However, as with Amazon, identifying problem areas only takes you so far if you don’t have enough resources to act on these findings. The Nature Conservancy uses its AI model to inform conversations with land managers about potential threats to wildlife or biodiversity. The implementation of conservation in the Mojave Desert is overseen by the U.S. Land Management Office, which has only about 270 rangers and special service agents.
In northern Europe, the company Iceye began monitoring the accumulation of ice in the waters near Finland with microsatellites and machine learning. But in the last two years, the company began predicting flood damage using microwave wavelength images that can be seen through the clouds at any time of the day. The biggest challenge now, says Iceye vice president of analytics Shay Strong, is not spacecraft engineering, data processing or the development of machine learning models that have become commonplace. These are institutions caught up in centuries-old ways of doing things.
“We can understand more or less where things will go, we can acquire images, we can produce an analysis. But the piece we have the biggest challenge with now is still working with insurance companies or governments, ”he says.
“This is the next step in local coordination and implementation needed to take action,” said Hamed Alemohammad, chief data scientist at the non-profit Radiant Earth Foundation, which uses satellite imagery to address sustainable development goals. how to end poverty and hunger. “That’s where I think the industry needs to put more emphasis and effort. It’s not just a fantastic blog post and a deep learning model. “
It is often not just a matter of incorporating political leaders. In a 2020 analysis, a group of academic, government and industry researchers highlighted the fact that the African continent has most of the world’s uncultivated arable land and is expected to account for much of the world’s growth. world population in the coming decades. . Satellite imagery and machine learning could reduce dependence on food imports and turn Africa into a barn for the world. But, they said, lasting change will require an accumulation of professional talent with technical expertise and government support so that Africans can manufacture technology to meet the needs of the continent instead of importing solutions from elsewhere. “The road from satellite imagery to public policy decisions is not easy,” they wrote.
Labaly Touré is the co-author of this article and head of the geospatial department of an agricultural university in Senegal. In this sense, and as the founder of Geomatica, a company that offers automated satellite imaging solutions for farmers in West Africa, he has seen that satellite imagery and machine learning help those responsible for decision-making in recognizing how salt flow can affect irrigation and influence crop yields. He has also seen that it helps to solve questions about how long a family has been on a farm and helps with land management issues.
Free satellite imagery of services like NASA’s LandSat or the European Space Agency’s Sentinel program is sometimes enough, but some projects require high-resolution photos of commercial vendors and the cost can be high. a challenge.
“It simply came to our notice then [the value] It can be easy, but if you don’t know it, it’s not always easy, “said Touré.
Back in Brazil, in the absence of federal support, Imazon is forging links with more state-level policymakers. “Right now, there is no evidence that the federal government is leading conservation or deforestation efforts in the Amazon,” Souza says. In October 2022, Imazon signed cooperation agreements with prosecutors to collect evidence of environmental crimes in four Brazilian states on the border of the Amazon rainforest to share information that could help prioritize enforcement resources.
When you prosecute people deforesting protected land, the damage is already done. Now Imazon wants to use artificial intelligence to stop deforestation before it happens, intertwining this roadside detection model with one designed to predict which communities bordering the Amazon have the highest risk of deforestation over the next year.
Deforestation continued at a historic pace in early 2022, but Souza hopes that by working with nonprofits, Imazon will be able to expand its deforestation AI to seven other South American countries that touch the Amazon rainforest. .
And Brazil will hold presidential elections this fall. The current leader of the polls, former President Luiz Inácio Lula da Silva, is expected to strengthen Bolsonaro’s weakened enforcement agencies and restore the Amazon Fund for foreign investment in reforestation. Lula’s environmental plan is not expected in a few months, but the environment ministers of his previous term anticipate that he will make reforestation a cornerstone of his platform.