Addressing Climate Change with AI

World leaders, activists, and experts are gathering in Glasgow, Scotland for the 2021 United Nations Climate Change Conference, also known as COP26, to discuss and address the greatest threat of our time — climate change. From protests to international agreements, delegates from around the world are vocalizing their demand for action and are taking steps to mitigate the consequences of this exacerbating crisis.

In this larger conversation about solutions to climate-related issues, it is relieving and exciting to see how artificial intelligence can be harnessed to tackle the challenge of reducing emissions and responding to climate crises. For instance, ClimateChangeAI, an organization dedicated to leveraging machine learning for impactful work in climate change, has worked in concert with other organizations, such as the Centre for AI and Climate and the German Federal ministry, to increase awareness and bring information about the intersection of AI and climate action to COP26.

At a high-level, AI refers to the simulation of human intelligence in machines that are programmed to think like humans, meaning that a machine can then exhibit traits associated with the human mind, such as problem-solving and learning. One of the key functions of AI, as a result of this human-like logical reasoning and intelligence, is making predictions. After the machine has been trained on a historical dataset, it can create an algorithm that can then be applied to new data, thereby forecasting the likelihood of a particular outcome. Therefore, in the context of climate action, AI can be leveraged to make highly accurate and useful predictions, which will enhance preparation and response. Some examples of this may be:

  • Using machine learning to guide crop yield prediction, which can help farmers predict crop demand and decide what to plant at the beginning of the season (agriculture makes up a large portion of greenhouse gas emissions and improving modern industrial agricultural practices to be more precise can help limit these emissions);
  • Making far more detailed and precise predictions about extreme events, which may help improve re-designing infrastructure for those at risk; and,
  • Creating personalized predictions on a household’s emissions to create uniquely-tailored interventions at the individual carbon footprint level.

Already, we are starting to see examples of these applications. Recently, Columbia University with funding by the National Science Foundation launched an AI-based climate modeling center called Learning the Earth with Artificial Intelligence and Physics (LEAP). The Center will use big data and machine learning, specifically leveraging existing algorithms and creating new ones, to improve climate projections. Google AI, a division at Google focused on conducting research related to AI, has also been leveraging machine learning to improve its flood forecasting system called HydroNets in India and Bangladesh.

Additionally, AI can be used in unexpected ways, such as through natural language processing (NLP) — a process that studies how machines understand the human language and makes sense of text to perform tasks such as topic classification or translation. NLP can be used to analyze political texts and legislation to inform the study of climate change policies, or social media data like tweets to understand the public discourse on climate change. These insights gained from the application of AI may help facilitate behavioral change and political action on climate issues.

Given the breadth of the applications of AI, there are more opportunities beyond what’s discussed above — from robotics to computer vision to generative modeling — to leverage this technology against climate change. Furthermore, although there are some advantages to the use of AI, there are some harms as well which need to be considered. AI is not the panacea to the climate crisis, and it also has the potential to accelerate environmental harm and increase carbon emissions. There will need to be a nuanced and active discussion among policymakers, climate scientists, activists, and other stakeholders about the advantages and disadvantages to using AI for climate action.

Here at Persolv AI, we hope to provide everyone (including non-coders who are interested in policy, history, and humanities, etc.!) with the technical fundamentals to start thinking about the future applications of AI in the battle against climate change. At the end of the program, students are able to work with their mentor on a research project, which provides them with an opportunity to apply learned concepts over the course of the program to their own areas of interest. Former projects have touched on the issue of climate change, such as the efficiency of windmills and other renewable energy sources.

Persolv AI Bootcamp, a class taught by a handful of Stanford Lecturers and Teaching Assistants, will provide you with the most applicable fundamentals of Artificial Intelligence and Machine Learning to engage meaningfully on the impact of AI.




Stanford ’19, Editor-in-Chief, Persolv AI

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium


Tiny four-bit computers may enable neural nets to be trained directly on smartphones

Respeecher Interviewed in LinkedIn Course ‘Understanding the Impact of Deepfake Videos’

AI Content Generator Ultimate Guide in 2022 | Clear your Doubts!


Grandpa, Do you want to know about Machine Learning?

A chat bot for one

A Practical Guide for Creating Chatbot Content

How can emotional support be provided through communicating with Artificial Intelligence?

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Irene Kim

Irene Kim

Stanford ’19, Editor-in-Chief, Persolv AI

More from Medium

For Consideration: ESGC instead of ESG

Meet JuneBrain 🧠🥽

Limits to growth: identifying sustainability opportunities using the producer price index