Reclassification rules
This section provides a high-level introduction to reclassification rules used in the LUC-Brazil project. This stage implements 27 specialized reclassification rules to refine and standardize land cover classification. Temporal trajectory rules analyze multi-year patterns to detect transitions, enforce consistency, and correct isolated pixel misclassifications. Each rule addresses specific classification challenges such as pasture-agriculture confusion, urban expansion detection, or temporal consistency in perennial crops.
The heart of the system is the reclassification and remapping pipeline, which transforms diverse input classifications into a standardized output schema. The package implements 27 specialized rules organized into the following categories:
- Forest Rules: Uses PRODES to distinguish between Natural Forests and Secondary Vegetation;
- Agriculture Rules: Uses TerraClass to improve the agricultural classes, especially in the case of Perennial and Semi-Perennial Agriculture;
- Infrastructure Rules: Includes urban and mining areas from TerraClass;
- Water Rules: include water mask from TerraClass;
- Multi-year transitions: considers three consecutive years to ensure consistency of more difficult classes (e.g., conflicts between Shrubby Pasture and Secondary Vegetation).
The rules are described below, in the order on which they are applied.
Base Mask Preparation
Base Mask Preparation is a key part in the classification pipeline. It prepares reference masks from two authoritative external datasets: PRODES deforestation monitoring data, Terraclass land use and land cover maps, and water masks. These base masks serve as ground truth references for all downstream processing stages.
The base mask preparation includes geomtrically adjusting the PRODES deforestation mask to remove some inconsistencies in the border pixels which distort the overall statistics.
Reclassification Part 1: Yearly Rules Defined by Masks
Secondary Vegetation Rule
This rule distinguishes forested area in Amazonia between primary forests and secondary vegetation. To that aim, it uses the PRODES mask, which indicates the primary forest area. The secondary vegetation areas are those that have been deforested and then abandoned so that a forest regeneration process has started.
Current Deforestation Rule
For each year, the PRODES masks also contains information on forest removal on the current rule. This rule ensures that all areas deforested in a given year are not marked as “Pasture” or “Agriculture”, since TerraClass also follows the same convention of not classifying land use for areas deforested in the year it is produced.
Residuals Rule
This rule is necessary due to problems in the PRODES mask. Sine PRODES only observes one image per year for a given Landsat tile, some areas are not observed due to clouds and are masked as such. When such areas are visible in later years and then assigned as “residuals”. Since LUC-Brasil uses time series which enable removal of most cloudy areas, this rule assigns PRODES residuals to the “Pasture” class.
Silviculture Rule #1
This rule improves the representation of silviculture (planted forests) by using TerraClass maps as a reference. Pixels in the LUC-Brasil maps are thus updated to reflect the TerraClass maos. This rule is applied only to the years where TerraClass maps are available. There is another rule (see below) that updates the “Silviculture” class in years without TerraClass maps.
Silviculture Rule #2
This rule considers the case of pixels classified as “Silviculture” by LUC-Brasil which are not classified as such by TerraClass. These pixels are reclassified as “Pasture”.
Semi-Perennial Agriculture Rule #1
This rule reclassifies the LUC-Brasil pixels to match the TerraClass “Semi-Perennial Agriculture” class, in the years where TerraClass maps are available.
Semi-Perennial Agriculture Rule #2
This rule reclassifies the LUC-Brasil pixels which are classified as “Semi-Perennial Agriculture” but that do not match any agricultural label in the TerraClass maps. Such pixels are reclassified as “Pasture”. The rule applies in the years where TerraClass maps are available.
Semi-Perennial Agriculture Rule #3
This rule reclassifies the LUC-Brasil pixels which are classified as “Semi-Perennial Agriculture” to match the TerraClass “Temporary Agriculture” class, in the years where TerraClass maps are available.
Annual Agriculture Rule
This rule reclassifies the LUC-Brasil pixels which are classified as “Semi-Perennial Agriculture” to match the TerraClass “Temporary Agriculture” class, in the years where TerraClass maps are available.
Mining Rule
This rule includes areas which TerraClass identifies as “Mining”, since the LUC-Brasil classes detected using Landsat do not provide a consistent basis for such classification.
Urban Areas Rule
This rule includes areas which TerraClass identifies as “Urban Areas”, since the LUC-Brasil classes detected using Landsat do not provide a consistent basis for such classification.
Water Bodies Rule #1
This rule includes areas which TerraClass identifies as “Water Bodies” and maps them to the “Water” class, provided that LUC-Brasil did not identify them as either “Wetlands” or “Seasonally Flooded”.
Water Bodies Rule #2
This rule includes areas which PRODES identifies as “Hidrography” and and maps them to the “Water” class, provided that LUC-Brasil did not identify them as either “Wetlands” or “Seasonally Flooded”.
Natural Non-Forest Areas Rule
This rule reclassifies as “Natural Non-Forest” pixels which fall inside the PRODES mask of “Non-Forest” class.
Reclassification Part 2: Year-Specific Mask Generation
Water Consistency Rule
Processes a 3-year window centered on 2019, identifying pixels classified as “Water” across any of the years 2018, 2019, and 2020 are reclassified as “Water” for all three years.
Perennial Agriculture Trajectory
This rule validates perennial crop classifications by consulting TerraClass reference data from surrounding years (year-1 and year+1). Perennial crop pixels are only retained if TerraClass confirms their presence in adjacent years, reducing false positives.
The rule targets specific years where TerraClass surveys are available:
| Target Year | TerraClass Before (year-1) | TerraClass After (year+1) | Rationale |
|---|---|---|---|
| 2009 | 2008 | 2010 | Between consecutive TerraClass surveys |
| 2011 | 2010 | 2012 | Between consecutive surveys |
| 2013 | 2012 | 2014 | Between consecutive surveys |
| 2019 | 2018 | 2020 | Between consecutive surveys |
| 2021 | 2020 | 2022 | Between consecutive surveys |
Secondary Vegetation - Pasture Consistency
This rule analyzes secondary vegetation (SV) to pasture transitions by examining 3-year trajectories. This rule identifies pixels classified as SV that are surrounded by pasture classifications in adjacent years, helping distinguish true secondary vegetation from misclassified pasture areas.
The rule processes 21 consecutive years from 2001 to 2025, creating overlapping 3-year windows. For each target year, the algorithm examines year-1, year, and year+1 classifications to detect SV-pasture patterns.