Should AI’s Role To Cut Greenhouse Gas Emissions Be Greater?

Sign up for daily news updates from CleanTechnica on email. Or follow us on Google News!

Scientists warn that heat waves, floods, droughts, and severe storms will get far worse in the decades ahead unless we change course. Looking ahead, could AI’s role in developing new climate models save us many gigatons of carbon emissions?

In 2023, there were 25 confirmed weather/climate disaster events with losses exceeding $1 billion each to affect the US, according to the National Centers for Environmental Information.These events included 1 drought event, 2 flooding events, 19 severe storm events, 1 tropical cyclone event, 1 wildfire event, and 1 winter storm event. Overall, these events resulted in the deaths of 482 people and had significant economic effects on the areas impacted.

AI’s role in the struggle against climate change is already prominent and is also controversial. While it seems evident that AI can serve in the pursuit of a greener future, checks and balances that ensure fairness and equity must be implemented.

For decades, scientists looked at climate prediction models based largely on the rules of physics and chemistry to forecast weather patterns. Now hybrid-based models consider machine learning and other generative AI tools which help climate scientists create even more accurate and precise systems. For example, doctoral students who are working with officials from the Tennessee Valley Authority to provide a more accurate hybrid-based flood prediction system than the one they are using that is based solely on physics.

AI can help to build an inventory in which it automates data collection for things like flood risk or regulatory status – making unstructured data into structured data that will help people to intelligently explore and design.

“In the next 12 months, we are going to see more and more efforts where data-driven systems and artificial intelligence come together,” says Auroop R. Ganguly, professor of civil and environmental engineering and director of AI for Climate and Sustainability at Northeastern’s Institute for Experiential AI.

Businesses, too, have been incentivized over the past years to use more AI-based tools. It will take diligence to continue to refine the best practices of what it means to use AI responsibly and integrate ethics adequately into the innovation process.

Why is AI’s Role in Climate Change so Essential?

One such tool is the ICEF (Innovation for Cool Earth Forum) roadmap, a document that was designed to facilitate dialogue at COP28 in December, 2023. The authors could have asked, “How could AI contribute to climate change adaptation?” or “Will the broad societal forces that AI may unleash more likely to help or hinder the response to climate change?” However, the ICEF limited its inquiry to, “Can AI help cut emissions of greenhouse gases?”

Because the relationship between AI and climate change is a big topic, and because you may have missed this roadmap with all the information that poured out of COP28, let’s examine some of the highlights of “Artificial Intelligence for Climate Change Mitigation Roadmap.”

Artificial intelligence (AI) is the science of making computers perform complex tasks typically associated with human intelligence, according to the ICEF. Modern AI relies on machine learning, which is a type of software in which algorithms detect patterns from large datasets without being explicitly programmed. This is different from traditional software, which requires explicit programming of domain knowledge. AI, instead, relies on implicit programming by using historical data and simulations to train models to extract patterns.

Access to large, high-quality datasets is important for complex real-world applications of AI. These data can come from various public and private sector organizations. Tabular, time series, geospatial, and text data are all commonly used in AI. Data must be properly measured, digitized, and accessible for AI applications.

AI is making important contributions to scientific understanding of climate change. AI is improving climate-model performance, providing more advanced warning of extreme weather events and helping attribute extreme weather events to the increase in heat-trapping gasses in the atmosphere. AI is analyzing vast amounts of data from earth-observation satellites, airplanes, drones, land-based monitors, the Internet of Things (IoT), social media, and other technologies to improve understanding of greenhouse gas emissions.

Power Sector: AI’s role in addressing generation infrastructure, transmission and distribution networks, end-use sectors, and energy storage are substantial.Examples include:

• determining the optimal size and location of solar- and wind-power projects;
• predicting weather relevant to solar and wind generation;
• improving fault detection, outage forecasting and stability assessments on distribution grids; and,
• facilitating deployment of demand response and vehicle-to-grid (V2G) programs.

ICEF notes that several barriers limit adoption of AI for decarbonizing the power sector. They say that AI models and methods are not yet sufficiently robust or well-developed for widespread deployment, standards for performance evaluation are lacking, and knowledgeable workers are in short supply. Security risks must be studied and properly addressed before deploying AI for most grid infrastructure.

Manufacturing: AI can help decarbonize manufacturing by enabling manufacturers to adapt to production issues faster and better, avoid past mistakes by leveraging historical data, improve production yields, promote recycling and circularity by adapting to variable recycled feedstocks, minimize energy consumption, adopt alternative energy sources, and optimize manufacturing schedules and supply chains to reduce logistical overhead.

Materials innovation: In some cases, AI models can replace fully science-based computations, greatly speeding up processing times. AI can also help interpret results of material-characterization experiments, enabling rapid, high-throughput testing of advanced materials candidates. Natural language AI can scour the vast materials-science technical literature, summarizing thousands of published research articles to enable rapid, accurate literature reviews and surface harmonized process steps for materials production.

Food systems: AI has significant potential to help reduce GHG emissions in food systems, including by:

• integrating data from multiple sources—such as soil sensors and satellites—to recommend fertilizer application schedules that mitigate nitrous oxide emissions while maximizing crop yields;
• anticipating future needs for precision fertilizer applications under a range of projected climate conditions;
• analyzing data on biomass characteristics, growth rates and carbon-sequestration potential to optimize feedstocks for biomass carbon removal and storage;
• increasing renewable energy generation by optimizing land use for multiple purposes;
• forecasting pest and disease pressure;
• developing alternative protein products, which have a much lower carbon footprint than animal-sourced foods; and,
• reducing food loss and waste through intelligent harvest-timing to prevent food spoilage.

AI’s role in responding to climate change now includes greenhouse gas emissions monitoring, the power grid, manufacturing, materials innovation, the food system, and road transport. The ICEF recommends that:

• AI tools should be integrated into many aspects of climate change mitigation.
• AI skills-development and capacity-building should be a priority in all institutions with a role in climate mitigation.
• Educational institutions at all levels should offer courses relevant to AI.
• Governments and foundations should launch AI-climate fellowship programs.
• Government agencies with responsibility for climate issues should regularly review their staffs’ AI capabilities.
• All organizations working on climate mitigation should require minimum AI literacy from a broad cross-section of employees.
• Governments should assist in developing and sharing data for AI applications that mitigate climate change.
• Governments should systematically consider opportunities to generate and share data that may be useful for climate mitigation.
• Governments should establish policies to promote standardization and harmonization of climate and energy-transition data.
• Governments should establish climate-data task forces composed of key stakeholders and experts.