From vacuuming the kitchen and driving cars to reading and writing, artificial intelligence (AI) and machine learning
are
increasingly being used to save humans time.
But can these technological innovations help us save the planet?
One of the main challenges facing humanity today is how to stop deforestation and ensure that our forests are restored and managed sustainably.
We know the difference this would make in the battle against climate change and in improving the livelihoods of local people.
But despite enormous efforts around the world, we have not made it happen.
More information
40% of companies and banks linked to deforestation do not take measures to stop it, according to a report
The problem lies in the magnitude of the task.
Since 1990, more than 420 million hectares of forest have been lost to deforestation and converted to other land uses, such as farmland, mines, or infrastructure.
Even though deforestation rates have slowed, we are still losing 10 million hectares every year.
How can we reduce this figure to zero by 2030, as world leaders have committed to doing?
And furthermore, how do we restore the 1 billion hectares of degraded land and forests, as these same leaders have pledged to do?
The answer is that we need to know much more about what is happening in real time on the ground, in each forest and, in some cases, each tree.
Only then will we be able to take much more effective measures, everywhere and quickly enough.
This is where AI comes into play.
For a long time, active monitoring of remote and inaccessible forest areas has been difficult, providing windows of opportunity for illegal activities that have resulted in deforestation and degradation.
But the window of time in which illegal activity can go undetected is rapidly shrinking, thanks to the rapid evolution of satellite imaging technology and the creative use of artificial intelligence and machine learning to read the images and turn them into
information
.
We now have high spatial and temporal resolution satellite images thanks to Norway's International Forest and Climate Initiative, and algorithms that can interpret these images in a matter of hours.
This means that forest authorities can receive an alert through the Food and Agriculture Organization of the United Nations (FAO) SEPAL program within two days of something unusual happening in their forests.
Before, it could take two or three months, too late to intervene.
The impact this can have on efforts to crack down on illegal activities in forests around the world should be noticeable as countries begin to use this technology in the coming years.
In some parts of the world, such as the arid African Sahel region, it is individual trees, rather than forests, that matter.
They are appreciated by local communities for the benefits they provide, but are threatened by climate change, conflict and other factors.
Logistically, it is not feasible for field staff to monitor every tree in this vast region.
But from heaven, now we can.
FAO and its partners have been mapping the region's baobabs, which are particularly prized for their nutritious fruits.
Satellite images are now available with sufficient resolution to identify individual trees and monitor their growth.
Drones can provide images of a small area with enough detail to identify baobab species.
Subsequently, the phenological information of those species (i.e., seasonal patterns of greening and senescence) can be used to
train
AI and machine learning to identify and monitor those species over wider areas.
By combining these technologies, FAO has developed a system that should ultimately provide communities and governments in 14 countries with the information they need to better restore and protect each baobab tree.
At the same time, local experts can feed into the system to improve existing data or provide new information to
train
the AI to perform other tasks, such as predicting productivity or warning when a tree is not developing leaf buds. as it should.
In addition, the Forest Data Partnership, a collaboration funded by the US Agency for International Development (USAID), FAO, the World Resources Institute, Google, NASA and Unilever, is using AI and machine learning to harmonize conflicting data.
Over the next five years, this collaboration will develop a scientifically robust and transparent global system to check the deforestation footprint of any packet of coffee or chocolate bar sold around the world.
Having adequate information and being able to distribute it globally is crucial so that we can all make the right decisions in our daily lives.
And AI can be the game changer we need to make it happen.
Julian Fox
and
Anssi Pekkarinen
are forestry officers at the Food and Agriculture Organization of the United Nations.
You can follow PLANETA FUTURO on
,
and
, and subscribe
here
to our 'newsletter'
.