Integrating Human Domain Knowledge into Artificial Intelligence for Hybrid Forest Fire Prediction: Case Studies from South Korea and Italy

19660 11 105807 2 321626 document 105807 EGU24_HW_JO.pdf application/pdf e32627e4aff208e4f113e63f9db2a3af MD5 7734750 2024-04-23 09:08:05 https://pure.iiasa.ac.at/id/eprint/19660/1/EGU24_HW_JO.pdf 19660 1 1 application/pdf text en public cc_by_nc_4

EGU24_HW_JO.pdf

published 105808 1 321632 document 105808 indexcodes.txt text/x-c 34e00268ddd23265c5a5c9074456ff84 MD5 2560 2024-04-23 09:17:49 https://pure.iiasa.ac.at/id/eprint/19660/2/indexcodes.txt 19660 2 2 text/x-c other Generate index codes conversion from text to indexcodes en public

indexcodes.txt

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/105807 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/105807 http://eprints.org/relation/issmallThumbnailVersionOf https://pure.iiasa.ac.at/id/document/105807 archive 353 disk0/00/01/96/60 2024-04-23 09:09:31 2025-03-12 05:01:16 2024-04-23 09:09:31 conference_item show 1 Jo H.-W. 9770 0000-0001-6127-883X Corning S. 9382 0009-0001-5277-5380 Kiparisov P. 9395 0000-0003-1223-7964 San Pedro J. 2468 0000-0001-9317-7275 Krasovskiy A. 8266 0000-0003-0940-9366 Kraxner F. 7904 Lee W.-K. Integrating Human Domain Knowledge into Artificial Intelligence for Hybrid Forest Fire Prediction: Case Studies from South Korea and Italy pub BNR AFE Forest fires pose a growing global threat, exacerbated by climate change-induced heat waves. The intricate interplay between changing climate, biophysical, and anthropogenic factors emphasizes the urgent need for sophisticated predictive models. Existing models, whether process-based for interpretability or machine learning-based for automatic feature identification, have distinct strengths and weaknesses. This study addresses these gaps by integrating human domain knowledge, crucial for interpreting forest fire dynamics, into a machine learning framework. We introduce FLAM-Net, a neural network derived from IIASA's wildfire Climate impacts and Adaptation Model (FLAM), melding process-based insights of FLAM with machine learning capabilities. In optimizing FLAM-Net for South Korea, new algorithms interpret national-specific forest fire patterns, and multi-scale applications, facilitated by U-Net-based deep neural networks (DN-FLAM), yield downscaled predictions. Successfully tailored to South Korea's context, FLAM-Net and DN-FLAM reveal spatial concentration near metropolitan areas and the east coastal region, with temporal concentration in spring. Performance evaluation yields Pearson's r values of 0.943, 0.840, and 0.641 for temporal, spatial, and spatio-temporal dimensions. Projections based on Shared Socioeconomic Pathways (SSP) indicate an increasing trend in forest fires until 2050, followed by a decrease due to increased precipitation. During the optimization process of FLAM-Net for Italy, optimal parameters for sub-areas are identified. This involves considering biophysical and anthropogenic factors at each grid, contributing to improved localized projection optimization by utilizing various sets of optimal parameters. There by, this process illuminates the intricate connections between environmental factors and their interpretation in the dynamics of forest fires. This study demonstrates the advantages of hybrid models like FLAM-Net and DN-FLAM, seamlessly combining process-based insights and artificial intelligence for interpretability, accuracy, and efficient optimization. The findings contribute scientific evidence for developing context-specific climate resilience strategies, with global applicability to enhance climate resilience. 2024-04 published doi:10.5194/egusphere-egu24-12320 3478 3287 3306 3684 164 165 public paper EGU General Assembly 2024 Vienna 14-19 April 2024 conference FALSE Integrating Human Domain Knowledge into Artificial Intelligence for Hybrid Forest Fire Prediction: Case Studies from South Korea and Italy no info:eu-repo/semantics/conferenceObject