Forest automation and the spatialization of carbon stocks in native areas in the Western Amazon are part of a study by the Geoflora Project, by the Brazilian Agricultural Research Corporation - Embrapa, in the state of Acre, in partnership with an investment fund.
The use of technology to collect data on the ground and mapping the forest using a drone with artificial intelligence are part of the research.
The results will support public policies for sustainable use, such as forest management and payment for environmental services.
The activities of the Geoflora project involve monitoring greenhouse gases (GHG) and soil carbon stocks in native forests.
The results will show whether the forest system is sequestering or emitting equivalent carbon into the atmosphere, which will allow the calculation of the carbon balance in the forest systems evaluated.
Another component of the project uses drones and artificial intelligence to automate steps in the forest inventory to identify strategic species.
More than 40 thousand hectares of areas in the Amazon have already been mapped with the aim of collecting information to compose a database of images of forest species obtained through RGB cameras on board drones (orthophotos).
At the Geotechnology Laboratory of Embrapa Acre, the data is analyzed and the artificial intelligence algorithm is trained to identify forest species.
This work has already been carried out in forest areas in the Chico Mendes Extractive Reserve, Antimary State Forest (Acre), Jacundá and Jamary national forests (Rondônia), municipal parks in Rio Branco and forest management areas on private properties in Acre and Amazonas.

Source: Amazon Agency