AI for the green transition - Applications and use cases [Part 2]

AI has great potential to accelerate efforts to protect our environment, such as reducing emissions or making  more efficient use of scarce resources. Let’s dive into some examples of use cases - with no ambition to be exhaustive - where AI can help tackle important challenges. 

‍

In a series of blogposts, we will look at 4 dimensions, in line with the EU Green Deal actions, covered in the visual below. In this second blogpost, we will deepdive into the topics of transport and mobility and environment and oceans.

‍

‍

Transport and Mobility

Transport is a critical part of our infrastructure, but it comes with costs such as greenhouse gas emissions, pollution, noise, and congestion. With transport emissions representing 25% of total EU greenhouse gas emissions, the transport and mobility sector faces essential changes on the way to becoming climate-neutral (EU). Let’s explore where AI technology can help this transition:

‍

Journey planning and traffic prediction/management

‍AI allows for predicting and optimising traffic more accurately by making sense of complex variables influencing traffic flow and adjusting and planning traffic flows and journeys in real time. ML6 worked on a project with the City of London, for example, where we visualized data from road sensors and predicted congestion 40 minutes ahead of time, and calculated ripple effects to recommend appropriate actions to the authorities. AI based prediction of traffic volume can be a first step to optimising routes to be more cost- and fuel-efficient, adjusting tolls with smart pricing based on congestion, identifying key bottlenecks for strategic improvement, or helping to solve the last mile delivery problem. Another important way AI can improve resource use and sustainability in trucking and shipment is by optimising backhauls, i.e. empty return trips of unloaded trucks. Multiple AI apps are already tackling this problem, helping companies and drivers to book backhauls efficiently, decreasing empty mileage and reducing emissions.

‍

Connected and Autonomous Vehicles & deliveries

‍Autonomous driving could bring significant mobility changes. While autonomous vehicles are still in their infancy, with a long process towards full autonomy that could take many years, there is potential for autonomous driving for sustainability. Vehicles driven by AI technology can implement eco-driving and energy-saving features and provide more efficient routing. Shared mobility and Mobility as a Service could reduce the need for ownership of cars by sharing cars and rides. This being said, we can currently not assess the net impact of autonomous vehicles, as it will depend on how customer patterns will develop in the future. Increased (empty) trips or increased car ownership could have a negative impact on sustainability, if consumer behaviours change in that direction.

‍

Battery efficiency and EV charging

The number of electric vehicles is expected to grow exponentially. This growth brings along the challenge of organising charging infrastructure,scheduling battery charging, and improving battery efficiency. ML6 and Sarolea worked on the latter, using sensor data from electric motorbikes to improve battery performance. 

‍

Environment & oceans

The agriculture and water sectors have a vital role in preserving the health of our Earth’s natural systems, including biodiversity conservation, ocean health, freshwater quality, biogeochemical flows, forests and land system change, and related impacts on the security of food and water supply. Also here, AI can play a role in managing and preserving essential resources:

Protecting Oceans

‍The use of AI can help to detect illegal activities or suspicious activity in the ocean, such as overfishing or oil spills with the help of satellite data and computer vision, as well as to protect wildlife (e.g. whale detection). Another way AI can help conserve oceans is by fighting plastic pollution by tracking and measuring in much more detail how plastic waste gets into oceans. UNEP’s CounterMEASURE project, for example, developed a model to identify sources and pathways of plastic pollution in the Mekong River using geospatial data and images of plastic waste (Source). We can use the created knowledge to inform policy decisions and actions to reduce plastic pollution. Lastly, in a Christmas project last year, ML6 created an ML model to detect coral, so researchers can better predict the coral's coverage and track its health to better target protective measures. Such models could ultimately help to assess vulnerable reefs and provide early warning and actions to protect them.

‍

Detecting illegal deforestation

‍Illegal logging has significant economic, social and environmental impacts. For the environment, it is associated with deforestation, climate change and a loss of biodiversity (Source). Machine learning methods have become increasingly powerful and accurate to spot even selectively cut down trees from satellite images. As such, ML can help detect illegal logging activity in rainforests, protecting  the indispensable trees that counter climate change.

‍

Water resource prediction and management

‍AI can be used to managewater resources. On the demand side, predicting water use is crucial for reliable water management, increasingly made possible with cheaper sensors that can supply more precise information. We can use AI to decrease water wastage or loss on the supply side. Leakage is a major issue in water distribution systems, and AI can help detect burst pipes or leaks by analysing pressure and sensor signals. A near real-time prediction could help to raise alarms and decrease wastage. Another critical area is water contamination and reducing pollutants by monitoring the water quality with AI. 

‍

Closing statement

While this series of blog posts did not aim to give a comprehensive overview of use cases or domains where AI could help drive sustainability for the green transition, we believe it can be a starting point to inspire uses of AI to help drive forward towards a more sustainable future. In order to ensure AI can have an actual impact, we must put the right processes and structures in place to ensure that an AI solution is not only developed with a strong ethical framework and sustainable practices in mind but also makes it into production and is ultimately adopted and used. 

Of course, AI alone will not be the silver bullet to move to a sustainable world. If we want to transform the current course we are taking, many different factors will have to come together - not least a sense of shared responsibility and true commitment from the private and public sectors.

‍

‍