How AI is helping WWF battle illegal deforestation

19 June 2020 6 min. read

Digitalisation has already had a major impact on the world of business, but now a project helmed by Deloitte has helped the World Wildlife Fund wield new technology in the fight to protect the world’s most fragile ecosystems. Supported by the Deloitte Impact Foundation, the Cognitive Deforestation Prevention programme uses artificial intelligence to prevent illegal deforestation.

According to Mark Boersma, the Senior Manager within Consulting who leads the Deloitte Impact Foundation initiative, the ideas behind the Cognitive Deforestation Prevention began to form five years ago, during a trip to the Indonesian island of Sumatra. During the expedition with his wife, they encountered rare species such as orang-utans and a group of black gibbons, but they were also struck with the serious toll human activity was taking on the shrinking natural world.

Recounting the experience on Deloitte’s website, Boersma said, “I remember that around the rainforest, we were struck with acres and acres of palm oil trees which had often come in place for the less intrusive rubber plantations. This is when I started to think about the effect that our palm oil consumption is having on our world… [When] WWF sent out an open request for proposals for their Early Warning System and I instantly knew that I wanted to be a part of it.”

Cognitive Model Early Warning SystemWWF was looking for a technology partner to improve and scale an existing prototype built by BCG Gamma. The Early Warning System was designed to predict where illegal deforestation will take place in the next six months based on satellite images and other geographical data. This would enable conservationists to act proactively to safeguard threatened habitats, and help aim for a 30% decrease in illegal deforestation by 30%. According to Boersma, the use of artificial intelligence and cloud technology made this a great fit for Deloitte.

Joanne Lijbers works within the AI department at Deloitte. As a data scientist, she is in charge of the modelling part of the solution, and in another blog on the firm’s site, she explained how the Early Warning System predicts and prioritises the areas of potential deforestation, how these areas are prioritised and how the model’s accuracy is ensured.

Lijbers said, “The goal of the project is to predict illegal deforestation before it happens. So far we focused on predictions six months ahead. Using labelled satellite images combined with other data such as the location of forest fires and distance to population, we predict the location and likelihood of deforestation on a 480 by 480 meter level. The predictions are displayed in a user interface. A prioritisation framework instantly lets the users know which predictions need action first.”

Pointing to an example of how this plays out in the tool’s use, Lijbers noted that the solution is currently active in Kalimantan (the Indonesian portion of the island of Borneo). There, it prioritises predictions on whether or not specific species live in an area – such as the orang-utan, or clouded leopard – and how much carbon is stored in the trees which would come under threat.

In terms of accuracy, meanwhile, Lijbers said that her work has focused on “user’s accuracy” and “detection rate.” The user’s accuracy shows the fraction of predictions that turn out to be true 6 months later. By testing different model parameters, input data sets and training methods, Deloitte was able to improve the detection rate by over 30%, while retaining a high user’s accuracy – something which heightens trust in the system, and ensures that its reports are acted upon swiftly.

Cloud implementation

Sebastian Panman de Wit is also part of the AI team at Deloitte. He mainly focused on leveraging cloud technology to bolster the project.

“The amount of data we are working with is huge,” said Panman. “Around 100 gigabytes of raw data is transformed into more than 3 terabytes of information-rich data. Therefore is it important that we use the right technologies for the right tasks. To create a scalable and maintainable solution we work together with Amazon Web Services (AWS) to leverage the Cloud throughout our data pipeline.”

The work saw Deloitte develop a microservice-like infrastructure, where its experts could use the scalability of the cloud to ensure fast data transformations. Simply put, Panman explained, “data transformations take about the same processing times for small amounts of data as for large amounts of data.”

He elaborated, “This allowed us to reduce the total pre-processing time from 12 hours to 4 hours and keep this consistent with larger datasets. Additionally we use other Cloud solutions such as AWS Sagemaker, Lambda Functions and Step Functions to accelerate our Data Science activities. These technologies will make scaling the solution to large landscapes a lot easier!”

Finally, Deloitte looked to ensure that the system in place could deliver its results to users in the quickest, simplest way, to enable a rapid response. Bas Wagenmaker is part of the Visual Analytics team within Deloitte Consulting, and he explained that without the right means to deliver predictions to end-users, the insights of Cognitive Deforestation Prevention might well lose their value, obstructing effective prevention in the process.

User-interface Early Warning SystemWagenmaker explained, “We decided to create a custom user interface by leveraging state-of-the-art technologies and the power of the cloud. As a backbone for the development of this web application, we used open-source software like React and Node.js… Various features were implemented to allow the user to effectively navigate through the predictions. Custom solutions were created to, for example, measure distance and area size, upload and visualise shapefiles and export a geospatial pdf to be used during field visits with no internet connection.”

Stating that this is among the most rewarding projects he has worked on, Wagenmaker added, “One of the initiatives that make working on a project like this possible at Deloitte is the Deloitte Impact Foundation. This initiative allows us to use our professional expertise to make an impact in society. I am very grateful that this initiative is in place and gives us to the opportunity to contribute to preventing illegal deforestation and protecting the world’s rainforests.”