Conference Agenda

Human activities have transformed nearly three-quarters of the Earth's land cover, with urbanization being one of the most irreversible forms of land use change. Large infrastructure projects often accelerate these transformations, reshaping landscapes and ecosystems. This study examines the spatial and urban transformations linked to the Rio de Janeiro Petrochemical Complex (COMPERJ) in Eastern Metropolitan Rio de Janeiro between 2006 and 2023. Using remote sensing data (MapBiomas Collection 9) and census data from the Brazilian Institute of Geography and Statistics (IBGE), we assess how the construction—and subsequent halt—of COMPERJ influenced land use and land cover (LULC) changes, urban expansion, and population dynamics. Results reveal accelerated urban growth (19.51%) and population growth (13.94%) between 2000 and 2010, driven by expectations of economic development, followed by population decline (-0.74%) after the project's suspension, while urban areas continued expanding (5.49%) at lower rates, at the expense of forest and productive areas. The findings demonstrate that large infrastructure projects can trigger irreversible urbanization, even when economic promises fail, leading to inefficient land use and reduced urban densities.

There is a lack of detailed demographic data in the northern Brazil region from the 1980s to the early 2000s. These data are available only at the municipal level, which in northern Brazil corresponds to extensive territorial areas. This data gap may hinder understanding of various human settlement processes in the region, affecting insights into processes such as the expansion of economic activities, deforestation, and even violent conflicts. Machine learning algorithms, such as Random Forest, combined with geospatial data from different sources, can be employed to disaggregate demographic data, transforming the discrete space of municipal polygons into a continuous raster surface. Thus, this study aims to assess the performance of these technologies under limited data availability in scenarios similar to those in the late decades of the twentieth century. To this end, a Random Forest model was implemented and evaluated against both the 2022 Brazilian census data and the WorldPop dataset. The results indicate that the methodology proposed here is a viable solution in data-scarce contexts, yielding estimates comparable to official census figures and to more complex products like WorldPop, while demanding significantly less computational effort. Future research should examine the model’s performance across broader and more heterogeneous regions to better assess its generalizability.

Artificial reservoirs and lakes play a key role as

sources of water supply, recreational spaces, and support for

local economic development. A major issue is that they are often

managed in isolation, without considering the dynamics of their

contributing watersheds. Changes in land use and land cover

(LULC) pose a direct threat to water resources by altering runoff

patterns, infiltration rates, and contaminant transport.

This study analyzes LULC transformations in the Los Molinos

Reservoir basin, C´ordoba, Argentina, between 2000 and 2024.

The reservoir is a critical system for water supply, ecosystem

services, and recreational activities. Using Landsat imagery and

supervised classification with the Random Forest algorithm on

Google Earth Engine, complemented by spatial analysis in

QGIS, a significant urban expansion and notable loss of natural

vegetation were detected, especially near the shoreline.

These changes could increase the risk of diffuse pollution,

reduce water retention capacity, and degrade the reservoir’s

water quality. The results underscore the need to incorporate

multitemporal LULC analysis as a central tool for integrated

watershed management in the context advancing urbanization.

This study analyzes urban verticalization and socio- spatial patterns in Belo Horizonte using LiDAR-derived building heights and infrastructure indicators. A normalized Digital Sur- face Model (nDSM) was generated from LiDAR data to map vertical structures with high spatial accuracy. Self-Organizing Maps (SOM) were applied to cluster neighborhoods based on height, infrastructure, and demographic data. The results reveal distinct urban typologies, including central consolidated zones, peripheral vulnerable areas, and hybrid transitional regions. While verticalization reflects urban consolidation, it must be interpreted alongside socio-infrastructural conditions to fully understand spatial inequalities and urban dynamics.