Machine Learning on Geospatial Data with Malte Loller-Anderson & Mathilde Ørstavik
What can machine learning do for geospatial data? Carl and Richard talk to Malte Loller-Anderson and Mathilde Ørstavik about their work at Norkart, using aerial imagery to build detailed maps around Norway. Mathilde dives into the critical role of machine learning - identifying buildings in images. Usually done by hand with each new image, Norkart has a machine learning model that automates the process trained on previous vector maps of buildings. But there are many things that look like buildings in Norway, including patches of snow, mountains, and even shapes under water. Malte also discusses how Norkart has decided to train in-house with nVidia L40 processors rather than in the cloud - the hardware is used 24 hours a day since some models can take weeks to train! There are many interesting ideas about geospatial data and machine learning from people who have been doing it for years.
Guests:
Malte Loller-Andersen
Malte Loller-Andersen is a passionate Machine Learning Engineer working for Norkart, operating in the geospatial domain. After he graduated with a masters degree in AI, he spent 6 years gathering knowledge within the machine learning-sphere on various complex projects as a consultant. A year ago he joined Norkart and he is now trying to solve whatever curveball Mathilde throws at him. And she really knows how to throw a ball... In addition to diving deep into the technicalities, Malte enjoys sharing knowledge and has held multiple talks at national and international conferences such as NDC, Devoxx, PyData and Javazone.
Mathilde Ørstavik
Mathilde Ørstavik has a Master’s degree in Geographical IT with a specialization in Geographical AI. Over the past seven years she has worked as a software developer at Norkart, contributing to a range of innovative projects. In 2022, Mathilde was promoted to Head of AI, where she is dedicated to leveraging AI and geographical data to tackle new challenges, with a particular focus on enhancing the efficiency of municipalities across Norway. Mathilde is recognized for her ability to communicate complex technologies through talks at various conferences, and as a leader capable of driving cultural change and innovation.
Links:
- Norkart https://www.norkart.no/
- nVidia L40 GPU https://www.nvidia.com/en-us/data-center/l40/
- SQLite https://www.sqlite.org/
- Python https://www.python.org/
- GitHub Copilot Customization https://docs.github.com/en/copilot/about-github-copilot/what-is-github-copilot