相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Interdisciplinary Applications
Ying H. Huang et al.
Summary: The physics-informed neural network (PINN) is used to solve various systems, including fluid dynamics problems. However, the original PINN method has issues with the gradients of the residuals, leading to poor results. By applying existing techniques that incorporate both boundary and initial conditions in the governing equations, the bif-PINN approach shows improved convergence, lower memory usage, and faster training. Tests on different fluid dynamics problems demonstrate the advantages of bif-PINN over PINN in terms of performance and accuracy.
JOURNAL OF COMPUTATIONAL PHYSICS
(2023)
Article
Environmental Sciences
Ozren Hasan et al.
Summary: The study successfully classified bottom sediments using integrated data from multibeam echosounder, backscatter echosounder, side-scan sonar, and sub-bottom profiling, along with ground-truthing and sediment analyses. It also revealed distinct geomorphological features, including submerged tufa barriers and carbonate mounds, and constructed a prediction map for marine sedimentary carbon using multibeam echosounder data. The study emphasizes the importance of additional inputs to achieve accurate results.
Article
Chemistry, Multidisciplinary
Arman Yeleussinov et al.
Summary: This paper aims to improve the accuracy of Kazakh handwriting text recognition (KHTR) by using a generative adversarial network (GAN), which includes a handwriting word image generator and an image quality discriminator. Multiple losses are used to encourage the generator to learn the structural properties of the texts in order to obtain high-quality handwritten text images. The proposed approach generates document images that preserve texture details and simulate different writer styles, resulting in better OCR performance in public databases. The method achieves a character error rate (CER) of 11.15% and a word error rate (WER) of 25.65%.
APPLIED SCIENCES-BASEL
(2023)
Article
Geography, Physical
Liquan Sun et al.
Summary: This research presents a method that combines deep learning and geospatial analysis to extract check dam areas from high-resolution Gaofen-2 (GF-2) multispectral imageries. The results showed that the deep learning models could accurately and quickly extract dam areas, and the use of RGB + DEM images achieved the best segmentation results.
EARTH SURFACE PROCESSES AND LANDFORMS
(2023)
Article
Environmental Sciences
Xilin Wu et al.
Summary: Human regulations have significantly affected the hydrogeomorphic processes and functions of silt-laden rivers, such as the braided reach of the lower Yellow River. The construction of the Xiaolangdi Reservoir and river training works have altered the conditions of the river, leading to changes in channel morphology and flood transport capacity. These changes are primarily driven by anthropic flow regime changes and boundary modifications. Managing erosion and deposition processes is crucial for stabilizing silt-laden rivers, requiring integrated management of soil conservation, dam regulation, and floodplain governance at a basin scale. Lessons from the lower Yellow River have important implications for other rivers facing siltation issues, particularly in the Global South.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Energy & Fuels
Daniyar Kazidenov et al.
Summary: Coarse-graining methods for a three-dimensional CFD-DEM model are developed to investigate sand production phenomenon and are compared with the original fine-scale model. The results show good agreement between the original and coarse-grained models in terms of fluid streamlines, fluid and particle velocities. The performance of two coarse-grained models is evaluated, and it is found that the SSW model is more accurate in terms of particle size distribution and sand production rate, while the SSP model performs better in terms of speedup.
GAS SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
N. Sukumar et al.
Summary: In this paper, a new approach based on distance fields is introduced to accurately impose boundary conditions in physics-informed deep neural networks. By using geometry-aware trial functions and concepts from constructive solid geometry and generalized barycentric coordinates, the method constructs an approximate distance function to the boundary of a domain and exactly satisfies homogeneous and inhomogeneous boundary conditions. This approach eliminates modeling errors and ensures kinematic admissibility.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2022)
Proceedings Paper
Computer Science, Information Systems
Bakdauren Narbayev et al.
Summary: This study investigates the impact of wind comfort on pedestrians using computational fluid dynamics around the tallest building in Kazakhstan. Numerical simulations reveal that the wind velocity profile can vary in different areas, affecting pedestrian comfort conditions.
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2022 WORKSHOPS, PART IV
(2022)
Article
Environmental Sciences
Colin B. Phillips et al.
Summary: This Perspective examines how the size and shape of alluvial river channels are controlled and adjusted by the flow of water and sediment. The feedback between flow and form modulates flood risk and the impacts of climate and land-use change. Despite variations in hydro-climates, sediment supply, geology, and vegetation, rivers follow remarkably consistent hydraulic geometry scaling relations.
NATURE REVIEWS EARTH & ENVIRONMENT
(2022)
Article
Engineering, Marine
Chen Cheng et al.
Summary: This paper utilizes physics informed neural network (PINN) to solve VIV and WIV problems of cylinders, combining RANS equations and structure dynamic equations, using CFD technique for data acquisition, and validating the effectiveness of PINN method in solving VIV and WIV problems of cylinders.
Article
Engineering, Geological
Nurhan Ecemis
Summary: The study investigates the seismic response of stratified sands interlayered with silts using large-scale model tests and numerical simulations, showing that the thickness of the silt layer significantly influences liquefaction resistance and that the properties of silt and sand beneath the silt layer affect the dissipation of excess pore pressure and ground settlement after shaking. Simplified liquefaction evaluation procedures may lead to inaccuracies when applied to soil profiles with various layering patterns in the field.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2021)
Article
Environmental Sciences
Zhili Zhang et al.
Summary: Accurately extracting water bodies from high-resolution remote sensing imagery is a major challenge. This study addresses the difficulty in identifying water body boundaries and semantic inconsistency in feature fusion by designing a novel multi-feature extraction and fusion module. Extensive experiments demonstrate that the proposed method achieves state-of-the-art segmentation performance and robustness in challenging water body extraction scenarios.
Article
Engineering, Multidisciplinary
Xuhui Meng et al.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2020)
Article
Engineering, Civil
Rajiv Sinha et al.
JOURNAL OF HYDROLOGY
(2019)
Article
Biology
Robert J. Hawley
Article
Environmental Sciences
Francesco Dottori et al.
NATURE CLIMATE CHANGE
(2018)
Article
Engineering, Environmental
Jasmin Fetzer et al.
Article
Engineering, Civil
Peng Yao et al.
COASTAL ENGINEERING
(2015)
Article
Geosciences, Multidisciplinary
Jose Antonio Constantine et al.
Review
Multidisciplinary Sciences
Philip M. Marren et al.
SCIENTIFIC WORLD JOURNAL
(2014)
Article
Thermodynamics
Reza Khodadadi Azdaboni et al.
Article
Physics, Multidisciplinary
Peter Holland
INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS
(2012)
Article
Engineering, Civil
Laurent Goutiere et al.
JOURNAL OF HYDRAULIC RESEARCH
(2011)
Article
Mathematics, Applied
Hamid Alemi Ardakani et al.
EUROPEAN JOURNAL OF APPLIED MATHEMATICS
(2010)
Article
Engineering, Civil
Lukas Schmocker et al.
JOURNAL OF HYDRAULIC RESEARCH
(2009)
Review
Engineering, Civil
David C. Froehlich
JOURNAL OF HYDRAULIC ENGINEERING-ASCE
(2008)
