How to apply the latest AI developments to combat climate change and build a more sustainable, low-carbon world
AI is a powerful technology that will change our future. So how can AI be applied to combat climate change and find sustainable solutions?
Sims Witherspoon, our Head of Climate and Sustainability, who recently spoke at TED Countdown about how AI can accelerate the transition to renewable energy, explains: “Climate change is a multifaceted problem with no single solution. We must move beyond the debate what We can do it and start focusing how We can do it.”
The impacts of climate change on Earth’s ecosystems are incredibly complex, and in an effort to use AI to solve some of the world’s toughest problems, some of the ways we are working to increase our understanding and optimize existing systems include: It’s the same. Accelerate groundbreaking science on climate and its impacts.
Understand weather, climate and its impacts.
Better understanding the key issues and their impacts is an important first step in tackling climate change. Working with the UK Met Office, we have developed a current observation model of precipitation to better understand weather changes. This current casting model is more accurate than existing, state-of-the-art models and is much preferred by the Met’s professional meteorologists. Our climate and weather research spans short-range (less than two hours) to medium-range (10 days) forecasts, which can have a major impact on how we optimize renewable energy systems based on natural resources.
From modeling the behavior of animal species across the Serengeti to supporting machine learning projects that advance conservation projects in Africa, we are helping scientists track and better understand the impacts of climate change on ecosystems and biodiversity. . Looking ahead, our team is building an AI system used to identify bird songs in Australia, supporting advanced tools to monitor changing wildlife at large scale.
Additionally, we are working with the nonprofit Climate Change AI to address critical gaps in climate-related data. Currently, the partnership is focused on building a comprehensive wishlist of datasets that can advance AI solutions for climate change. Once this wish list is completed, it will be made available to the wider public.
Optimizing existing systems
We need to transition to a more sustainable infrastructure while optimizing the systems the world relies on today. For example, today’s computing infrastructure, including AI itself, is energy-intensive. To help solve some of these problems, we have been developing AI that can enhance existing systems, including optimizing industrial cooling and creating more efficient computer systems.
Because our energy grid does not yet run on clean energy, it is important to use resources as efficiently as possible during the transition to renewable energy. Accelerating the global transition to renewable energy sources could also significantly reduce carbon emissions.
In 2019, Google’s Climate and Sustainability team worked with subject matter experts from Google-owned wind farms to increase the value of wind energy. Ultimately, we aim to support growth across the broader industry. By developing a custom AI tool to better predict wind power output and another model to recommend commitments to supply predicted energy to the grid, the tool has significantly increased the value of wind energy. Cloud is currently developing a software product using this model, which is being piloted by French power company ENGIE.
Accelerate groundbreaking science
In addition to optimizing existing infrastructure, scientific innovation is needed to help build a sustainable energy future. One particular area that holds great promise is nuclear fusion, an incredibly powerful technology with the potential to provide limitless carbon-free energy. A fusion reactor is powered by a pressurized plasma of ionized hydrogen that is hotter than the solar core. The intense heat means that this plasma can only be sustained by rapidly adjusted magnetic fields. This is a notorious engineering challenge.
Mastering the magnetic control of plasma is a fundamental part of solving the problem of controlling the fusion process and harnessing the abundant green energy it can provide. So we worked with the Swiss Plasma Center at EPFL to develop an AI system that learned how to successfully predict and control plasma in a tokamak-type fusion reactor. And rather than simply isolating the plasma, it’s ‘sculpting’ it into a variety of experimental shapes.
Bring your challenges to us
To build effective AI solutions, researchers need a solid understanding of the challenges facing people around the world. This includes accessing data that is representative of the problem, working with domain experts to ensure you are building trustworthy systems, following policy guidance on regulatory structures, and finding real-world opportunities to test these systems. For this reason, collaboration with affected communities, scientists, industry experts, regulators and governments is central to our sustainability efforts.
If you are an industry professional or climate scientist who needs to address a specific challenge that can help the world understand, mitigate and adapt to climate change, our Climate and Sustainability team would like to hear from you.
Contact us: contact-gdm-sustainability@google.com