-
Article
-
A New Paradigm of Artificial Neural Network Learning for Atmospheric and Oceanic Predictions: Physics-Informed Neural Networks and Operator Learning
대기 및 해양 예측을 위한 인공신경망 학습의 새로운 패러다임: 물리정보 신경망과 연산자 학습
-
Dong-Hoon Kim, Il-Ju Moon
김동훈, 문일주
- This study explores the potential of Physics-Informed Neural Networks (PINNs) and Operator Learning (OL) techniques in advancing scientific computation and prediction. PINNs …
- This study explores the potential of Physics-Informed Neural Networks (PINNs) and Operator Learning (OL) techniques in advancing scientific computation and prediction. PINNs integrate physical principles into neural network training, enabling accurate modeling and prediction of complex physical systems, even in data-scarce and noisy environments. They have been successfully applied to solve challenging nonlinear partial differential equations (PDEs), such as Euler and Navier-Stokes equations, and continue to evolve with variants. Meanwhile, OL methods, represented by Deep Operator Network (DeepONet) and Fourier Neural Operator (FNO), focus on learning mappings between function spaces. These methods excel in high-dimensional data processing and have demonstrated remarkable performance in applications such as global atmospheric modeling with NVIDIA’s FourCastNet. Hybrid approaches, such as Physics-Informed DeepONet (PIDON) and Physics-Informed Neural Operator (PINO), combine the strengths of PINNs and OL. These methods leverage data-driven learning and physical constraints, achieving superior generalization and prediction accuracy. Notably, PINO enables zero-shot super-resolution predictions by integrating multi-resolution data with PDE constraints. While PINNs and OL individually present powerful tools for modeling and prediction, their computational cost and sensitivity to noise pose challenges. Hybrid approaches offer a pathway to address these issues by optimizing their integration through quantitative analyses. Future research directions include accelerating training through high-performance computing, extending applications to multiscale problems, and designing innovative loss functions to enhance data efficiency. This work synthesizes the latest advancements in PINNs, OL, and hybrid methods, providing a new paradigm for precise and efficient scientific computation across diverse fields. - COLLAPSE
-
A New Paradigm of Artificial Neural Network Learning for Atmospheric and Oceanic Predictions: Physics-Informed Neural Networks and Operator Learning
-
Article
-
Characteristics of Global Sea Level Changes during ENSO periods
ENSO 기간 전 지구 해수면 변화 특징
-
Juhye Kang, Hyeonsoo Cha, Jae-Hong Moon
강주혜, 차현수, 문재홍
- Natural climate variability, such as El Niño and La Niña, can result global sea levels rise or fall over several months, which …
- Natural climate variability, such as El Niño and La Niña, can result global sea levels rise or fall over several months, which leads to rapid sea level changes in coastal areas. Thus, it is very important to identify the causes of sea level fluctuations during the El Niño-Southern Oscillation (ENSO). In this study, Gravity Recovery and Climate Experiment (GRACE) satellites and reanalysis data based on Array for Real-time Geostrophic Oceanography (Argo) from April 2002 to December 2022 were used to identify the characteristics of land mass and ocean density and examine the contribution of each process to Global Mean Sea Level (GMSL) changes during the ENSO period. The results show that the interannual variability of GMSL is highly correlated with ocean mass changes caused by Land Water Storage (LWS), which contributes a larger amount to GMSL than ocean density driven Steric Sea Level (SSL) changes. SSL exhibits significant regional variations, representing the distinct dipole pattern of the tropical Pacific sea levels during the ENSO period. During El Niño period, SSL decreased by about -11 cm in the western tropical Pacific and increased by about 7 cm in the eastern Pacific. In contrast, during La Niña, SSL increased by approximately 10 cm in the tropical western Pacific and decreased by approximately -7 cm in the eastern Pacific. LWS pattern indicated negative anomalies of more than -5 cm in India, eastern China, and northern South America, and positive anomalies of more than ~5 cm in southern China and southeastern South America during El Niño period. During La Niña period, the opposite pattern was observed in these regions. The global LWS and total precipitation showed a high correlation of 0.61 with a lag of 6 months and the land precipitation during the ENSO period exhibited a similar spatial pattern to the LWS. Additionally, we quantified the contribution of LWS to GMSL over the continents. The results showed that Asia has the largest contribution to GMSL rise (39 ± 1.63%) during El Niño, while Africa is the largest contribution to GMSL decrease (53.67 ± 6.13%). - COLLAPSE
-
Characteristics of Global Sea Level Changes during ENSO periods
-
Article
-
Ongoing South China Sea Dispute: Is it Permitted for Continental States to Establish an Archipelagic Regime in their Outlying Archipelagos?
끝나지 않은 남중국해 분쟁: 대륙국가의 원양군도 체제는 인정될 수 있는가?
-
Minchul Kim, Hee Cheol Yang
김민철, 양희철
- This article explores the controversies between the United States (US) and China regarding the renewed attention given to China’s claims for an …
- This article explores the controversies between the United States (US) and China regarding the renewed attention given to China’s claims for an archipelagic regime encompassing four groups of islands in the South China Sea, following the 2016 arbitral award. It examines whether continental States, rather than archipelagic States, can establish straight baselines enclosing their outlying archipelagos in light of the United Nations Convention on the Law of the Sea (UNCLOS) and contemporary State practice. Following the 2016 South China Sea award, this issue became a key point of sharp debate between the US and China, particularly regarding China’s attempts to justify its claims to maritime jurisdiction within the nine-dash line. Although the claims of continental States for an archipelagic regime were not accepted during the Third United Nations Conference on the Law of the Sea, it cannot be definitively concluded that the practice of continental States establishing straight baselines around their outlying archipelagos is entirely precluded from evolving into customary international law. However, considering current State practice, it is difficult to argue that the recognition of an archipelagic regime for outlying archipelagos by continental States has met the requirements for the formation of a part of customary international law. - COLLAPSE
-
Ongoing South China Sea Dispute: Is it Permitted for Continental States to Establish an Archipelagic Regime in their Outlying Archipelagos?