Before starting the Master of Data Science (MDS) program at UBC, I had been working as a civil engineer for a consulting firm in Vancouver. I soon realized that despite producing vast amounts of data, the civil engineering and construction industries have felt little influence from advancements in data science and machine learning. Having seen the capabilities of data science and machine learning implemented in other industries, it became apparent that the civil engineering and construction industries could benefit greatly through the implementation of these technologies.
The engineering and construction industries are not unique in this respect; many industries around the world are only now starting to take advantage of data science as the Internet of Things (IoT) and mobile computing has allowed for data collection in traditionally non-data driven industries. The UBC MDS program presented itself as a bridge, connecting students of diverse professional backgrounds with data science. Empowering professionals to harness the value of their data will help drive change and shape these industries in the future.
One of the best experiences I had with the MDS program was the year-end capstone project. During the last two months of the program, students work with an external capstone partner and a UBC mentor to address a question facing the capstone partner’s organization using data science. Just like the students, the capstone industry partners are diverse, ranging from agriculture to tourism. Coming from an engineering background, I was initially concerned whether I would find an industry partner that fit my experience. Despite having a good understanding of data science and analytics, it was important to me to be knowledgeable of the capstone partner’s problem from their perspective to be able to formulate an appropriate solution.
For the capstone project, my partner was BGC Engineering, a boutique geological engineering consultancy with a specialization in software development. The project was to develop an anomaly detection and flood forecasting system using real-time hydrometric data. The main challenges with this project were determining useful features from the vast amounts of data we had available to us, and determining what models would be appropriate for BGC Engineering, under the consideration that the chosen model will need to be scalable to use in a real-time across thousands of gauges.
Students in my group included a geoscientist with two masters degrees, geography graduate, and a mathematics graduate. Our UBC mentor for the project is a doctorate in statistics who has publications related to anomaly detection, and our partner mentor from BGC was actually a graduate from last year’s MDS cohort. Having access to this breadth of knowledge in the group proved useful for identifying useful hydrological features in addition to eliminating extraneous features from being considered within our models. Ultimately, it was our group’s strong geo-science and data science skills that lead us to develop a solution can be implemented into BGC Engineering’s business.
While the capstone project showed me that there are companies in traditionally non-data driven industries utilizing big data, it signalled to me the start of acceptance and adoptance throughout these industries. I remain optimistic that the demand for data scientists will only continue to grow as more useful applications of data science are discovered.
Ted Haley is a graduate of the UBC MDS program in 2018. He hopes to solve problems in the engineering industry with data science.