How AI is helping make the world greener
The AI revolution could be the key to a greener, cleaner planet, as these incredible smart solutions are proving.
This article is sponsored by Microsoft. As part of its AI for Good Cohort programme, Microsoft is supporting organisations using innovative technologies to solve the world’s biggest challenges, empowering them to create a more sustainable planet through AI.
Artificial Intelligence (AI) is here, and it’s already changing the shape of many industries and seeping into daily life. In our previous article, we’ve explored how AI (Artificial Intelligence) is helping open up the digital world for people with disabilities. But AI is also being used to solve some of the biggest challenges facing the world right now – namely, how to prevent environmental crises and accelerate sustainability and conservation efforts.
AI’s main is goal is to identify patterns in vast swathes of data, continuously refining its understanding as it ‘learns’ new information. Many environmental problems involve understanding complex natural systems and processes, and this is where the ability of AI to recognise patterns, learn from data and unlock powerful new insights is starting to break through many barriers.
Below, we’ve highlighted some of the ways in which AI is being used by researchers, companies and non-profit organisations on the front lines of sustainability.
Monitoring endangered species
It’s estimated that at least 10,000 species go extinct every year, with so many animal species vulnerable to poaching, habitat loss and climate change. Protecting biodiversity is a very real and serious challenge, but fighting extinction requires a tremendous amount of data, including population size, location and migration patterns.
Gathering this data manually is time-consuming and expensive, making citizen engagement critical to data collection efforts. That’s where AI is stepping in, as in the case of Wild Me – a project that uses computer vision and deep learning algorithms to create a platform called Wildbook, which scans millions of crowdsourced wildlife images at scale.
AI hosted on Microsoft Azure can identify the species as well as the individual animal, and the public can follow the movements of their favourite animals. The aggregated data is used by scientists to help inform conservation decisions.
Using water more efficiently
Over 2 billion people worldwide live in countries already experiencing water scarcity, and it’s estimated that hundreds of millions more could be displaced as a result by 2030 should climate change continue, let alone the issues that billions face from water pollution.
While AI in water management is in its early days, machine learning models are starting to be applied to this vital area. Researchers around the world are using AI to understand and predict risks to water quality, forecast groundwater levels and even predict floods.
A great early example is IBM China’s AI tools that are helping alleviate much of the work in monitoring waterways and recognise illegal fishing, floods and pollution.
Forestry is one of the world’s most complex professions, involving many strategic decisions. It’s essential for conservationists, governments, and landowners to inventory forests for ecological, social and economic health. By utilising AI, cloud software, and machine learning these groups can work together to study the effects of climate change and improve habitats.
SilviaTerra is a project combining high-resolution satellite imagery, and US Forest Service inventory and analysis field data to train machine-learning models to measure forests. Terabytes of high-resolution photos can then be used to aid decision making about these vital ecosystems and protect them for future generations.
Keeping air clean
Air toxicity is affecting billions around the world, with a staggering 93% of the world’s children breathing air that is hazardous to health.
Launched in 2014, IBM’s Green Horizons project is using real-time data from optical sensors combined with AI to track various pollutants such as ozone, sulphur dioxide and particulates, analysing historical and real-time data from thousands of sources.
The project has been trialled in China, India and South Africa and is helping city authorities build a better picture of what pollution will look like the following day, so that authorities can issue public health warnings well in advance.
So far the project has helped the Beijing government cut deadly airborne pollution by 20% in less than a year as part of China’s clean air action plan.