growth, and supporting social infrastructure.
Ensuring the innovation ecosystem provides value and impact for the local community. Innovate Cambridge aims to increase collaboration within and beyond the region, formalising partnerships with other innovation hubs and economic centres. ̽��ֱ��initiative strives to deliver high-quality employment and training opportunities while ensuring benefits extend beyond geographical limits.
Forming partnerships with other regions and collaborators to drive scale and deliver social and economic benefits. By 2035, Innovate Cambridge aims to achieve significant economic, social, and environmental impact through collaborations and partnerships. Practical infrastructure issues, such as water scarcity and transportation, are addressed in conjunction with local government and Cambridge Ahead.

"Innovation is critical to local, national and global prosperity and central to the UK's economic success. Cambridge is the UK's leading research-based innovation ecosystem. A recent analysis found that spinouts and start-ups associated with the ̽��ֱ�� contributed over £18bn to the UK economy and there are many other companies within the Cambridge ecosystem without a direct connection to the ̽��ֱ�� that make a further significant contribution." Professor Andy Neely OBE, Senior Pro-Vice-Chancellor, ̽��ֱ�� of Cambridge

“ ̽��ֱ��City Council has an important placemaking and leadership role for the whole city. We want Cambridge to be an even better place to live, work and study, and ensure the city maintains its status as a global innovation hub. Cambridge also has significant challenges around health inequalities, housing affordability, and life changes for disadvantaged young people. That’s why it's vital successful businesses, innovators, and entrepreneurs that have benefited from the unique, nurturing, innovation environment in Cambridge to give back to the city in a more tangible way.” Robert Pollock, Chief Executive, Cambridge City Council

"This strategy represents a pivotal moment for the innovation ecosystem in Cambridge. ̽��ֱ��collaboration of over 200 organisations has yielded a strategic roadmap that provides a shared vision for Cambridge as a global innovation hub. This initiative, rooted in inclusivity and sustainability, will drive positive economic and social impacts for the local community. Cambridge Enterprise is proud to be part of this ambitious endeavour, and we look forward to fostering groundbreaking discoveries and translating them into world-changing businesses." Dr Diarmuid O'Brien, Chief Executive, Cambridge Enterprise

“Innovation is critical to local, national and global prosperity and central to the wider UK growth agenda, and Cambridge remains the most intensive science and technological cluster in the world. It is an ecosystem where companies have the potential to go from lab to market quicker than anywhere else. We excel in life sciences, deep tech, and interdisciplinary research; and the city is home to a blend of start-ups and global leaders. ̽��ֱ��fact that so many of those stakeholders and businesses have now come up with an inclusive, forward-looking plan to ensure the city continues to innovate, compete, and deliver impact on a global scale, fills me with enormous pride.” Michael Anstey, Partner, Cambridge Innovation Capital

News release first published by Cambridge Enterprise

An ambitious new strategy to nurture and grow its innovation ecosystem has been unveiled at Cambridge summit.

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

AI cuts waiting times for cancer patients in NHS first

Anonymous — Tue, 27 Jun 2023 08:00:18 +0000

'OSAIRIS' is saving many hours of doctors’ time in preparing scans and helping to cut the time patients have to wait between referral for radiotherapy and starting treatment.

Working alongside this AI technology, specialists can plan radiotherapy treatments approximately two and half times faster than if they were working alone, ensuring more patients can get treatment sooner and improving the likelihood of cure.

̽��ֱ��technology is currently being used at Addenbrooke’s for prostate and head and neck cancers, but has the potential to work for many other types of cancer, benefitting patients across the NHS.

Dr Raj Jena, oncologist at Cambridge ̽��ֱ�� Hospitals NHS Foundation Trust, led the research for the NHS and ̽��ֱ�� of Cambridge. His research includes long- term collaborations with Microsoft Research on an AI research project known as Project InnerEye to develop machine learning techniques to support the global medical imaging community. To broaden access to research in this field, Microsoft Research made available Project InnerEye toolkits as open-source software.

With a £500,000 grant from the NHS AI Lab, Dr Jena’s team created a new AI tool, OSAIRIS, using open-source software from Project InnerEye and data from patients who had previously been treated in the hospital and agreed to contribute to the research.

OSAIRIS works by significantly cutting the amount of time a doctor needs to spend drawing around healthy organs on scans before radiotherapy. Outlining the organs, known as ‘segmentation’, is critical in order to protect the healthy tissue around the cancer from radiation. It can take a doctor between 20 minutes and three hours to perform this task, per patient. This complex but routine task is ideally suited to AI with the oncologist in control, checking every scan after OSAIRIS has done the segmentation.

Rigorous tests and risk assessments have been carried out to ensure OSAIRIS is safe and can be used in the day-to-day care of radiotherapy patients across the NHS. In masked tests, known as ‘Turing tests’, doctors were unable to tell the difference between the work of OSAIRIS and the work of a doctor colleague.

Dr Raj Jena said: “OSAIRIS does much of the work in the background so that when the oncologist sits down to start planning treatment, most of the heavy lifting is done. It is the first cloud-based AI technology to be developed and deployed within the NHS. 18 months of rigorous testing will enable us to share this technology safely across the NHS for patient benefit.”

“We’ve already started to work on a model that works in the chest, so that will work for lung cancer and breast cancer particularly,” he explains. “And also, from my perspective as a neurooncologist, I’m interested that we’re building the brain model as well so that we’ve got something that works for brain tumours as well.”

Aditya Nori, General Manager of Healthcare for Microsoft Research, said: “By combining the power of AI with the world-class clinical expertise of the NHS, we have an amazing opportunity for revolutionising healthcare together, while preserving the human element that is the essence of high-quality and safe care.”

“Healthcare offers the possibility not only to have technical impact but also societal impact, so I am really thrilled about this. ̽��ֱ��fact that we have AI finally in the NHS will also open the doors for other kinds of AI technologies to really reduce the burden that’s placed on clinicians, and more importantly, improve patient safety, outcomes, and experiences.”

Health and Social Care Secretary Steve Barclay said: “Cutting edge technology can help us reduce waiting times for cancer patients, free up time for staff so they can focus on patient care, and ultimately save lives – and artificial intelligence is playing an increasingly important role.

“Backed by £500,000 in government funding, the team at Addenbrooke’s Hospital are utilising the innovative OSAIRIS tool to speed up radiotherapy scans at more than twice the normal rate - reducing the time it takes to start potentially life-saving treatment.

“It will also help ease the pressure on the NHS and cut waiting lists, one of the government’s five priorities.

“In the year the NHS turns 75 we are investing in its future and last week announced a new £21 million fund for Trusts to deploy AI tools in a safe and controlled way to speed up the diagnosis and treatment for a range of conditions.”

Artificial intelligence developed by and for the NHS at Addenbrooke’s Hospital in Cambridge is reducing the amount of time cancer patients wait for radiotherapy treatment.

CUH

Dr Raj Jena

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Multi-million pound initiative from Microsoft to support AI research at Cambridge

cjb250 — Wed, 31 Oct 2018 09:19:20 +0000

As part of the Microsoft Research - Cambridge ̽��ֱ�� Machine Learning Initiative, Microsoft will help increase AI and machine learning research capacity and capability at Cambridge by supporting visiting researchers, postdoctoral researchers, PhD students and interns from the UK, EU and beyond.

̽��ֱ��new Initiative builds on more than two decades of collaboration between the ̽��ֱ�� and Microsoft Research Cambridge, and will be based in the ̽��ֱ��’s Department of Engineering. It will be formally announced today at the Microsoft Future Decoded Conference in London.

AI and machine learning have the potential to revolutionise how we interact with the world, but before these technologies can be widespread and used in industries such as healthcare, education and transportation, there are complex problems that need to be solved.

A shortage of skills in AI and machine-learning, particularly at PhD level and above, has led to many large tech companies recruiting from academia, leaving behind a shortage in research and teaching capacity at universities.

“By focusing on a two-way collaborative initiative for long-term growth, not short-term gain, we are taking a different approach to this problem. We are working with universities to build up AI and machine learning talent and research in the UK,” said Chris Bishop, Lab Director, Microsoft Research Cambridge. “Our researchers regularly work together on projects with global impact, and this initiative will help to build on the already strong links between the ̽��ֱ�� of Cambridge and Microsoft.”

“Cambridge has a culture of ideas going back and forth between industry and academia, and this agreement with Microsoft is a prime example,” said Professor Andy Neely, Pro-Vice-Chancellor for Enterprise and Business Relations at Cambridge. “By working together with industry on issues such as how best to use AI and machine learning, we can not only help solve complex issues for industry, but continue to support world-leading research and train the next generation of leaders in the field.”

Earlier this year the Government and the AI sector agreed a Sector Deal to further boost the UK’s global reputation as a leader in developing AI technologies, ensuring the UK remains a go-to destination for AI innovation and investment.

Secretary of State for Digital, Culture, Media and Sport, Jeremy Wright, said: “ ̽��ֱ��UK is a beacon for international talent and at the forefront of emerging technologies because of the ideas developed in our world-leading universities.

“This new collaboration between Microsoft and Cambridge ̽��ֱ�� will help us continue to develop home-grown AI talent and supports the government's modern Industrial Strategy and £1 billion AI sector deal. It is crucial that we do all we can to capitalise on our global advantage in this technology.”

Business Secretary Greg Clark said: “ ̽��ֱ��UK has an unmatched heritage in AI and its application in emerging sectors and technologies.

“This partnership between one of the world’s leading universities and technology developer and Microsoft is a great example of collaboration between business and academia. ̽��ֱ��UK’s leading research and innovation base are driving parts of our modern Industrial Strategy supported with the biggest increase in public research and development investment in the UK’s history.”

̽��ֱ�� ̽��ֱ�� of Cambridge is joining with Microsoft to help tackle the problem of ‘brain drain’ in AI and machine learning research.

By working together with industry on issues such as how best to use AI and machine learning, we can not only help solve complex issues for industry, but continue to support world-leading research and train the next generation of leaders in the field

Andy Neely

Geralt

Artificial intelligence

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Public Domain

Computer model of blood development could speed up search for new leukaemia drugs

cjb250 — Mon, 09 Feb 2015 16:00:00 +0000

̽��ֱ��human body produces over 2.5 million new blood cells during every second of our adult lives, but how this process is controlled remains poorly understood. Around 30,000 new patients each year are diagnosed with cancers of the blood each year in the UK alone. These cancers, which include leukaemia, lymphoma and myeloma, occur when the production of new blood cells gets out of balance, for example if the body produces an overabundance of white blood cells.

Biomedical scientists from the Wellcome Trust-MRC Cambridge Stem Cell Institute and the Cambridge Institute for Medical Research collaborated for the past 2 years with computational biologists at Microsoft Research and Cambridge ̽��ֱ��’s Department of Biochemistry. This interdisciplinary team of researchers have developed a computer model to help gain a better understanding of the control mechanisms that keep blood production normal. ̽��ֱ��details are published today in the journal Nature Biotechnology.

“With this new computer model, we can carry out simulated experiments in seconds that would take many weeks to perform in the laboratory, dramatically speeding up research into blood development and the genetic mutations that cause leukaemia,” says Professor Bertie Gottgens whose research team is based at the ̽��ֱ��’s Cambridge Institute for Medical Research.

Dr Jasmin Fisher from Microsoft Research and the Department of Biochemistry at the ̽��ֱ�� of Cambridge says: “This is yet another endorsement of how computer programs empower us to gain better understanding of remarkably complicated processes. What is ground-breaking about the current work is that we show how we can automate the process of building such programs based on raw experimental data. It provides us with a blueprint to develop computer models relevant to other human diseases including common cancers such as breast and colon cancer.”

To construct the computer model, PhD student Vicki Moignard from the Stem Cell Institute measured the activity of 48 genes in over 3,900 blood progenitor cells that give rise to all other types of blood cell: red and white blood cells, and platelets. These genes include TAL1 and RUNX1, both of which are essential for the development of blood stem cells, and hence to human life.

Computational biology PhD student Steven Woodhouse then used the resulting dataset to construct the computer model of blood cell development, using computational approaches originally developed at Microsoft Research for synthesis of computer code. Importantly, subsequent laboratory experiments validated the accuracy of this new computer model.

One way the computer model can be used is to simulate the activity of key genes implicated in blood cancers. For example, around one in five of all children who develop leukaemia has a faulty version of the gene RUNX1, as does a similar proportion of adults with acute myeloid leukaemia, one of the most deadly forms of leukaemia in adults. ̽��ֱ��computer model shows how RUNX1 interacts with other genes to control blood cell development: the gene produces a protein also known as Runx1, which in healthy patients activates a particular network of key genes; in patients with leukaemia, an altered form of the protein is thought to suppress this same network. If the researchers change the ‘rules’ in the network model, they can simulate the formation of abnormal leukaemia cells. By tweaking the leukaemia model until the behaviour of the network reverts back to normal, the researchers believe they can identify promising pathways to target with drugs.

Professor Gottgens adds: “Because the computer simulations are very fast, we can quickly screen through lots of possibilities to pick the most promising ones as pathways for drug development. ̽��ֱ��cost of developing a new drug is enormous, and much of this cost comes from new candidate drugs failing late in the drug development process. Our model could significantly reduce the risk of failure, with the potential to make drug discovery faster and cheaper.”

̽��ֱ��research was supported by the Medical Research Council, the Biotechnology and Biological Sciences Research Council, Leukaemia and Lymphoma Research, the Leukemia and Lymphoma Society, Microsoft Research and the Wellcome Trust.

Dr Matt Kaiser, Head of Research at UK blood cancer charity Leukaemia & Lymphoma Research, which has funded Professor Gottgens’ team for over a decade, said: “For some leukaemias, the majority of patients still ultimately die from their disease. Even for blood cancers for which the long-term survival chances are fairly good, such as childhood leukaemia, the treatment can be really gruelling. By harnessing the power of cutting-edge computer technology, this research will dramatically speed up the search for more effective and kinder treatments that target these cancers at their roots.”

Reference
Moignard, V et al. Decoding the regulatory network of early blood development from single-cell gene expression measurements. Nature Biotech; 9 Feb 2015.

̽��ֱ��first comprehensive computer model to simulate the development of blood cells could help in the development of new treatments for leukaemia and lymphoma, say researchers at the ̽��ֱ�� of Cambridge and Microsoft Research.

With this new computer model, we can carry out simulated experiments in seconds that would take many weeks to perform in the laboratory

Bertie Gottgens

E. M. Unit, Royal Free Hospital

SEM image of normal red blood cells, computer-coloured red

̽��ֱ��text in this work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page. For image rights, please see the credits associated with each individual image.

Yes