Zobrazeno 1 - 10
of 255
pro vyhledávání: '"Naonori Ueda"'
Publikováno v:
Progress in Earth and Planetary Science, Vol 11, Iss 1, Pp 1-9 (2024)
Abstract Earthquake-induced crustal deformation provides valuable insights into the mechanisms of tectonic processes. Dislocation models offer a fundamental framework for comprehending such deformation, and two-dimensional antiplane dislocations are
Externí odkaz:
https://doaj.org/article/be1eacef7ad94ed3af7116247b9dd632
Publikováno v:
Machine Learning with Applications, Vol 17, Iss , Pp 100569- (2024)
Intense tropical cyclones (TCs) cause significant damage to human societies. Forecasting the multiple stages of TC intensity changes is considerably crucial yet challenging. This difficulty arises due to imbalanced data distribution and the need for
Externí odkaz:
https://doaj.org/article/96ef02108c6e4b88a5aa66405eadb287
Autor:
Yasuhiro Fujiwara, Yasutoshi Ida, Atsutoshi Kumagai, Masahiro Nakano, Akisato Kimura, Naonori Ueda
Publikováno v:
Data Science and Engineering, Vol 8, Iss 3, Pp 279-291 (2023)
Abstract Network representation learning is a de facto tool for graph analytics. The mainstream of the previous approaches is to factorize the proximity matrix between nodes. However, if n is the number of nodes, since the size of the proximity matri
Externí odkaz:
https://doaj.org/article/9f96328299044e299ef2c1e3deef884f
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-15 (2023)
Abstract Modeling typhoon-induced storm surges requires 10-m wind and sea level pressure fields as forcings, commonly obtained using parametric models or a fully dynamical simulation by numerical weather prediction (NWP) models. The parametric models
Externí odkaz:
https://doaj.org/article/f2d2df7e78794a13b55968b947f387c2
Autor:
Hirotaka Hachiya, Kotaro Nagayoshi, Asako Iwaki, Takahiro Maeda, Naonori Ueda, Hiroyuki Fujiwara
Publikováno v:
Machine Learning with Applications, Vol 14, Iss , Pp 100514- (2023)
Acquiring continuous spatial data, e.g., spatial ground motion, is essential to assess the damaged area and appropriately assign rescue and medical teams. Therefore, spatial interpolation methods have been developed to estimate the value of unobserve
Externí odkaz:
https://doaj.org/article/9aa99b2d16fe49e48796599d7a595e6f
Autor:
Vahideh Saeidi, Seyd Teymoor Seydi, Bahareh Kalantar, Naonori Ueda, Bahman Tajfirooz, Farzin Shabani
Publikováno v:
Geomatics, Natural Hazards & Risk, Vol 14, Iss 1 (2023)
AbstractThe estimation of water depth in coastal areas and shallow waters is crucial for marine management and monitoring. However, direct measurements using fieldwork methods can be costly and time-consuming. Therefore, remote sensing imagery is a p
Externí odkaz:
https://doaj.org/article/7cd8f62884dc4dc5b2f4fe701a87aeb4
Publikováno v:
Applied Network Science, Vol 8, Iss 1, Pp 1-16 (2023)
Abstract In this paper, we address the problem of earthquake declustering, and propose a k-nearest neighbors approach based on the selection of multiple-parent nodes with respect to each of the given earthquakes, which can be regarded as a natural ex
Externí odkaz:
https://doaj.org/article/d1c1c0ba27d149689493d20ef60ba609
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-9 (2022)
Modeling crustal deformation is critical for understanding of tectonic processes and earthquake potentials. Here, the authors propose a deep learning approach that can be extended in a straightforward manner to complex crustal structures and inverse
Externí odkaz:
https://doaj.org/article/a2c4df6a89bd4d758cb3e695afcf45d1
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-14 (2022)
One of the main challenges in the tsunami inundation prediction is related to the real-time computational efforts done under restrictive time constraints. Here the authors show that using machine learning-based model, we can achieve comparable accura
Externí odkaz:
https://doaj.org/article/4f1f436c6da5455aad9243195927ede3
Publikováno v:
Machine Learning with Applications, Vol 12, Iss , Pp 100473- (2023)
As the damage caused by heavy rainfall worsens, there is a growing demand for improved forecasts. One practical approach to address this issue is the linear integration of multiple existing forecasts, which allows for visualizing the contribution of
Externí odkaz:
https://doaj.org/article/3f276bd665454884b59cac11a1c3dfaf