AI has already had a substantial positive influence in the battle against global warming. However, quantifying its significance and characterizing its effects remain open problems. 

This article provides an overview of AI-reliant initiatives and projects for understanding and combating climate change, highlights existing research documenting the potential positive impact of AI on climate change, and identifies a set of obstacles to be overcome to ensure such use of AI is both practical and ethically sound.

Climate change problem

Climate change will profoundly affect environments, societies, and economies. Many of its environmental repercussions, from prolonged droughts to more devastating storms, are already being seen.

Eighty-seven per cent of business and public sector CEOs with decision-making power in AI and climate, according to a 2022 BCG Climate AI Survey report, think AI is a crucial instrument in the battle against climate change. In the same survey, public and private sector leaders ranked mitigation (reduction) as the most critical commercial benefit of climate-related advanced analytics and AI, with mitigation (measured emissions) coming in at 57%. The remaining percentages are split as follows:

• 44% in adapting to climate change (hazard forecasting)
• 42% in adapting to climate change (vulnerability and exposure management)
• 37% in mitigating climate change (emissions removal)
• 28% in fundamentals (facilitating climate research, climate finance, and education)

Existing solution

To get a good idea of how urban areas are affected by climate change, we need to look at them from many angles. Some are soil and water surface temperatures, weather events, and the number of plants and ice on the ground. Using these parameters, many climate models can figure out what the weather will be like in a region. Earth System Models (ESMs) and Global Climate Models (GCMs) are two of the most important models that are often used in this field (GCMs). ESMs have all the same parts as GCMs, but they also simulate the carbon cycle and other chemical and biological cycles that are important for figuring out how much greenhouse gas will be in the air in the future. In addition, ESM models simulate environmental indicators in large computational domains, so we can use them to predict large areas.

• Researchers from Finland, Sweden, and Canada ran higher-resolution ESM simulations. They discovered flow-blockage effects that were very relevant to the global climate behaviour and were absent from the coarse cases.
• Researchers from the US also spoke about this problem and reported that global models (or large-grid models) produce minimal accurate findings when applied in a smaller area.
• Simulating a variety of scenarios based on the characteristics of a particular location would be the best approach to make forecasts, according to academics from the University of Washington Seattle and other universities.
• Research conducted in Ireland looked at various data types that we should gather in smart cities to understand better the causes and impacts of human activity on the environment.
• Researchers from the United Kingdom suggested we could utilize ISO (International Organization for Standardization) smart-city indicators (ISO 37122:2019 Sustainable cities and communities, Indicators for smart cities) to determine which measurements must be collected to track the sustainable development of cities.
• Italian researchers demonstrated that it is possible to estimate and follow changes in the urban heat island effect by measuring the surface heat stress of cities using satellite sensors.
• German researchers have proposed using remote sensing photos to measure water quality and levels, soil and water surface temperatures, biomass, carbon, and air quality.
• Researchers from Spain, Sweden, and the Netherlands have demonstrated that we can utilize coarse data in conjunction with high-fidelity turbulent flow simulations. This study builds confidence in the future potential of high-fidelity flow and climate prediction using remote-sensing imagery and AI models.

Conclusion

The technology is already used to create greener smart cities in China, monitor deforestation in the Amazon, and deliver natural catastrophe alerts to Japan. Additionally, AI applications could optimize the deployment of renewable energy sources by supplying solar and wind energy into the electrical grid as needed, increasing power storage, and designing more energy-efficient structures. On a lesser scale, it might assist families in reducing their energy consumption by automatically turning off lights when not in use or rerouting electricity from electric cars to the grid to fulfill expected demand.