Information
📍 GitHub | |
📚 Organization | UNICEF/University of Oxford |
🔨 Linkedin | |
🔗 Google Scholar |
Bio
I am a PhD Student in Autonomous Intelligent Machines and Systems at the University of Oxford, a part of the Oxford Applied and Theoretical Machine Learning Group (OATML), and a Research Affiliate at the NASA Jet Propulsion Lab with the Machine Learning and Instrument Autonomy Team, working on the Scientific Understanding from Data Science Initiative. I recently completed a joint research internship with UNICEF and the European Space Agency ϕ-lab working on the Giga project, using EO and AI to connect every child to the internet by 2030. I was previously a satellite operator at Planet, operating the world's largest Earth Observation satellite constellation. I hold a Master’s degree from the University of Western Ontario in Electrical and Computer Engineering, and a Bachelor's degree in Aerospace Engineering: Space Systems Design from Carleton University.
Current Role
Currently, I am a PhD Student in the Oxford Applied and Theoretical Machine Learning Group (OATML), focusing my research on the utilization of AI with Earth Observation data to tackle global climate and humanitarian problems. I am also a Data Scientist on the Climate and Environment Data Unit, developing the data pipeline and infrastructure necessary to create UNICEF's Children’s Climate and Environment Risk Index (CCRI). In my role as NASA JPL Research Affiliate, I am working on the SUDS initiative to utilize Deep Learning to understand the drivers of global air pollution.
Areas of Expertise
My expertise is in Deep Learning and Data Science applications to Earth Observation contexts. These specialisations enable me to develop AI models and data processing techniques that can be utilized across research domains, which can significantly benefit ESA Φ-lab CIN by providing the tools necessary to work on diverse climate and humanitarian applications.
Vision for the Future
I am driven by a vision of the future where we have equitable access and development of AI tools to benefit all. I am committed to working at the intersection of AI and Earth Observation to develop solutions to climate and humanitarian problems, focusing on underserved communities.
Latest LinkedIN or X (Twitter) Posts (optional)
Publications (outside CIN)
- K.Doerksen*, I. Tingzon*, and D.Kim. “AI-powered school mapping and connectivity status prediction using Earth Observation.” ICLR 2024 Machine Learning for Remote Sensing Workshop.
- K. Doerksen, Y. Marchetti, K. Miyazaki, K. Bowman, S. Lu, Y. J. Montgomery, Gal, F. Kalaitzis “Leveraging Deep Learning for Physical Model Bias of Global Air Quality Estimates”. NeurIPS Machine Learning and the Physical Sciences Workshop 2023.
- K.Doerksen, Y. Gal, F. Kalaitzis, C. Rossi, D. Petit, S. Li, S. Dadson “Precipitation-Triggered Landslide Prediction in Nepal using Machine Learning and Deep Learning”, Conference: IEEE International Geoscience and Remote Sensing Symposium, June 2023
- C. Briand, K. Doerksen, F. Deleflie, “Solar EUV-Enhancement and Thermospheric Disturbances”. Space Weather Journal Vol. 9, Issue 12, https://doi.org/10.1029/2021SW002840, 22 November 2021.
- K. Doerksen*, K. Fischer*, “Autonomous Systems Validation (SysVal) environment for advancing Mission Operations”. Conference: Small Satellite 2021, Online, Submitted June 2021, shared first authorship.
- P. Bernal, K. Doerksen, C. Yap, “Machine Learning for Early Satellite Anomaly Detection”. Conference: Small Satellite 2021, Online, Submitted June 2021.
- J. Ahumada*, K. Doerksen*, and S. Zeller*, “Automated fleet commissioning workflows at Planet”. Conference: Small Satellite 2021, Online, Submitted June 2021, shared first authorship.