Hyun-Woo Jo
Korea University Postdoctoral Fellow
Capacity Development and Academic Training Unit
Korea University Postdoctoral Fellow
Agriculture, Forestry, and Ecosystem Services Research Group
Biodiversity and Natural Resources Program
Biography
Hyun-Woo Jo participated in the 2022 IIASA Young Scientists Summer Program (YSSP) conducting research on forest fire modeling. His project titled, Optimization of the IIASA Wildfire climate impacts and adaptation model (FLAM) to represent forest fires in South Korea, earned him an honorable mention at the YSSP awards for that year. After optimizing FLAM as a YSSP participant, he further developed the model by incorporating its process-based algorithm into neural networks as part of his PhD thesis. He is currently a Korea University Postdoctoral Fellow at IIASA.His research interests include application of remote sensing and deep learning techniques in agriculture and forestry domains, especially by combining domain specific knowledge with machine-learnable architecture.
His interest in this area encouraged Jo to participate in joint projects with the European consortiums related to EU-Horizon2020: the Horizon2020 EOPEN (Nov.2017-Oct.2020) and Horizon2020 CALLISTO (Jan.2021-Dec.2023). As part of the EOPEN project, he developed a neural network model for rice paddy detection, the algorithms of which can be operated on a cloud-based platform of EOPEN. As part of the CALLISTO project, he performed joint research with the National Observatory of Athens in Greece on AI-based farmland monitoring. The research was followed by applying the model tested in South Korea to European regions through transfer learning. The results were presented at the Conference on Neural Information Processing Systems on Climate Change and AI.
Jo is also interested in developing software for AI and remote sensing data analysis. Learn more about his work in this sphere by taking a look at this example: https://www.platform-dryad.com
Last update: 19 OCT 2023
Publications
Park, E., Jo, H.-W., Biging, G.S., Chun, J.A., Jeon, S.W., Son, Y., Kraxner, F., & Lee, W.-K. (2024). Advancement of a diagnostic prediction model for spatiotemporal calibration of earth observation data: a case study on projecting forest net primary production in the mid-latitude region. GIScience & Remote Sensing 61 (1) e2401247. 10.1080/15481603.2024.2401247.
Jo, H.-W., Corning, S., Kiparisov, P., San Pedro, J., Krasovskiy, A. , Kraxner, F., & Lee, W.-K. (2024). Integrating Human Domain Knowledge into Artificial Intelligence for Hybrid Forest Fire Prediction: Case Studies from South Korea and Italy. DOI:10.5194/egusphere-egu24-12320. In: EGU General Assembly 2024, 14-19 April 2024, Vienna.
Jo, H.-W., Krasovskiy, A. , Hong, M., Corning, S., Kim, W., Kraxner, F., & Lee, W.-K. (2023). Modeling Historical and Future Forest Fires in South Korea: The FLAM Optimization Approach. Remote Sensing 15 (5) e1446. 10.3390/rs15051446.
Jo, H.-W. (2022). Optimization of the IIASA’s FLAM model to represent forest fires in South Korea. IIASA YSSP Report. Laxenburg, Austria: IIASA