Method
GET TO KNOW MAPBIOMAS ALERTA METHOD
MapBiomas Alerta is a system for compiling alerts from different remote sensing-based deforestation detection systems in Brazil, aggregating, validating and refining these alerts with high-resolution images (Planet Scope with 3 m spatial resolution), generating reports and publishing them on a single, open-access platform.
All data and reports are available publicly, openly and free of charge on the web platform so that inspection agencies, financial agents, companies and civil society can act to reduce illegal deforestation.
A detailed description of the deforestation detection systems considered in the process and the step-by-step method for validation and refinement can be found here (and also in Appendices 1 and 2 of the Annual Deforestation Report/RAD 2022).
STEP DESCRIPTION
The MapBiomas Alerta process involves the stages of compilation, validation, refinement, cross-referencing with public data, auditing, and publication of the alerts and reports of deforestation.
Figure 1. MapBiomas Alerta's methodological process for compiling, validating, refining, cross-referencing data, auditing, and publishing deforestation alerts in Brazil.
Step 1: Compilation of alerts from existing systems for all Brazilian biomes.
MapBiomas Alerta consults, organizes and consolidates information produced by the various official and independent systems that monitor deforestation in Brazil and generate deforestation alerts based on 10 m, 30 m or even 60 m spatial resolution images. For the year 2022, MapBiomas Alerta consults monthly alerts made available by the following sources of information and existing systems:
- Deter/INPE - for Amazon and Cerrado (only deforestation alerts are analyzed. Degradation, fire or logging alerts are not analyzed);
- SAD/Imazon - for Amazon;
- GLAD/Universidade de Maryland - for Pampa;
- SAD Caatinga/Geodatin - for Caatinga;
- SIRAD-X/Instituto Socioambiental (ISA) - for tha Xingu Basin region in the Amazon and Cerrado;
- SAD Mata Atlântica/SOS Mata Atlântica e ArcPlan - for Atlantic Forest;
- SAD Pantanal/SOS Pantanal e ArcPlan - for Pantanal;
- SAD Pampa/GeoKarten e UFRGS - for Pampa;
- SAD Cerrado/Instituto de Pesquisa Ambiental da Amazônia (IPAM) - for Cerrado (being included).
SIRAD-X complements SAD and DETER data with radar monitoring in the Xingu Basin. SAD Caatinga was developed by Geodatin in partnership with the State University of Feira de Santana (UEFS) to detect deforestation with a focus on dry forests in the Caatinga biome, and may include some areas in the Cerrado and Atlantic Forest. SAD Atlantic Forest and SAD Pantanal were developed with a focus on forest and savanna formations, in the respective biomes, by SOS Mata Atlântica and SOS Pantanal in partnership with ArcPlan. SAD Pampa was developed by GeoKarten in partnership with the Federal University of Rio Grande do Sul and is in operation to detect deforestation in forest environments and in tests for grassland environments. SAD Cerrado was developed by IPAM, in partnership with the Image Processing and Geoprocessing Laboratory of the Federal University of Goiás (LAPIG-UFG) and MapBiomas, focusing on the forest, savanna and grassland formations of the Cerrado biome (https://sadcerrado.ipam.org.br/).
In addition to the sources of monthly alerts, annual alerts are being included to avoid omissions (PRODES/INPE for Amazonia and Cerrado and Atlas of Forest Remnants/SOS Mata Atlântica and INPE for the Atlantic Forest).
Step 2: Validation and selection of before and after images
Validation occurs in two steps. The first is done in an automated way, eliminating all alerts that overlap with agricultural areas from the annual land use and land cover maps of MapBiomas Brasil or that have already been detected in previous surveys, because it configures the vegetation cover as not being native. The second step is done visually by trained analysts organized into teams per biome, with the support of monthly high resolution Planet mosaics (4 m resolution images). At this point, alerts that correspond to cases of false positives are discarded, with the corresponding record of the reason for rejection (forestry, agriculture, seasonality, etc.). When the alert is considered valid, an image where it is possible to visualize the native vegetation before deforestation and an image where it is possible to see the area that was deforested are selected and purchased with project resources. The purchase of the images considers a minimum area of 500 by 500 m and a surrounding area that helps to contextualize the deforested area.
Step 3: Validation and refinement in high-resolution images
A technician, experienced in interpreting satellite images in the biomes, performs a new validation of the deforestation identified in the high-resolution images. If confirmed, a refinement process is carried out with the purpose of more precisely delimiting the area that had the native vegetation suppressed. The generation of the refined polygon is done automatically, using a supervised classification algorithm (Random Forest), which is processed on the Google Earth Engine platform through Workspace, an application of the MapBiomas Project. The only manual action in this step is the collection of training samples that represent the deforested and non-deforested area in the high-resolution images for use by the classifier. The refined polygon goes through a simplification process that removes excess vertices. Based on the before and after images, the interpreter also identifies the pressure vector that may have caused the deforestation event (mining, gold mining, urban expansion, agriculture and cattle ranching, natural causes, or others).Figure 2. Example Planet images of before and after deforestation and the refined polygon from the 2019 Code 93831 alert.
Step 4: Cross-referencing with public territorial databases
The refined polygons are spatially overlaid with spatial land and surveillance information, including boundaries of Indigenous Lands (ITs), Conservation Units (UCs), quilombola territories, rural settlements, areas registered in the Rural Environmental Registry (CAR) - including declared Areas of Permanent Preservation (APPs) and Legal Reserve (RL) - in addition to areas embargoed by the environmental agency, suppression authorizations and forest management plans from IBAMA's Sinaflor. The alerts are also linked to geographical boundaries such as municipalities, states, biomes, and watersheds. Crossings with special territories are also considered, such as Legal Amazon, area of application of the Atlantic Forest Law, MATOPIBA, AMACRO, Biosphere Reserves, and others. These crossings qualify the alerts and allow the generation of technical reports based on information that is relevant to the user institutions.
Step 5: Auditing
Each refined polygon goes through an audit process done by the technical supervisor of each biome. At this stage, the eventual need to redo some adjustments is evaluated before the final publication of the confirmed deforestation.
Step 6: Publication
All confirmed deforestation polygons are published on the MapBiomas Alert Platform, with weekly updates. Reports are available for each confirmed deforestation and for each intersection of an alert with a property registered in the CAR, SIGEF and SNCI (with an area larger than 0.1 ha). The reports contain the following information:
- deforestation alert code;
- original source of the alert (detection system);
- Biome, State e Municipality;
- deofrestation area;
- deforestation area that intersects with the property;
- property code;
- image and date from before deforestation;
- overlap of deforestation with: APP, Legal Reserve, springs, Indigenous Lands, Conservation Units, Sustainable Forest Management Plan, embargoed areas, vegetation suppression authorization, and others;
simplified description of the coordinates of the deforestation polygon - MapBiomas land cover and land use history in the evaluated area.
Observation:
If an error is found at any stage of this processing in the deforestation polygon published by MapBiomas Alerta, formally reported by environmental agencies or platform users, the technical team conducts a new and thorough analysis. If confirmed that it is not deforestation of native vegetation, the alert is removed from the map and from the platform statistics. The polygon is kept in the database only for individual consultation through its identifier code, where the reason for its cancellation is registered. We emphasize that there is no analysis of legality or regularity of deforestation in the platform. Each and every loss of native vegetation is an alert.
METHOD OF LIMITATIONS
As every method, MapBiomas Alerta has some limitations that must be considered when applying its data:
- Processsing time - the importation of alerts from their sources (detection systems) occurs monthly, with the exception of DETER alerts, which occur every 15 days. As part of the alerts processing is done individually and visually by trained analysts, the validation and processing time depends on the biome and the time of year. It can vary from 30 to 90 days from the date of detection by the source system to publication on the MapBiomas Alerta platform. The purpose of MapBiomas Alerta is to increase certainty about confirmed deforestation data and provide ready reports for remote surveillance. Rapid field surveillance operations aimed at flagrant deforestation can be planned directly with the pre-existing detection systems.
- Alert Omissions – deforestation are validated and refined based on the existence of an alert previously captured by a third-party deforestation detection system. The possible omissions of these systems in detecting deforestation also affect the alerts evaluated by MapBiomas Alerta..
At the beginning of the project, most of the Brazilian biomes did not have a monthly monitoring system, and the main source of alerts used was GLAD. GLAD is a global system that uses images from Landsat satellites to automatically flag areas where forest cover has been disturbed. The system
system covers the entire tropical region. However, the alerts detect changes more reliably in areas with at least 60% forest cover, making them more useful in dense tropical forests. Therefore, it had omissions because it was not adjusted to the specific characteristics of each Brazilian biome.
To avoid omissions, MapBiomas supported the development of Deforestation Alert Systems (DAS) adapted for each Brazilian biome by several universities, research institutions and civil society organizations:
-
- SAD Caatinga, which started operating in 2020, developed by the MapBiomas na Caatinga team (UEFS and Geodatin);
- SAD Mata Atlântica, developed by SOS Mata Atlântica and ArcPlan, was deployed in 2021 for four river basins (Tietê, Jequitinhonha, Iguaçu and Miranda/Aquidauana), where 2,126 alerts were identified in addition to the GLAD alerts, and has been operating for the entire biome since January/2022;
- SAD Pantanal, developed by SOS Pantanal and ArcPlan to monitor deforestation alerts in forest and savanna formations, deployed in late 2021 (where 103 alerts were identified), operating monthly as of January 2022;
- SAD Pampa, developed by GeoKarten and UFRGS, which in 2022 operated complementarily to GLAD;
- SAD Cerrado, developed by IPAM in 2022. The form of integration to MapBiomas Alerta is still under development and only part of the alerts were incorporated into the 2022 data;
In a complementary manner, the annual deforestation identified by PRODES Amazon and Cerrado were used to identify omissions from the monthly monitoring systems of these biomes. With the same objective of reducing omissions, the annual deforestation identified by the Atlas of Forest Remnants of SOS Mata Atlântica/INPE were also included, rejecting those that overlap with alerts already validated.
It is also worth noting that deforestation monitoring systems present minimum detection areas and, therefore, may omit some deforestations. For example, alerts smaller than 6.25 hectares are not detected in the Amazon (DETER Amazon) and those smaller than 1 hectare are not detected in the Cerrado (DETER Cerrado).
c. Deforestation Speed Underestimated – when validating and refining an alert, a search is performed for a pair of good quality Planet satellite images of before and after deforestation. The "before" image is the most recent available in the period up to 12 months before detection, and the "after" image is the one closest to the end of deforestation. The presence of clouds can increase the period between before and after images by days, weeks, and even months. This does not change the statement that deforestation occurred in the period between the two images, but it does affect the calculation of the average speed at which deforestation actually occurred..
d. Automatic Polygon Delimitation – polygons delimiting the refined alerts are established by a process of automatic classification of the area of change between the two images, i.e., the place where the native vegetation was suppressed. In delimiting the deforestation polygon, areas with signs of previous change or with small clusters of trees that were maintained in the midst of deforestation are removed. In 2020, a procedure was developed to minimize the small islands within the polygons in the refinement step, as well as the excess of vertices, which correspond to the points that form the polygons. To reduce the number of vertices, a simplification mechanism was established.
e. Limitation to Non Woody Native Vegetation – the detection of non-forest vegetation suppression, such as grassland vegetation, for example, has limitations in the systems that originate alerts, whose methods focus on identifying where there was forest vegetation suppression. However, when non-forest vegetation suppression also occurs in the alert area or in an adjacent area, the use of high resolution images allows for its registration during the alert refinement phase. Because of this, most of the deforestation in non-woody vegetation that has been detected since 2019 has occurred occasionally, whenever observed around woody vegetation alerts, so the current system still underestimates vegetation suppression.
DIFFERENCES FROM THE OFFICIAL ANNUAL DATA
The comparison of the deforestation data from MapBiomas Alerta with the official deforestation data (PRODES) should be done with caution, as they present some important differences.
Subject |
PRODES Amazon |
PRODES Caatinga, Cerrado, Atlantic Forest, Pantanal e Pampa |
ATLAS Atlantic Forest |
MapBiomas Alerta |
Minimum Mapped Area |
6,25 ha |
1 ha |
3 ha |
0,3 ha |
Area Calculation |
releases rate that estimates deforestation also in unobserved areas |
data represents the sum of the observed areas |
data represents the sum of the observed areas |
data represents the sum of the observed areas |
Analysis period |
August 2019 to July 2022 |
August 2019 to July 2022 |
October 2018 to September 2022 |
deforestation detected between January and December 2019, 2020, 2021 and 2022. |
Image capture window |
July to September 2019, 2020 ,2021 e 2022 |
July to September 2020 , 2021 e 2022 |
July to November 2019, 2020 ,2021 e 2022 |
July 2018 to December 2022 |
Territorial Range |
Legal Amazon |
boundaries of the biomes at scale 1:250,000 (for the Cerrado, subtracting the overlap area with the Legal Amazon) |
area of application of the Atlantic Forest Law (biome + enclaves in the northeast) |
IBGE biome boundaries at scale 1:250,000 |
Mapped Vegetation Type |
primary or existing forest vegetation in 1988 (excludes cerrado areas and non-forested areas in 1988) |
forest and savanna vegetation existing in 2000 |
primary or existing forest vegetation in 1985 |
primary vegetation and may include secondary vegetation |
Developed by Luiz Motta (QGIS Contributor), this plugin allows visualizing the MapBiomas Alert data directly on the QGIS.
The minimum Windows version for installing this plugin is 3.14.12 or later.
To install the plugin, you must enable the experimental plugins.
The plugin displays only alerts that are within the QGIS drawing area.
Access the video tutorial to learn how to operate the plugin:
MapBiomas Alert is a system for validation and refinement of alerts on deforestation/conversion of native vegetation in all Brazilian biomes using high-resolution imagery.
This system is being developed and continuously improved by the collaborative network of MapBiomas co-creators, with input from government agencies (e.g., MMA, IBAMA, SFB, ICMBio, MPF, and TCU) and alert providers (e.g., INPE, IMAZON, University of Maryland, ISA, and others).
WARNING!
MapBiomas Alert publishes any and all loss of native vegetation detected by alert provider systems and validated through high-resolution satellite images. MapBiomas does not define the legality, responsibility, and/or restrictions related to the validated deforestation alerts published on this platform. The assessment of such matters lies exclusively within the competence of public agencies and/or private and financial institutions that have free access to the data provided by MapBiomas Alert. MapBiomas is not responsible for the decisions made by these agencies and institutions based on the published alerts, as they represent objective and concrete data about the existence of deforestation or conversion (loss of native vegetation).
Here are some clarifications about the scope and limitations of the alert data:
1. Alert period: the operational phase aims to evaluate all deforestation alerts detected in the country since January 2019. Alerts prior to this period (October to December 2018) represent the pre-operational phase with a sample of alerts from that period, and they do not appear in the statistics and map (they only remain in the platform's database for consultation using their respective alert codes). The detection date refers to when the alert was generated by the providers (e.g., DETER, SAD, GLAD) and does not necessarily represent the moment when the deforestation occurred. For example, deforestation detected in 2019 may have started or occurred in 2018. The data for the current year is always partial and subject to change due to the processing and publication time of the alerts. Once the data for a year is consolidated, we compile and publish the Annual Deforestation Report (RAD), which is available on the MapBiomas Alerta website
2. Minimum area: the minimum deforestation area to be published on the MapBiomas Alert Platform is 0.3 hectares. To be considered as overlapping with the Rural Environmental Registry (CAR), the minimum area is 0.1 ha.
3. Non-woody vegetation: MapBiomas Alert uses the deforestation indicators from the DETER/INPE, SAD/IMAZON, GLAD/University of Maryland, SIRAD-X/ISA, SAD Caatinga/UEFS-Geodatin, SAD Mata Atlântica/SOS Mata Atlântica-Arcplan, and SAD Pantanal/SOS Pantanal-ArcPlan systems. Among these systems, only DETER-Cerrado generates alerts for non-woody vegetation. Therefore, only in the Cerrado biome is deforestation in grassland vegetation monitored. In other biomes, deforestation in non-woody vegetation is only identified in MapBiomas Alert when associated with indicators of deforestation in forest and savanna formations (for more information about the data sources and method, visit the website http://alerta.mapbiomas.org/).
4. Embargos: the embargoed areas correspond to those provided in the IBAMA and ICMBio geo-services (http://siscom.ibama.gov.br/geoserver/) and may be incomplete regarding state and municipal embargoes.
5. Rural Environmental Cadastre (Cadastro Ambiental Rural - CAR): the data from the Rural Environmental Registry refers to the geo-service provided by SICAR managed by the Brazilian Forest Service. Properties that are registered in the states but have not been synchronized with SICAR are not included.
6. Authorizations for suppression of native vegetation: the authorizations for alternative use and suppression of vegetation, as well as forest management plans, are sourced from SINAFLOR/IBAMA, which integrates data from all Brazilian states with limitations on updates. For the states of Pará and Mato Grosso, the information was obtained from the geo-services of the respective SEMAs (https://monitoramento.semas.pa.gov.br/monitoramento/#/sig and http://monitoramento.sema.mt.gov.br/simlam/). Authorizations made at the municipal level may be incomplete, as well as authorizations issued by states before the implementation of SINAFLOR in 2018.
7. Legality, responsibility and/or restriction regarding validated Deforestation Alerts published on the Platform: MapBiomas does not conduct this type of evaluation. It is the responsibility of users (environmental agencies, financial institutions, etc.) to seek this information from the relevant authorities or their clients.
8. Pending Alerts: the purpose is to review all alerts generated by the main systems; however, some alerts may have pending validation for various reasons (e.g., lack of image due to cloud cover, excessive alerts in months with a higher quantity of deforestation, etc.). The number of pending alerts may vary over time, as they are continuously produced and published.
9. Omissions: MapBiomas does not generate its own alerts and relies on the quality of the systems operating in Brazilian territory to avoid omissions. The development of new alert detection systems and their inclusion as sources in MapBiomas Alert has reduced omissions and allowed for the accurate identification of deforestation in all biomes.
10. Cancelled Alerts: some alerts have been reviewed after publication on the platform and CANCELED due to reasons such as pasture or boundary cleaning, silviculture, or others. These alerts do not appear in the statistics or on the map. However, they remain in the platform's database for consultation using their respective alert codes.
If you have suggestions, criticisms, or ideas to improve the work, please contact us via email: suporte.alerta@mapbiomas.org.
The Law Enforcement Dashboard uses public databases of deforestation permits and law enforcement operations such as environmental infractions and embargoes. Data accessed through active transparency are used, which means public data provided by state agencies, most likely online, without an official request.
Access the full Methodological Note here.
METHODOLOGICAL NOTE FOR THE USE OF MAPBIOMAS ALERTA DATA IN THE FINANCIAL SECTOR AND RURAL CREDIT ANALYSIS
The MapBiomas Alerta initiative provides deforestation/conversion alerts from various sources (such as DETER/INPE, GFW, SAD etc.) ont a public and free platform. These alerts have been verified, validated and spatially overlaid with government territorial databases (SICAR/SFB, SIGEF/INCRA, IBAMA, ICMBio etc.). Details about the methodology are available at: https://alerta.mapbiomas.org/metodologia
It is important to note that MapBiomas does not evaluate the legality, responsibility, and/or restrictions regarding the validated and published alerts on the MapBiomas Alerta platform. Therefore, users interested in using the information contained in deforestation reports, including financial institutions, are responsible for evaluating such information based on documents and information obtained from the parties involved or competent public agencies.
The MapBiomas Alerta platform reports any validated loss of natural vegetation based on high-resolution satellite imagery, without evaluating the legality or responsibility of the deforestation. When there is an authorization for vegetation suppression (ASV) or alternative land use authorization (UAS) that has been registered and published in SINAFLOR (IBAMA) corresponding to the alert area, or voluntarily added by a user on the platform, this information remains public in the respective alert report for any user who accesses it.
Any regularization, authorization acquisition, commitment terms, or equivalents should be addressed with the competent government agency and do not result in the removal or cancellation of the alert on the MapBiomas Alerta platform. The eventual cancellation of an alert will only occur if it is technically proven that there has been no loss or removal of native vegetation.
We emphasize that, in the case of credit analysis by financial institutions, it is recommended that managers and responsible staff request documentation from the client to verify the legality of the deforestation/conversion and internally verify the procedures adopted by the institution to evaluate financing requests in such situations.
Without prejudice to the exclusive responsibility of the financial institution operating rural credit to request and analyze the documents related to the deforestation alert, we suggest some precautions in the credit analysis:
- Define a minimum overlapping area with the property, considering the specificities of the regions and biomes, to avoid, for example, a neighboring deforestation affecting the credit of a property due to small discrepancies that may exist in the databases. The report of the alert in the rural property presents both the total area in hectares of the deforestation and the area deforested within the property. This information can be used to calculate the percentage of the alert that occurred within the property.
- Do not consider alerts caused by natural causes as grounds for credit restriction, including areas of native vegetation loss due to landslides or floods.
- Adopt specific procedures for analyzing rural settlements and collective Rural Environmental Registrations (CARs) to prevent deforestation in individual lots from impacting access to credit for the entire community.
For further clarifications, please contact us via email at suporte.alerta@mapbiomas.org.