Spire Global is a space-to-cloud analytics company that owns and operates the largest multipurpose constellation of satellites. Its proprietary data and algorithms provide the most advanced maritime, aviation, and weather tracking in the world. In addition to its constellation, Spire’s data infrastructure includes a global ground station network and 24/7 operations that provide real-time global coverage of every point on Earth.

During this internship I studied both domain-specific information about digital health and the skills of project management and full-stack development. I also gained valuable experience using the React framework and explored user-centred design. I published an online blog documenting my work and ideas: https://emuni17191.wixsite.com/digital-health-2020.

I worked on my own project within the Light Rapid Transit team exploring the possible applications of machine learning and big data in rail operations for smarter, more efficient design. By streaming real-time data from application programming interfaces (APIs) and utilising historical data sets I was able to apply regression techniques in Python to provide new insights into rail operations. Once I had discovered several patterns of delay within the rail network, I used machine learning techniques to predict the evolution of delay minutes at different points. I also created a function to determine the root cause of a string of delays, hence uncovering operational and infrastructure related vulnerabilities in the rail network.

I worked on a project in the Light Rapid Transit team, analysing the existing Sheffield Supertram network and determining the feasibility of increased network capacity. After recognising the limitations of existing timetabling software, I applied my computer programming skills to create a new service feasibility analysis tool in Python. In addition to determining the operational feasibility of a new proposed tram service, my tool automatically generated timetables of multiple operationally feasible tram services for variable network constraints. I also analysed the possibility of using Python scripts across further projects to improve our team’s efficiency, presenting this back to our non-technical stakeholders.