Identifying Urban and Socio-Environmental Patterns of Brazilian Amazonian Cities by Remote Sensing and Machine Learning

Abstract

Identifying urban patterns in the cities in the Brazilian Amazon can help to understand the impact of human actions on the environment, to protect local cultures, and secure the cultural heritage of the region. The objective of this study is to produce a classification of intra-urban patterns in Amazonian cities. Concretely, we produce a set of Urban and Socio-Environmental Patterns (USEPs) in the cities of Santarém and Cametá in Pará, Brazilian Amazon. The contributions of this study are as follows: (1) we use a reproducible research framework based on remote sensing data and machine learning techniques; (2) we integrate spatial data from various sources into a cellular grid, separating the variables into environmental, urban morphological, and socioeconomic dimensions; (3) we generate variables specific to the Amazonian context; and (4) we validate these variables by means of a field visit to Cametá and comparison with patterns described in other works. Machine learning-based clustering is useful to identify seven urban patterns in Santarém and eight urban patterns in Cametá. The urban patterns are semantically explainable and are consistent with the existing scientific literature. The paper provides reproducible and open research that uses only open software and publicly available data sources, making the data product and code available for modification and further contributions to spatial data science analysis.

Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications

“…Deep learning models are recognized as intelligent modeling approaches, catalyzing advancements in land use modeling (Gaafar et al, 2022). The synergistic Integration of Google Earth Engine (GEE), remote sensing technology, and Geographic Information System (GIS) facilitates the rapid and precise mapping of land use and land cover, among other Earth surface features (Praticò et al, 2021;dos Santos et al, 2023). Geospatial researchers have employed a diverse array of LULC mapping techniques, ranging from conventional methodologies such as Bayesian Maximum Likelihood to advanced machine and deep learning models, including Support Vector Machine (SVM) (Braun et al, 2023), Light Gradient Boosting Machine, Random Forest (RF) (Magidi et al, 2021), and Decision Trees, (Gazzinelli et al, 2017).…”