This glossary contains terms commonly used to describe the methodology and products of Mapbiomas Colombia.
| Word | Definition |
| Accuracy (accuracy analysis) | Quantitative analysis of mapping accuracy. Indicates the allocation error and the area error. |
| Algorithm | Set of rules and procedures established to solve a task. |
| Accuracy samples | Points collected over the anual mosaics and visually classified by the interpreter as belonging to a specific land use land cover class. |
| Training samples | Points or Polygons used to train the classifier. |
| Empirical decision tree | A cascade of parameters set to define the pixel classification. In the empirical decision trees the format and parameters of the tree are defined by the analysts, as well as the parameterization of each decision node. |
| Asset | Collection of maps, images or georeferenced data available for processing and analysis in Google Earth Engine. |
| ATBD (Algorithm Theoretical Basis Document) | Document with methodological description and used algorithms. |
| Band | It refers to each layer of information of an Asset - be it maps or images. |
| Spectral band | Interval between two wavelength values in the electromagnetic spectrum. Landsat has several spectral bands each one covering a range of the electromagnetic spectrum. |
| Chart or Millionth chart | Mapping division of the Brazilian territory is defined by IBGE and integrated to the International Map of the World (IMW) or Millionth Map. This division is used to organize the MapBiomas map processing work. Each map unit covers an area of approximately 18,700 square kilometers and about 20 million pixels. |
| Scene | Defined portion of the planet that is continuously recorded (images) by a satellite sensor. Each scene is identified by a unique combination of a line (path) and column (row) number. In the case of Landsat, they usually have approximately 6,900 pixels per line and 5,400 lines per scene, covering 170 km from North to South and 183 km from East to West. |
| Classification | Assignment (distribution) of the pixels of a satellite image in thematic classes of the legend. |
| Classifier | Generic name for an automated classification method (an example of a classifier is Random Forest). |
| Code Editor | Online integrated development environment (IDE) that is part of Google Earth Engine and that allows the development of Earth Engine applications through scripts and the visualization of the results through a graphical interface. |
| Collect Mobile | Mobile application developed by MapBiomas for the collection of reference data in the field. |
| Collection | Version of the time series of maps and data on land cover and use of the MapBiomas Colombia project. Collections may vary in the period analyzed, methodology and legend. |
| Cloud computing | Data processing carried out in a distributed manner on processors available on the Internet. MapBiomas uses cloud computing through Google Earth Engine and Google Cloud Computing. |
| Spatial consistency | Consistency in the spatial distribution of pixels of a class with the characteristics of the local landscape. For example, the occurrence of some glacier pixels in the middle of a forest indicates a spatial inconsistency. |
| Temporal consistency | Classification history of a pixel to a certain class over time and consistency with possible or probable land cover or land use transitions. For example, a pixel that has been classified as forest for 20 years, but appears as non-forest in one year in the middle of the series, is probably an inconsistency or classification error. |
| Dashboard (control panel) | Platform for visual presentation of the consolidated data that helps track the information. |
| Feature Space | Set of spectral information used as classification inputs with Random Forest, such as the bands, indices and metrics used. |
| Spatial filter | Post-classification tool that corrects spatial inconsistency errors in a class less than the minimum mapping unit. |
| Temporal filter | Post-classification tool to correct temporal consistency errors between classes and years. |
| Google Cloud Storage | Google's web service for online file storage and data access that uses the Google Cloud Platform infrastructure. |
| Google Earth Engine | Cloud-based multi-petabyte geospatial dataset analysis platform that enables users to analyze data on a global scale. All MapBiomas image processing and data production are performed on this platform. |
| Landsat image | Satellite image generated by the Landsat project satellites. Landsat is a joint effort of the United States Geological Survey (USGS) and the National Aeronautics and Space Administration (NASA). |
| Integration | Routine of superimposition of the classifications of biomes, countries and cross-cutting themes, generating regionally integrated maps. The data by countries and certain classes of MapBiomas (cross-cutting themes) are worked separately. These are subsequently integrated into a single map using prevalence rules. |
| Integration map | Final map consolidating maps of biomes, countries and cross-cutting themes. |
| Transition map | Map showing the main transitions of land use and land cover. It is produced from a comparison of a pair of maps (e.g. 2000 x 2016). In these maps each pixel can be classified as change or no change. For each change, it receives a code that represents the class in T1 and the class in T2. |
| Image mosaic | Set of Landsat pixels with good quality (little cloud interference, for example) selected in a given period. The MapBiomas mosaics are constructed by individually analyzing each pixel of the Landsat images available for the analysis period. In the mosaic, we try to represent the analysis area for the specified period in the best possible way. In MapBiomas image mosaics generally represent the period of one year. |
| Spectral index | Parámetro resultante de operaciones matemáticas entre los valores numéricos del píxel en las diferentes bandas espectrales de una imagen. Por ejemplo, el Índice de Vegetación de Diferencia Normalizada (NDVI) se calcula como: (NIR – R) / (NIR + R), siendo NIR la banda del infrarrojo cercano y R la banda del Rojo. |
| Píxel | Smallest unit in a digital image. Satellite images are made up of a matrix of pixels, each with a digital value. The pixel in MapBiomas corresponds to the pixel of Landsat images with 30m average spatial resolution. The pixel area undergoes variations according to latitude, the farther from the Equator the area tends to be smaller. |
| Post-classification | Automated routines to improve the consistency of maps performed after classification and map integration. The temporal and spatial filters are examples of post classification. |
| Random Forest | Supervised classification method that is based on decision trees. |
| Raster | Digital image, composed of an array of values (pixel). |
| Spatial resolution | Pixel size of a satellite image. Spatial resolution is a measure of the level of detail in an image. For example, Landsat images have an average spatial resolution of 30m. |
| Script | Set of instructions written in a programming language for a function to be executed |
| Satellite sensor | Satellite instrument responsible for the remote sensing of electromagnetic energy. A satellite may have multiple sensors for picking up different spectral ranges. |
| Shapefile | File format with a set of spatial data in vector format. |
| Transversal theme | Class mapped in a parallel process, which later becomes part of the map in the integration phase. Examples of cross-cutting themes in MapBiomas Colombia are the Mangrove and Flooded forest classes. |
| WebCollect | Platform used to collect points for the accuracy analysis. |
| Workspace | Web platform developed by MapBiomas for parameterization and classification of land use and land cover maps. The platform serves as an interface between analyst work and the cloud processing on Google Earth Engine. |