The expansion of agricultural frontiers in the Amazon region poses a significant threat to forest conservation and biodiversity persistence. This study focuses on Pará state, Brazil, aiming to identify and characterize the predominant production systems by combining remote sensing data and landscape structure metrics. A rule-based classification tree algorithm is applied to classify hexagonal cells based on land cover, deforestation patterns, and distance from dairy facilities. The results reveal three dominant production systems: Natural Region, Non-Intensive Beef, and Initial Front, with livestock production being prominent. The analysis indicates that there is a correlation between the productive area and deforestation, emphasizing the role of agriculture as a driver of forest loss. Moreover, road networks significantly influence production system spatial distribution, highlighting the importance of infrastructure in land use dynamics. The Shannon diversity index reveals that areas with production systems exhibit greater diversity in land use and land cover classes, reflecting a wider range of modifications. In contrast, natural vegetation areas show lower Shannon values, suggesting that these areas are more intact and are less affected by human activities. These findings underscore the urgent need for sustainable development policies that will mitigate threats to forest resilience and biodiversity in Pará state.

The Brazilian Cerrado, a global biodiversity hotspot, is under increasing pressure from agricultural expansion and native vegetation conversion, underscoring the need for efficient monitoring to support conservation and environmental policies. In heterogeneous landscapes, land use and land cover (LULC) mapping using supervised classification methods faces a major bottleneck: the need for extensive and high-quality training datasets. To address this challenge, we propose a semi-automated, clustering-based methodology for mapping secondary vegetation within previously deforested areas, reducing training-sample requirements and enabling scalable mapping through the clustering of satellite image time series. In the first stage, an unsupervised process integrates graphics processing unit (GPU)-accelerated Self-Organizing Maps and hierarchical clustering with Dynamic Time Warping to produce spectro-temporal clusters. In the second stage, specialists label and refine these clusters by visual interpretation, transferring expert knowledge from individual pixels to grouped spectro-temporal patterns. Applied to 692,000 km² of previously deforested land in the Cerrado biome, the methodology produced a mapped secondary vegetation area of 81,209 km² (11.74%). The design-based estimated area was 98,683 ± 10,071 km², with an overall accuracy of 96.45 ± 1.52%, a user’s accuracy of 96.27 ± 2.40%, a producer’s accuracy of 79.22 ± 7.94%, and an F1-score of 86.90%. The initial cluster labeling accounted for 86.3% of the final secondary vegetation area and limited the interpretation task to approximately 3000 cluster-level decisions. Implemented in the TerraClass Cerrado 2024 cycle, the workflow reduced the secondary vegetation mapping phase from approximately two years to six months while maintaining the thematic accuracy required for large-scale operational monitoring.