Laetitia Adam

I am a master’s student in Applied Geoinformatics with a B.Sc. in Urban Studies and a passion for city planning and mobility.

One year of analysing air quality and traffic data

From August 1st 2024 until July 30th 2025, I have been working as a research assistant at the Chair for Transport System Planning at Bauhaus-University Weimar. I have participated in two research projects for 20 hours per week.

INMEA: This project, funded by the German Federal Ministry of Education and Research and the European Union, focuses on applying machine learning methods for predicting and evaluating urban air quality. The study area is Erfurt, Thuringia. For more information click here.

MOVEWELL: This project aims to enhance mobility in rural Thuringia by developing demand-oriented, sustainable public transport solutions. The project is also funded by the German Federal Ministry of Education and Research. For more information click here.

Coming from a background of urban studies and wanting to pursue a master in geoinformatics, I viewed this job as a great preparation for deepening my skills in geospatial technologies.

In the context of INMEA project I was responsible for acquiring infrastructure and traffic data. This included specifically querying OpenStreetMap datasets as well as geospatial data from various official geoportals. In the process of data acquisition, I learned web scraping for efficiently downloading bigger datasets. This included traffic counting of numerous detectors which have measured traffic volume in five-minute intervals over several years. In addition to that, I have started using python as a data analyst tool. I especially enjoyed discovering the features of geopandas. For example, I used geopandas to examine different factors that potentially affect air quality. The analysis included the proximity to industrial sites as potential emission sources, the proximity to traffic lights which interrupt traffic flow, the building density that impacts wind circulation and the slope of roads that influences vehicle emissions. In order to structure the work flow of the so-called proximity analysis, I created a kedro pipeline. The pipeline combines all python scripts so that one can run the analysis with given input data and parameters in one go. This helped me to better organise my analysis and connect all the necessary steps. The main advantage of the pipeline is that I only used OpenStreetMap data so that any city can be used as input parameter and study area.

An exemplary outcome of the pipeline for the city of Erfurt can be seen here:

Next to the data analysis, I was responsible for a broad literature review. On the one hand, this included literature on emission sources impacting air quality and meteorological factors influencing distribution patterns. On the other hand, papers considering machine learning approaches to better predict air quality have been taken into account. On a regular basis my colleague and me revised and discussed selected literature to build connections to our own research project. This created a helpful knowledge to start summarizing and publishing our own results. Since INMEA Project does not only consist of the work of my colleague and me, we had monthly meetings with all contributors. This included seven researchers from Bauhaus-University as well as from University of Schmalkalden. For me it was interesting, to see how long-term projects are organised over several years including financing, cooperation with project partners as well as bringing the final results together.

In the context of MOVEWELL project, I was involved in creating mobility concepts for one of the main hospitals in Thuringia as well as for all institutions of “Arbeiterwohlfahrt”. For this, I analysed the commuting routes of all employees to their work place. The OpenRouteService API makes it possible to calculate distance and duration for multiple origin-destination pairs at the same time and allows a quick travel time analysis. Furthermore, I helped carrying out a questionnaire with the employees. The questionnaire was designed to gain inside knowledge about the employees’ mode of transport, awareness for sustainable mobility options and willingness to adapt their transport preferences.