https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/147 Sat, 04 Apr 2026 11:46:33 GMT 2026-04-04T11:46:33Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/169983 Title: Bayesian Uncertainty Estimation for Deep Learning Inversion of Electromagnetic Data Authors: Oh, S.; Byun, Joong moo Abstract: With the recent progress in deep learning (DL), DL inversion, which reconstructs subsurface physical properties from geophysical data using DL techniques, has been widely applied. For decision-making and risk management related to the application of DL inversion, assessing the reliability of a prediction is essential, and such assessment can be achieved through uncertainty estimation. However, most geophysical studies have focused on deterministic prediction that does not provide uncertainty estimates. In this letter, a practical uncertainty estimation method based on the Bayesian framework is introduced for DL inversion of electromagnetic data. More specifically, iterative estimation by a convolutional neural network with dropout provides epistemic and aleatoric uncertainties as well as a resistivity model. Using numerical tests, we observed that aleatoric uncertainty indicates the nonuniqueness of the inverse problem, showing which parts of the resistivity model are less sensitive to the data. In addition, we proposed an empirical criterion for determining whether new data are similar to training data using estimated epistemic and aleatoric uncertainties. Based on this criterion, out-of-distribution data were identified; these data showed larger data misfit, indicating that the predictions would be unreliable. The applicability of uncertainty estimation and the empirical criterion derived from uncertainties were demonstrated using field data. Bayesian uncertainty estimation and the criterion established here may help to achieve more reliable prediction via DL inversion. https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/169983 https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/169985 Title: Biomethane enhancement via plastic carriers in anaerobic co-digestion of agricultural wastes Authors: Faisal, Shah; Salama, El-Sayed; Hassan, Sedky H. A.; Jeon, Byong Hun; Li, Xiangkai Abstract: Two types of plastic carriers low-density polyethylene (LDPET) and high-density polyethylene (HDPET) were used as a support material for biofilm formation during anaerobic co-digestion of agricultural wastes. LDPET and HDPET were added separately to different reactors containing binary substrates: corn straw and cauliflower leaves (G 1), corn straw and cow dung (G 2), while ternary substrates corn straw, cauliflower leaves, and cow dung were used in G 3. Reactors containing either HDPET or LDPET carriers supported the enhancement of biogas and biomethane. Maximum daily biomethane (333.43 and 368.35 mL/day) was achieved after HDPET addition to G1 and G2 at day 10 and 12, respectively. The accumulative biomethane were significantly enhanced (p < 0.05) by 17.14% and 23.52%, compared with reactors having LDPET carriers 11.89% and 5.53%, respectively. HDPET addition to ternary substrates (G 3) resulted in highest biomethane production (31.61%) and total solids (31.70%) and volatile solid (61.63%) removal. The major short-chain fatty acids (SCFAs) detected in all groups were acetic acid (4-5 g/L) and propionic acid (2-3 g/L), and their conversion to biomethane was the highest with HDPET. Scanning electron microscopy (SEM) analysis of the supporting materials showed that the plastic carriers support the biofilm formation especially in the case of HDPET. This study demonstrated that addition of cost-effective plastic carrier (HDPET) to anaerobic digestion system supported the formation of biofilm, leading to significantly increase in substrate utilization and biomethane production. https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/169985 https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211397 Title: Bumper-guided representation interpolation for black-box unsupervised domain adaptation Authors: Choi, Jin-Seong; Lee, Jae-Hong; Chang, Joon-Hyuk Abstract: Black-box unsupervised domain adaptation (BUDA) presents a challenging scenario in which only unlabeled target data are available, and access to the source model's parameters is limited. Recent BUDA methods that rely on consistency training struggle with error accumulation caused by fixed source representations. In this paper, we propose a novel framework called bumper-guided representation interpolation (BGRI), which introduces a bumper model that interpolates between the source and target domain representation spaces. Using interpolated representations, the bumper model delivers generalized source information and enables stable and effective knowledge transfer to the target model. Through extensive experiments conducted in real-world scenarios across diverse acoustic and linguistic domains, BGRI consistently outperforms the existing BUDA approaches in terms of adaptation performance and robustness. Thu, 01 Oct 2026 00:00:00 GMT https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211397 2026-10-01T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211349 Title: A dual-branch parallel network for speech enhancement and restoration Authors: Yang, Da-Hee; Kim, Dail; Chang, Joon-Hyuk; Choi, Jeonghwan; Moon, Han-Gil Abstract: We present a novel general speech restoration model, DBP-Net (dual-branch parallel network), designed to effectively handle complex real-world distortions including noise, reverberation, and bandwidth degradation. Unlike prior approaches that rely on a single processing path or separate models for enhancement and restoration, DBP-Net introduces a unified architecture with dual parallel branches-a masking-based branch for distortion suppression and a mapping-based branch for spectrum reconstruction. A key innovation behind DBP-Net lies in the parameter sharing between the two branches and a cross-branch skip fusion, where the output of the masking branch is explicitly fused into the mapping branch. This design enables DBP-Net to simultaneously leverage complementary learning strategies-suppression and generation-within a lightweight framework. Experimental results show that DBP-Net significantly outperforms existing baselines in comprehensive speech restoration tasks while maintaining a compact model size. These findings suggest that DBP-Net offers an effective and scalable solution for unified speech enhancement and restoration in diverse distortion scenarios. Thu, 01 Oct 2026 00:00:00 GMT https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211349 2026-10-01T00:00:00Z