Blog 1 | Cognitive Deforestation Prevention | Deloitte Impact Foundation

Article

Blog 1: Setting up the tech consortium

Blog 1/4 from the series about the Deloitte Impact Foundation initiative ‘Cognitive Deforestation Prevention’ that aims to prevent illegal deforestation by building an artificial intelligence solution that predicts where illegal deforestation will happen

Mark Boersma, Senior Manager within Consulting leads the Deloitte Impact Foundation initiative Cognitive Deforestation Prevention. In this blog he talks about the Early Warning System and how Deloitte is involved in this initiative. He talks about the initiative’s ambition, its first achievements and the next steps.

Early Warning System

Mark: “This project really started around five years ago for me: when my wife and I trekked through the Sumatran rainforests for three days. I remember trotting through the dense forest in jungle gear and numerous encounters with wildlife including the orangutan and a rare sighting of a group of black gibbons. But I also 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.


WWF sent out an open RfP for their Early Warning System and I instantly knew that I wanted to be a part of it. The Early Warning System predicts where illegal deforestation will take place in the next six months based on satellite images (radar technology) and other geographical data. Its unique selling point is that it helps to anticipate illegal deforestation – proactively, before it’s too late! 

Deloitte’s tech consortium

WWF was looking for a tech partner to improve and scale an existing prototype built by BCG Gamma. The ambitious goal setting - the program aims to decrease illegal deforestation by 30% at deforestation fronts - and the use of artificial intelligence and cloud technology make this a great fit for Deloitte. 


To take on such a fundamental global challenge we believe that we should team beyond our own organization, therefore a tech consortium was set up with Jheronimus Academy of Data Science (JADS), Utrecht University (UU) and Amazon Web Services (AWS) to take on this fundamental global challenge. JADS and UU provide leading researchers in AI and Data Science, supervise two master students and participate in JADS’ Data Entrepreneurship in Action course and we expect that the research component will increase in scope further. AWS provides their cloud platform and key subject matter expertise on the optimal use of their own technology. 


Deloitte is the motor of the tech consortium: actually building and optimizing the Early Warning System with Cloud, A.I. and geo-visual expertise. The tech consortium works closely with WWF who leads the EWS program and all consortium partners are providing substantial in-kind investments.

Achievements

Since January of this year, the Early Warning System has made leaps and strides of progress. The geographical scope has been expanded from Central Kalimantan to a wider area of Borneo over four times as big, including Sarawak (Malaysia). All thirteen initial site visits in the pilot area in Central Kalimantan showed signs of possible deforestation. We were able to increase the scalability of the solution through use of cloud-native AWS technologies, improve the model and enhance the user experience by developing a fully custom frontend powered by MapBox. I invite you to read the in-depth articles of my colleagues here

Next steps

The current pilot in Central Kalimantan has been put on hold temporarily due to the COVID-19 outbreak, but we are looking forward to restarting it, and continuing our journey in multiple other deforestation fronts.

As you can imagine, I am still very proud to lead the EWS tech consortium and work closely with WWF and the much wider ecosystem of governments and local actors. I look forward to increasing the impact and scope of this initiative!”

Did you find this useful?