A comprehensive dataset of environmentally contaminated sites in the state of São Paulo in Brazil

Nouha Samlani, Daphne Silva Pino, Reginaldo Bertolo, Tannaz Pak

Research output: Contribution to journalArticlepeer-review

29 Downloads (Pure)

Abstract

In the Brazilian state of São Paulo, contaminated sites (CSs) constitute threats to health, environment and socioeconomic situation of populations. Over the past two decades, the Environmental Agency of São Paulo (CETESB) has monitored these known CSs. This paper discusses the produced dataset through digitising the CETESB reports and making them accessible to the public in English. The dataset reports on qualitative aspects of contamination within the registered sites (e.g., contamination type and spread) and their management status. The data was extracted from CETESB reports using a machine-learning computer vision algorithm. It comprises two components: an optical character recognition (OCR) engine for text extraction and a convolutional neural network (CNN) image classifier to identify checked boxes. The digitisation was followed by harmonisation and quality assurance processes to ensure the consistency and validity of the data. Making this dataset accessible will allow future work on predictive analysis and decision-making and will inform the required policy-making to improve the management of the CSs in Brazil.
Original languageEnglish
Article number263
JournalScientific data
Volume11
DOIs
Publication statusPublished - 2 Mar 2024

Fingerprint

Dive into the research topics of 'A comprehensive dataset of environmentally contaminated sites in the state of São Paulo in Brazil'. Together they form a unique fingerprint.

Cite this