Maria Jose Molina-Contreras


She is a passionate plant molecular biologist, working as a data scientist at INFARM (Berlin, Germany).

In her spare time, she loves to develop projects that can help people around her, especially people who are eager to learn new things in tech. For that reason, she tries to develop projects that are beginner-friendly, even with complex topics.

She is an active member in the Python Berlin communities, helping to organize workshops and participating actively in mentoring newcomers (specially, people who are changing from career path) and giving talks in many local communities like PyLadies and also in international conferences. Moreover, she participated in the python documentation translation (English-Spanish) and she is a coordinator in the discord channel of "Python en Español".

How to build an indoor air quality monitoring and predictive system Talk

Anglický jazyk

Maria Jose Molina-Contreras

In the last couple of years, most people have been moved to a full working from home work-style, which made us realize benefits we were not aware of, but sadly some little inconveniences as well some health related issues.

Some scientific studies show that we spend over 90% of our time indoors [1]. Furthermore, advances in construction technology have caused a much better isolation, so a good ventilation is necessary. However, overventilation results in higher energy consumption usage but inadequate ventilation leads to indoor air quality that affects a person's comfort, health and even our ability to be focused and work effectively.

In order to improve my quality of life working from home, I decided to monitor and evaluate the air of my new working place (a.k.a living room). In this talk, we will explore how to build a functional system to track the air quality, collect our own data using different sensors and implement a predictive approach to avoid future health problems.

We are going to dive into the different setups to interact with air quality sensors using Python on microcontrollers and embedded systems (Raspberry pi), collecting your own data to evaluate different factors like humidity, temperature, CO2, particles, but that’s not all, also we will go into the implementation of a predictive machine learning (ML) model to predict Indoor CO2 levels and alerting us based on predictions before critical levels.

Assistants will see how Python is a great option to indoor air quality monitoring complemented with a predictive ML model for Indoor CO2, while having fun building and monitoring your home.