The Department congratulates PhD student Joshua Dimasaka on receiving the Student Presentation Award at the American Geophysical Union (AGU) Annual Meeting 2023 as well as the Helmholtz Visiting Researcher Grant

Joshua Dimasaka (PhD student) has been selected to receive the “Outstanding Student Presentation Award (OSPA)” for delivering one of the most exceptional presentations during the American Geophysical Union (AGU) Annual Meeting 2023 in San Francisco, California, United States, last December 13, 2023. In addition to the prestige of receiving an OSPA, he will also receive a $500 prize from the AGU Natural Hazards leadership team.

His work is entitled “Near-real-time Country-wide Estimation of Susceptibility and Settlement Exposure from Norwegian Mass Movements via Intergraph Representation Learning". The research introduces the integraph approach that could advance the current Norway early warning system to mass movements by understanding the patterns of various geophysical characteristics (e.g., daily rainfall, daily snow, steepness information, land use, etc.), 257000-km road networks, and over 4,700 settlement groups across Norway.

The public can access the presentation and the data and code through the following links:

• Presentation: Earth and Space Science Open Archive
• Data and Code: GitHub Repository, Zenodo Repository

Joshua has also received the Helmholtz Visiting Researcher Grant to do a fully-funded short-term research stay at the Earth Observation Centre, German Aerospace Centre (DLR) from July to September 2024 in Weßling, Germany. He will continue working with his PhD co-supervisor, Professor Christian Geiß (in-person) with his Team Georisks, and Professor Emily So (remotely) in acquiring advanced skills necessary to develop a benchmark dataset for auditing global disaster risk using Earth observation data and machine learning.

The ongoing PhD work of Joshua Dimasaka on “Global Mapping of Exposure and Physical Vulnerability Dynamics in Least Developed Countries using Remote Sensing and Machine Learning” has also been accepted as a poster presentation at the 2^nd Machine Learning for Remote Sensing Workshop in the 12^th International Conference on Learning Representations (ICLR) for 11^th of May 2024 in Vienna, Austria. He will showcase an ongoing effort to globally map not only the exposure (e.g., human settlements) but also its associated physical vulnerability characteristics (e.g., building material and construction type) using time-series medium-resolution satellite imagery. He aspires to bring into awareness this timely and relevant interdisciplinary problem to advance the area of large-scale risk quantification to ultimately inform our collective SFDRR and post-2030 long-term efforts in reducing climate and disaster risk.

• ICLR Workshop Website: Machine Learning for Remote Sensing | https://ml-for-rs.github.io