Using a method based on satellite images and artificial intelligence, Brazilian researchers have shown that the priority area for actions to combat illegal deforestation could comprise 27.8% less territory than the 11 municipalities controlled by the federal government under the the current strategy, known as the Amazon 2021/2022 plan. This monitoring ignores new deforestation boundaries outside the target areas.
According to an article by the researchers, published in June in retention letters a total of 414,603 square kilometers (km 2) this year, while the total area covered by the plan for the 11 municipalities is 574,724 km . amounts to 2. In other words, the area to be monitored can be reduced by 160,000 km 2 which is about the size of Suriname.
While the deforestation hotspots identified by the researchers accounted for 66% of the average annual deforestation rate, the 11 municipalities covered by the plan accounted for 37% of the deforestation rate for the past three years (2019-21).
In the article, scientists associated with Brazil’s National Space Research Institute (INPE) and universities in the United States conclude that the proposed method would sharpen monitoring and law enforcement focus. In addition, they emphasize, it reveals new deforestation limits outside the priority area and thus not covered by the official monitoring plan.
“Using this new approach, we concluded that prioritizing areas with higher deforestation rates would be more effective than limiting monitoring to certain municipalities. This is an important finding, as the agencies responsible for law enforcement in this case are mainly IBAMA and ICMBio, Their budgets and staff are steadily dwindling. Some of these deforestation hotspots are located in the 11 municipalities, but others are nearby and forming new borders,” Guilherme Augusto Verola Mataveli, corresponding author of the article, told Agência FAPESP. Mataveli is a researcher at INPE’s Earth Observation and Geoinformatics Division.
The National Council for Legal Amazonia (CNAL), which oversees the Amazon Plan 2021/2022, responded to Agência FAPESP’s request for comment as follows: “The purpose [of the plan] was to focus on where the occurrence of illegal environmental activities had the most impact on the results of environmental management in Brazil, without losing sight of the need to act in other areas of Legal Amazonia.”
Legal Amazonia is an area of more than 5 million km 2 consisting of the states of Acre, Amapá, Amazonas, Maranhão, Mato Grosso, Pará, Rondônia, Roraima and Tocantins. It was established by federal laws dating back to 1953 to promote special conservation and development policies for the area.
According to CNAL, “the 11 municipalities were chosen because they had the largest deforested area and the highest incidence of fires, with the potential to include others for mapping by the Amazon Protection System’s Center for Management and Operations.” [Censipam].”
The council also stated that INPE was one of the “leading institutions in the process of choosing priorities” and that the scientists who conducted the research “could have contributed in an institutional manner as soon as the opportunity arose.”
“CNAL always works with official information that is managed, processed and analyzed by official government agencies,” the statement said.
Progress in data processing
The authors of the article note that deforestation in the 11 municipalities targeted by the plan has been significant in recent years and is a reason for monitoring, but not sufficient to prioritize only these areas, namely: São Félix do Xingu, Altamira, Novo Progresso, Pacajá, Portel, Itaituba and Rurópolis (Pará); Apuí and Lábrea (Amazons); Colniza (Mato Grosso); and Porto Velho (Rondonia).
They also note that despite the concentration on these areas for monitoring and law enforcement purposes, deforestation increased by 105% between February and April 2021 compared to the average for the same period between 2017 and 2021. DETER, the official warning program for deforestation of Brazil, pointed out 524.89 km 2 of new deforestation areas in these areas.
“The study confirms the importance of INPE, which for 60 years has trained outstanding researchers and produced science and technology from satellite data for society and national development. The advances in data processing embodied in the use of artificial intelligence to plan actions for Fighting deforestation is crucial to reduce the country’s environmental problems and establish a national sustainable development plan,” said Luiz Aragão, the last author of the article. Aragão heads INPE’s Earth Observation and Geoinformatics division,
Priority Areas
The data sources for the study include INPE’s Legal Amazonia Deforestation Satellite Monitoring Service (PRODES), which produces the annual deforestation statistics used by the Brazilian government in formulating public policies for the region. PRODES focuses on cut-and-burn speeds and has been using the same method since 1988.
According to the latest report, deforested areas in the region totaled 13,235 km 2 between August 2020 and July 2021. This was a 22% year-on-year increase, the largest since 2006.
“The idea for the article came about in February 2021 when the Amazon Plan 2021/2022 was announced,” said Mataveli. “Deforestation in the 11 municipalities would be responsible for 70% of the total deforestation detected in the Amazon, but the PRODES number was different. When we improved the model, we found that it was a useful tool to make surveillance and law enforcement more effective. to concentrate.”
To establish the priority areas, the researchers first defined what they call grid cells measuring 25 km by 25 km and regularly spread across the Amazon. Using the Random Forest machine learning algorithm to predict deforestation hotspots in the following year based on sets of multivariate regressions, they placed each cell in a high, medium or low priority class. According to the article, the method identified a greater proportion of areas at risk of deforestation in terms of overall size and public lots where felling trees is illegal.
The model took into account five predictors: deforestation in previous years, distance from grid cells with high cumulative deforestation in previous years, distance from infrastructures such as roads and waterways, total protected area in grid cells and the number of active fires.
The three priority classes were based on predicted deforestation, with values below the 70th percentile classified as low, values between the 70th and 90th percentile as medium, and values above the 90th percentile as high. The grid cells classified as high were used to map priority areas for 2022 with a total of 414,603 km 2.
The authors also note that their method prioritizes actions in border areas of the 11 priority municipalities where deforestation activities are concentrated, identifies other areas of increasing deforestation that are not controlled by the plan, determines priorities based on land used in the previous year is freed, and not dependent on geopolitical boundaries like municipalities.
“Giving priority to these 11 municipalities will be insufficient for Brazil to fulfill its international obligations, including the pledge to reduce illegal deforestation to zero by 2028, announced at COP-26 [ the 2021 UN Climate Change Conference ]”In addition, the plan aims to reduce deforestation by 8,719 km . ” said Mataveli 2 per year, but a 2018 decree set a much lower target of 3,925 km 2 per year after 2020.”
This was a reference to Decree 9578 (2018), which consolidated national climate change policies and set a target of reducing deforestation in the Amazon by 80% compared to the 1996-2005 average. This is one of Brazil’s commitments to contain greenhouse gas emissions.
In addition to committing to zero deforestation by 2028, Brazil also announced at COP-26 that it would cut greenhouse gas emissions by half from 2005 levels by 2030 and achieve climate neutrality by 2050. greenhouse gas emissions are due to mismanagement of forests and land use, including deforestation and fire.
When the Amazon Plan 2021/2022 was announced, experts criticized the stated goals as insufficient because they were based on the average deforestation rate for the 2016-20 period, which was already 35% higher than the average of the previous ten years.
Call for additional actions
The article advocates a number of complementary actions to combat deforestation, as well as direct methods for setting public policy objectives. These include environmental education and awareness raising, identifying and holding accountable actors who violate environmental protection laws and profit from illegal deforestation, promoting projects that invest in the green economy and the maintenance of standing forest, and regularizing public and indigenous land tenure.
“We used open source code to build the model and define priority areas,” Mataveli said. “We are talking to the Terra Brasilis platform to include these areas in the information available to anyone who wants to access them so that it can be used in practice by all interested state or municipal governments.”