UNU report: Artificial intelligence should not be underestimated when assessing the impacts of climate change
According to scientists at the UN University, AI can bridge the digital divide and support climate protection in countries in the global south.
While climate change impact assessment is critical for implementing equitable mitigation and adaptation measures, it is difficult to conduct at the community level, especially in developing countries and disadvantaged communities. AI could be the answer.
As climate change accelerates, the number and intensity of climate and weather-related disasters are increasing worldwide. UN member states must develop urgent mitigation and adaptation measures based on reliable climate projections.
However, obtaining these projections can prove difficult. Climate change impact assessment models – the primary means of estimating future climate-related impacts – are complex computer models that require specialist knowledge to run and interpret. This specialist knowledge and computing requirements are rare in many regions and local communities. This lack of robust impact assessments puts communities at a disadvantage and makes them more vulnerable to climate change.
A new report by UN scientists encourages the global climate community and UN member states to consider artificial intelligence (AI) as a promising solution to this problem. AI is flexible, computationally efficient, and can run in web and cloud-based services. As AI becomes increasingly popular for a variety of applications, it is likely that soon more people will be able to operate and interpret AI results than the traditional models for assessing the impacts of climate change.
However, AI is not yet fully utilized in the field of climate impact assessment. This motivated researchers at the United Nations University Institute for Water, Environment and Health (UNU-INWEH) to explore the possibilities of AI by conducting a fast, flexible and reliable climate impact assessment for 46 cities in the United States. Their results show that this technique can replace traditional local-level climate impact assessment methods, which are computationally intensive and time-consuming.
“AI is a powerful tool used in almost all sectors, from imaging to medicine. There is no reason why it cannot also be used to strengthen society’s resilience to climate change,” said Dr Renee Obringer, Research Associate for Urban and Interdependent Infrastructure Systems at UNU-INWEH, who led this study.
They report projections that water demand in the 46 modelled cities could increase by as much as 15% and electricity demand by as much as 20%. Cities in the US Midwest are likely to see a median increase in electricity consumption of 20% if global warming exceeds 2.0°C above pre-industrial levels. For the city of Chicago, this equates to 745,000 MWh/month, which is equivalent to the annual electricity consumption of over 26,000 residents of the UK, 98,000 residents of India or 292,000 residents of Nigeria.
In terms of water use, the study found that cities in the Midwest could see a 7.5% increase if global warming is 2.0°C above pre-industrial levels. Since the average U.S. household uses over 1,100 liters of water per day, a 7.5% increase would result in an additional 85 liters of water use per household, or 57 million liters per day for the entire city. That’s the equivalent of nearly 23 Olympic-sized swimming pools – in just one day for just one city.
California cities are expected to see a significant increase in electricity demand, while water demand is expected to increase relatively little. However, some cities in the southern United States may see a decrease in water demand in the summer due to increased rainfall and humidity caused by global warming.
In their report, the UN University scientists show how the concept of “climate analogues” can be used to create cost-effective and understandable forecasts. Based on this concept, they compared each US city studied with another North American city whose current climate matched the best estimate for the US city’s future climate. For example, their results show that New York City’s future climate is closest to the current climate of Jonesboro, Arkansas, a city in the southern US. By using these analogues, the researchers were able to forego complex climate models, leading to further improvements in the accessibility of their AI approach.
Using these analogues is a novel approach that streamlines the process and can be particularly useful for local studies of climate change impacts. “The analogues reduce the computational burden of the AI impact assessment process and eliminate the need for users to create large, complex future climate projections. This is an ideal way for countries, regions and cities to minimise costs and effort when they lack the expertise and capacity for climate simulations,” said Dr Obringer.
The authors make several recommendations to expand the use of AI in assessing climate change impacts, including developing web- and cloud-based services that can be particularly useful in developing countries. However, the report notes that AI relies on high-quality, readily available data – a problem in many parts of the world. So as society seeks to build resilience to climate change through equitable mitigation and adaptation actions, it is critical to ensure that the relevant data and models remain open and freely accessible so that communities can understand their local climate change impacts.
“This report is just a small snippet of how the world can benefit from the technological innovations of the Fourth Industrial Revolution to address the challenges of equity and sustainability,” said UNU-INWEH Director Prof. Kaveh Madani. “AI has its own risks and limitations, but also major benefits that cannot be ignored, especially when it comes to bridging the digital divide and inequality. The lack of computing infrastructure should not prevent nations from taking adequate climate action. AI can help the global South and underserved communities overcome a major barrier and improve their plans to cope with climate change and extreme events.”
Download the report
“Harnessing the power of AI to assess the impacts of climate change”
Media contacts
Kyra Bowman, UNU Communications Director [email protected]
The UNU research team is available for interviews:
Dr. Renee Obringer, Research Associate for Urban and Interdependent Infrastructure Systems, UNU-INWEH, [email protected]
Prof. Kaveh Madani, Director, UNU-INWEH, [email protected]
Report information
Obringer, R., Kumar, R. and Madani, K. (2024). Harnessing the Power of AI for Climate Change Impact Assessment, United Nations University Institute for Water, Environment and Health (UNU-INWEH), Richmond Hill, Ontario, Canada, ISBN: 978-92-808-6120-4 , DOI: 10.53328/INR24ROR012
