Theme: Health and Air Quality in São Paulo: An Integrated Analysis ABOUT THE TEAM Our team consists of passionate and highly dedicated professionals, all united by an unwavering commitment to innovation and technological progress, with the goal of significantly improving the quality of life for the population of São Paulo. Each member plays an essential role in realizing this truly revolutionary project. Mi929954
The main challenge of this project is to understand and effectively communicate the relationship between air quality and health issues in São Paulo. This involves integrating health and air quality data, creating machine learning models for predictions, and making this information publicly available.
High-Level Summary: Provide a high-level summary of your project. What have you developed? How does it "solve" the challenge? Why is this important? The relationship between health and air pollution is a topic that has been receiving increasing attention. This project aims to raise awareness about the impacts of public health pollution in São Paulo by providing an interactive Power BI dashboard and using machine learning techniques with health and air quality data. It integrates data from the Unified Health System (SUS), the Pan American Health Organization (PAHO), and air quality measurements provided by the Environmental Company of the State of São Paulo (CETESB). The interactive dashboard will present integrated data clearly for anyone to easily understand and visualize the information.
The primary focus of the dashboard is the relationship between air pollution and the health of the population in São Paulo. Interactive graphs and tables will allow users to analyze the relationship between different health indicators and real-time air quality. We hope to plan policies and actions to improve air quality and consequently, public health. This dashboard will be publicly accessible on the web, allowing people to easily view and understand information about the relationship between diseases and air quality.
We believe that our project can have a significant impact on raising awareness about health risks associated with air quality and motivating actions to improve air quality in critical areas. Additionally, we will provide useful data for decision-makers in government and health agencies to guide environmental improvement policies and measures.
Project Demonstration: For a project demonstration, we invite you to access our interactive dashboard on Power BI, where you can explore charts, maps, and analyses related to air quality and health.
For a project demonstration, we invite you to access our interactive dashboard on Power BI, where you can explore charts, maps, and analyses related to air quality and health.
Final Project: Upload your entire final project to an external website (a cloud-based hosting service or code repository, e.g., YouTube, Google Drive, GitHub, One Drive, Dropbox, etc.) and provide a public access link. The link you provide should not require a password, permission, or registration to access your final project.
Project Details: Provide additional details about your project. What exactly does it do? How does it work? What are the benefits? What do you hope to achieve? What tools, coding languages, hardware, or software did you use to develop it?
It involves data integration and the impacts of air pollution on public health in São Paulo, where they will be stored in a database, an interactive dashboard will be created, statistical analysis will be performed, and machine learning models will be implemented for predictions.
We begin by collecting data from the Unified Health System (SUS) related to public health. We also collect data from CETESB related to air quality, such as atmospheric pollutant levels.
Before analyzing the data, we undergo a preprocessing process. This includes cleaning the data, handling missing values, and addressing potential errors. We transform and organize the data appropriately to facilitate analysis.
We apply data modeling techniques, ranging from descriptive statistics to more advanced analyses, depending on the project's objectives. This step helps us extract information and insights from raw data, revealing trends, correlations, or relevant information.
To ensure that the data is stored effectively and is accessible, we place it in a MySQL database hosted in Docker containers. This allows us to keep the data organized and accessible through SQL queries.
Using the Power BI tool, we establish a connection to the MySQL database. This enables data integration in real-time or at specific intervals.
In Power BI, we design an interactive dashboard. This dashboard likely includes charts, tables, filters, and other visual elements that represent the data comprehensibly. You can interact with these elements to explore the data and gain insights.
The interactive dashboard created in Power BI is published on the web, making it accessible to anyone with internet access. You can access the dashboard through a link without needing to install Power BI on your devices.
Anyone accessing the dashboard link can view the data and interact with visualizations to gain information about air quality and its relationship with health.
Visualization of relationships between diseases and air quality: Integrated analysis allows for a clear and objective visualization of the relationships between air quality and the occurrence of respiratory diseases. Geographic mapping of areas most affected by poor air quality and related diseases. Statistical analyses highlighting correlations between atmospheric pollutants and diseases. Predictions and estimates using machine learning techniques to identify future trends in air quality and health impacts. Public Health Impact: The results obtained will enable the proposal of actions and strategies for public health promotion, contributing to the prevention and control of respiratory diseases. Possible Intervention Measures: The information obtained in the dashboard can be useful for decision-making by public and private managers, allowing the adoption of measures to reduce the impact of air pollution on the population's health.
Use of Artificial Intelligence: Did you use any Artificial Intelligence tools and software in preparing your solution? If yes, which ones and how did you use them? (The answer to this question will not affect the judgment of your project.)
We use a database to store and manage data; Power BI for creating the interactive dashboard. Programming languages like Python for data modeling and implementing machine learning techniques to identify correlations between atmospheric pollutants and diseases, as well as making future predictions based on collected data.
Artificial intelligence was not implemented. It was only used for corrections and assistance in the production of processes and ideas developed during the Space Apps hackathon and also for the final project pitch.
We used a database to store and manage data; Power BI for creating the interactive dashboard. Programming languages like Python for data modeling and implementing machine learning techniques to identify correlations between atmospheric pollutants and diseases, as well as making future predictions based on collected data.
NASA Space Agency Data: Provide specific details about which NASA and NASA Space Apps Challenge Space Agency Partner data you used in your project, how you used them, or how they inspired your project. Remember: you can use any open data in your project. However, to be eligible for a Global Prize, you must use NASA data or resources.
List all the data, resources, and tools used in your project. Resources should include any code, text, and images (even if they are open source or freely available) that you used while creating your project. If you are using any copyrighted material, make sure you have permission to use it.
Companhia Ambiental do Estado de São Paulo (CETESB). (2020). Air Quality Report 2019. Retrieved from https://cetesb.sp.gov.br/ar/wp-content/uploads/sites/28/2020/07/Relat%C3%B3rio-de-Qualidade-do-Ar-2019.pdf
World Health Organization (WHO). (n.d.). Ambient and Household Air Pollution Attributable Death Rate (per 100,000 population). Retrieved from https://www.who.int/data/gho/data/indicators/indicator-details/GHO/ambient-and-household-air-pollution-attributable-death-rate-(per-100-000-population)
World Health Organization (WHO). (n.d.). Air Pollution. Retrieved from https://www.who.int/data/gho/data/themes/air-pollution
Pan American Health Organization (PAHO). (n.d.). Impact of Air Pollution on Health in the Americas. Retrieved from https://iris.paho.org/bitstream/handle/10665.2/54963/9789275724613_por.pdf?sequence=1&isAllowed=y
AQI.in. (n.d.). Air Quality in São Paulo. Retrieved from https://www.aqi.in/pt/dashboard/brazil/sao-paulo/sao-paulo
NASA - Jet Propulsion Laboratory (JPL). (n.d.). NASA Power and Energy. Retrieved from https://power.larc.nasa.gov/data-access-viewer/
Ministry of Health of Brazil. (n.d.). Open Data SUS. Retrieved from https://opendatasus.saude.gov.br/dataset?q=&tags=SRAG&sort=score+desc%2C+metadata_modified+desc
NASA - Goddard Space Flight Center. (n.d.). Giovanni - NASA GES DISC. Retrieved from https://giovanni.gsfc.nasa.gov/giovanni/#service=TmAvMp&starttime=&endtime=&variableFacets=dataProductObservation%3AModel%3B
NASA - Goddard Space Flight Center. (n.d.). Gupta et al. 2020. Retrieved from https://science.gsfc.nasa.gov/610/applied-sciences/nasa_rio_materials/guptaRio2.pdf
Canva. (n.d.). Canva - Create Amazing Designs. Retrieved from https://www.canva.com
Please note that the "(n.d.)" indicates "no date" for web sources where the publication date is not available.