Source author record

Hyunho Lee

Hyunho Lee appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Artificial Intelligence Computer Vision Machine Learning physics.med-ph

Catalog footprint

What is connected

4works

4topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Based Flood Mapping

The increasing number of satellites has improved the temporal resolution of Earth observation, making satellite-based flood mapping a promising approach for operational flood monitoring. Deep learning-based approaches for flood mapping using satellite imagery, an important application within Geospatial Artificial Intelligence (GeoAI), have shown improved predictive performance by learning complex spatial and spectral patterns from large volumes of remote sensing data. However, the opaque decision-making processes of deep learning models remain a major barrier to their integration into critical scientific and operational workflows. This highlights the need for a systematic assessment of whether model explanations align with established domain knowledge in remote sensing. To address this research gap, this study introduces the ADAGE (Alignment between Domain Knowledge And GeoAI Explanation Evaluation) framework. The proposed framework is designed to systematically evaluate how well explanations of deep learning models align with established remote sensing knowledge, particularly regarding the distinctive spectral properties of the Earth's surface. The ADAGE framework employs Channel-Group SHAP (SHapley Additive exPlanations) method to estimate the contributions of grouped input channels to pixel-level predictions. Experiments on two satellite-based flood mapping tasks demonstrate that the ADAGE framework can (1) quantitatively assess the alignment between model explanations and reference explanations derived from domain knowledge and (2) help domain experts identify misaligned explanations through alignment scores. This study contributes to bridging the gap between explainability and domain knowledge in GeoAI for Earth observation, enhancing the applicability of GeoAI models in scientific and operational workflows.

preprint2025arXiv

A Spatially Masked Adaptive Gated Network for multimodal post-flood water extent mapping using SAR and incomplete multispectral data

Mapping water extent during a flood event is essential for effective disaster management throughout all phases: mitigation, preparedness, response, and recovery. In particular, during the response stage, when timely and accurate information is important, Synthetic Aperture Radar (SAR) data are primarily employed to produce water extent maps. Recently, leveraging the complementary characteristics of SAR and MSI data through a multimodal approach has emerged as a promising strategy for advancing water extent mapping using deep learning models. This approach is particularly beneficial when timely post-flood observations, acquired during or shortly after the flood peak, are limited, as it enables the use of all available imagery for more accurate post-flood water extent mapping. However, the adaptive integration of partially available MSI data into the SAR-based post-flood water extent mapping process remains underexplored. To bridge this research gap, we propose the Spatially Masked Adaptive Gated Network (SMAGNet), a multimodal deep learning model that utilizes SAR data as the primary input for post-flood water extent mapping and integrates complementary MSI data through feature fusion. In experiments on the C2S-MS Floods dataset, SMAGNet consistently outperformed other multimodal deep learning models in prediction performance across varying levels of MSI data availability. Furthermore, we found that even when MSI data were completely missing, the performance of SMAGNet remained statistically comparable to that of a U-Net model trained solely on SAR data. These findings indicate that SMAGNet enhances the model robustness to missing data as well as the applicability of multimodal deep learning in real-world flood management scenarios.

preprint2022arXiv

JORLDY: a fully customizable open source framework for reinforcement learning

Recently, Reinforcement Learning (RL) has been actively researched in both academic and industrial fields. However, there exist only a few RL frameworks which are developed for researchers or students who want to study RL. In response, we propose an open-source RL framework "Join Our Reinforcement Learning framework for Developing Yours" (JORLDY). JORLDY provides more than 20 widely used RL algorithms which are implemented with Pytorch. Also, JORLDY supports multiple RL environments which include OpenAI gym, Unity ML-Agents, Mujoco, Super Mario Bros and Procgen. Moreover, the algorithmic components such as agent, network, environment can be freely customized, so that the users can easily modify and append algorithmic components. We expect that JORLDY will support various RL research and contribute further advance the field of RL. The source code of JORLDY is provided on the following Github: https://github.com/kakaoenterprise/JORLDY

preprint2015arXiv

Study of quality assurance regulations for linear accelerators in Korea: A comparison study between the current status in Korea and the international guidelines

Quality assurance (QA) for medical linear accelerators is indispensable for appropriate cancer treatment. Some international organizations and western advanced countries provide QA guidelines for linear accelerators. Currently, QA regulations for linear accelerators in Korean hospitals specify a system in which each hospital stipulates its independent hospital-based protocols for QA procedures (HP_QAPs) and conducts QA based on these HP_QAPs while regulatory authorities verify whether items under these HP_QAPs have been performed. However, because this regulatory method cannot guarantee the quality of universal treatment, and QA items with tolerance criteria are different in many hospitals, the presentation of standardized QA items and tolerance criteria is essential. In this study, QA items in HP_QAPs from various hospitals and those presented by international organizations. Concordance rates between QA items for linear accelerators that were presented by the aforementioned organizations and those currently being implemented in Korean hospitals were shown to exhibit a daily QA of 50%, a weekly QA of 22%, a monthly QA of 43%, and an annual QA of 65%, and the overall concordance rates of all QA items were approximately 48%. In comparison between QA items being implemented in Korean hospitals and those being implemented in western advanced countries, concordance rates were shown to exhibit a daily QA of 50%, a weekly QA of 33%, a monthly QA of 60%, and an annual QA of 67%, and the overall concordance rate of all QA items were approximately 57%. The results of this study indicate that the HP_QAPs currently implemented by Korean hospitals as QA standards for linear accelerators used in radiation therapy do not meet international standards. To solve this problem, it is necessary to develop national standardized QA items and procedures for linear accelerators.