How We’re Applying the Latest AI Developments to Help Fight Climate Change and Build a More Sustainable, Low-Carbon World

AI is a powerful technology that will transform our future, so how can we best apply it to help combat climate change and find sustainable solutions? Our climate & sustainability lead, Sims Witherspoon, recently shared insights on how AI can accelerate our transition to renewables, stating, “Climate change is a multifaceted problem with no single solution. We need to move beyond discussing what we can do and start focusing on how we can do it.”

The effects of climate change on Earth’s ecosystems are incredibly complex. As part of our effort to use AI for solving some of the world’s most challenging problems, here are some of the ways we’re working to advance our understanding, optimize existing systems, and accelerate breakthrough science in relation to climate change and its effects.

Understand Weather, Climate, and Their Effects

A better understanding of the core problems and their effects is a critical first step in tackling climate change. In collaboration with the UK Met Office, we developed a precipitation nowcasting model to gain deeper insights into changing weather patterns. This nowcasting model offers greater accuracy than the existing state of the art, making it a preferred choice among the Met’s expert meteorologists. Our climate and weather research spans short-range (under two hours) to medium-range (ten days) forecasting, significantly impacting how we optimize renewable energy systems.

From modeling the behavior of animal species across the Serengeti to supporting machine learning initiatives that advance conservation projects in Africa, we’ve been instrumental in helping scientists track and better understand the impacts of climate change on ecosystems and biodiversity. Additionally, our team is enhancing AI systems used to identify bird songs in Australia, advancing tools that monitor changing wildlife at scale.

Moreover, we’re partnering with the non-profit Climate Change AI to address critical gaps in climate-related data. Currently, this partnership focuses on compiling a comprehensive wishlist of datasets whose availability would significantly bolster AI solutions for climate change. We will share this wishlist with the community when it is complete.

Optimize Existing Systems

As we transition to more sustainable infrastructure, it’s vital to optimize the systems that the world depends on today. Today’s computing infrastructure, which includes AI itself, is energy-intensive. To tackle some of these challenges, we’ve been developing AI that enhances existing systems, such as optimizing industrial cooling and creating more efficient computer systems.

Since our energy grids are not yet powered by clean energy, it’s essential to use our resources as efficiently as possible while transitioning to renewables. Accelerating the global shift to renewable energy sources can substantially reduce carbon emissions. In 2019, our climate & sustainability team collaborated with experts at a Google-owned wind farm to increase the value of wind energy. By developing a custom AI tool to better predict wind power output and recommending commitments to supply this anticipated energy to the electricity grid, we significantly boosted the value of wind energy. Our Cloud team is now developing a software product based on this model, currently being piloted by a French power company.

Accelerate Breakthrough Science

To build a sustainable energy future, we need scientific breakthroughs. One promising area is nuclear fusion, an incredibly powerful technology that has the potential to deliver limitless carbon-free energy. Fusion reactors operate on a pressurized plasma of ionized hydrogen that is hotter than the core of the sun. The intense heat requires the plasma to be contained by a rapidly adjusted magnetic field, presenting a notable engineering challenge.

Mastering the magnetic control of plasma is crucial for addressing the challenges of nuclear fusion and harnessing the abundant green energy it could provide. To that end, we collaborated with the Swiss Plasma Center at EPFL to develop an AI system that learns to predict and control plasma in a tokamak-style nuclear fusion reactor, allowing for the ‘sculpting’ of plasma into various experimental shapes.

Collaboration is Key

For effective AI solutions, researchers require a comprehensive understanding of the challenges faced by communities globally. This involves accessing data that truly reflects the issues, collaborating with domain experts to ensure the reliability of our systems, adhering to policy guidance on regulatory matters, and identifying real-world testing opportunities. Therefore, collaboration with affected communities, scientists, industry professionals, regulators, and governments is vital to our sustainability efforts.

If you are an industry expert or climate scientist facing a specific challenge that could enhance our understanding, mitigation, or adaptation to climate change, our climate & sustainability team is eager to connect with you.

Get in touch: contact-gdm-sustainability@hotnchill.com