How we apply the latest advances in artificial intelligence to assist fight climate change and build a more sustainable, low-carbon world
Artificial intelligence is a powerful technology that will change our future. So how can we best apply it to assist fight climate change and find sustainable solutions?
Our Climate and Sustainability Leader, Sims Witherspoon, recently spoke about how AI can accelerate our transition to renewable energy sources at: TED countdown, explains: “Climate change is a multi-faceted problem with no single solution. We need to move beyond discussion What we can do and start focusing on it How we can do it.”
The impact of climate change on Earth’s ecosystems is incredibly complex, and as part of our efforts to use artificial intelligence to solve some of the world’s most challenging problems, here are some of the ways we are working to deepen our understanding, optimize existing systems, and accelerate breakthrough climate science and its effects.
Understanding weather, climate and their effects
A better understanding of the underlying problems and their impacts is a crucial first step in the fight against climate change. Working with the UK Met Office, we have developed a rainfall forecast model to better understand changing weather. This forecasting model is more accurate than the current knowledge and is strongly preferred by expert meteorologists at the Met. Our climate and weather research covers short-term (less than two hours) and medium-term (ten days) forecasts that can have a huge impact on how we optimize renewable energy systems based on natural resources.
From modeling the behavior of animal species in the Serengeti to supporting machine learning projects that accelerate conservation projects in Africa, we help scientists track and better understand the impacts of climate change on ecosystems and biodiversity. In the future, our team will also use the artificial intelligence systems they are accustomed to recognizes birdsong in Australia, helping to improve tools that monitor a changing nature on a large scale.
Moreover, we cooperate with non-profit organizations Climate change AI to fill important climate-related data gaps. The partnership is currently focused on creating a comprehensive wish list of datasets whose availability would enable advancements in AI solutions to address climate change. Once complete, we will make this wishlist available to the wider public.
Optimize existing systems
As we transition to more sustainable infrastructure, we must optimize the systems on which today’s world depends. For example, today’s computing infrastructure, including artificial intelligence itself, is energy intensive. To help solve some of these problems, we are developing artificial intelligence that can improve existing systems, including optimizing industrial cooling and increasing the performance of computer systems.
Given that our energy networks are not yet powered by clean energy, it is important that we use our resources as efficiently as possible as we work to transition to renewable energy sources. Accelerating the global transition to renewable energy sources could also significantly reduce carbon emissions.
In 2019, our Climate and Sustainability team worked with domain experts at a Google-owned wind farm to drive the value of wind energy – ultimately with the goal of supporting growth across the broader industry. By developing a custom AI tool to better predict wind power and another model that recommends commitments to deliver the predicted energy to the power grid, the tool has significantly increased the value of wind energy. Cloud is currently developing software using this model, piloted by French energy company ENGIE.
Accelerate breakthrough science
In addition to optimizing our existing infrastructure, we need scientific breakthroughs to assist us build an energy-sustainable future. A particular area that holds great promise is nuclear fusion, an extremely advanced technology that has the potential to provide unlimited carbon-free energy. Fusion reactors are powered by compressed plasma of ionized hydrogen, which is hotter than the core of the Sun. The intense heat means the plasma can only be held in place by a rapidly adjustable magnetic field, which is an extremely tough engineering challenge.
Mastering magnetic control of plasma is an vital part of the solution to the problem of controlling nuclear fusion and harnessing the profuse green energy it can provide. That’s why we worked with the Swiss Plasma Center at EPFL to develop an artificial intelligence system that learned to effectively predict and control the plasma in a tokamak fusion reactor. And not only to contain the plasma, but also to “sculpt” it into a series of experimental shapes.
Bring us your challenges
To create effective AI solutions, researchers need a solid understanding of the challenges facing people around the world. This includes gaining access to data that is representative of the problems, collaborating with subject matter experts to ensure we are building strong systems, following regulatory framework guidelines, and finding real-world opportunities to test these systems. For these reasons, collaboration with interested communities, scientists, industry experts, regulators and governments is critical to our sustainability efforts.
If you are an industry expert or climate scientist with a specific challenge to solve that could assist the world understand, mitigate or adapt to climate change, our Climate and Sustainability team would love to hear from you.
Contact us: contact-gdm-sustainability@google.com