Deforestation Connection Prediction Intervention Preservation

Preserving the world’s rainforests by predicting deforestation

How AI powers a sustainable future

In an ever more complex world, multi-disciplinary collaboration is key to preserving the world’s rainforests. At Deloitte, collaboration is a rule we live by. Connect for impact, as we say. It’s how we helped the World Wide Fund for Nature (WWF) further develop an AI-powered online tool that can predict where deforestation will occur.

Over the last decades, more than half of Indonesia’s tropical rainforests have vanished, mainly due to palm oil cultivation, gold mining, logging and creation of arable land. To preempt further deforestation, WWF, Deloitte and a consortium of public an private entities have developed a tool that predicts deforestation through automated assessment of spectral satellite imagery and other geospatial data. The first phase of this pilot, part of the WWF Forest Foresight programme, ran from 2020 onwards in Kalimantan (part of the island of Borneo).

Because of the vast amounts of data our AI-model needed to process, we migrated the initial prototype to a cloud-native, scalable configuration. This allowed us to cut data processing time from twelve to four hours and significantly speed-up prediction generation for the entire island of Borneo (which harbours 425,124 square kilometers of rainforest). 

WWF: click the photo to visit the official website

Much of the input data consist of pixelated spectral satellite imagery. In order to generate predictions, our AI-algorithm asks a determined set of question for all the pixels in a landscape. To elucidate how the AI performs its task, one of our modelling specialists makes the following comparison: “Pretend you’re in a random spot within the vast Borneo rainforest, and ask yourself the question: how likely will deforestation occur here? You then assess: is deforestation happening close to me? How closeby is the nearest town? Would an illegal logger be able to transport the wood over roads or canals? Or easily build a (short) logging road? Can palm oil be processed in a mill nearby?”

The resulting predictions are then visualized in a web app, accessible to local government officials and other partners. In Gabon, where we also ran a pilot programme, rangers have actually visited specific sites, confirming that predictions had come true. This allowed them to make targeted interventions on the ground and preserve rainforest that would otherwise have perished.

 

We are proud to have successfully predicted deforestation in Kalimantan, Malaysia, Gabon, Surinam and Guyana, laying the ground work for preservation of ancient tropical rain forests, in close collaboration with local governments. Currently, our focus is on harvesting as much feedback from these projects as possible, in order to build a better system of prediction, intervention and – ulimately – preservation. A system that is both effective and scalable in the long run.

At Deloitte we are committed to helping our partners shape their business operations in a sustainable way. It’s how we make a global impact on the environment and the future of tropical rainforests. Together with the WWF. And together with you.

Connect for impact.