检索结果-内蒙古大学图书馆

Multimodel ensemble estimation of Landsat-like global terrestrial latent heat flux using a generalized deep CNN-LSTM integration algorithm

引用

AGRICULTURAL AND FOREST METEOROLOGY 2024年 349卷

作者： Guo, Xiaozheng Yao, Yunjun Tang, Qingxin Liang, Shunlin Shao, Changliang Fisher, Joshua B. Chen, Jiquan Jia, Kun Zhang, Xiaotong Shang, Ke Yang, Junming Yu, Ruiyang Xie, Zijing Liu, Lu Ning, Jing Zhang, Lilin Beijing Normal Univ Fac Geog Sci State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China Liaocheng Univ Sch Geog & Environm Liaocheng 252000 Peoples R China Univ Hong Kong Dept Geog Sci Hongkong 999077 Peoples R China Chinese Acad Agr Sci Inst Agr Resources & Reg Planning State Key Lab Efficient Utilizat Arid & Semiarid A Natl Hulunber Grassland Ecosyst Observat & Res Stn Beijing 100081 Peoples R China Chapman Univ Schmid Coll Sci & Technol Univ Dr Orange CA 92866 USA Michigan State Univ Dept Geog Environm & Spatial Sci E Lansing MI 48823 USA Space Engn Univ Sch Space Informat Beijing 101416 Peoples R China Univ Twente Fac Geoinformat & Earth Observat ITC NL-7500 AE Enschede Netherlands

Accurate estimates of high-spatial-resolution global terrestrial latent heat flux (LE) from Landsat data are crucial for many basic and applied research. Yet current Landsat-derived LE products were developed using single algorithm with large uncertainties and discrepancies. Here we proposed a convolutional neural network-long short-term memory (CNN-LSTM)-based integrated LE (CNN-LSTM-ILE) framework that integrates five Landsatderived physical LE algorithms, topography-related variables (elevation, slope and aspect) and eddy covariance (EC) observations to estimate 30-m global terrestrial LE. CNN-LSTM-ILE not only conserves good performance of LE estimation from pure deep learning (DL) algorithm, but partially inherits physical mechanism of the individual physical algorithms for improving the generalization of the integration algorithms for extreme cases. CNN-LSTM is an algorithm that combines two deep learning structures (CNN and LSTM) to effectively utilize the spatial and temporal information contained in the forcing inputs. The data were collected from 190 globally distributed EC observations from 2000 to 2015 and were provided by FLUXNET. The cross-validation results indicated that the CNN-LSTM integration algorithm improved the LE estimates by reducing the root mean square error (RMSE) of 5-8 W/m2 and increasing Kling-Gupta efficiency (KGE) of 0.05-0.16 when compared with the individual LE algorithms and the results of three other machine learning integration algorithms (multiple linear regression, MLR;random forest, RF;and deep neural networks, DNN). The CNN-LSTM integration algorithm had highest KGE (0.81) and R2 (0.66) compared to ground-measured and was applied to generate the Landsat-like regional and global terrestrial LE. An innovation of our strategy is that the CNN-LSTM-ILE model integrates pixel proximity effects and daily LE variations to enhance the accuracy of 16-day LE estimations. This approach can produce a more reliable Landsat-like global ter

关键词： Latent heat flux integration algorithm CNN-LSTM Landsat High -spatial -resolution products

来源：评论

学校读者我要写书评

暂无评论

Development of an explicit time integration algorithm based on optimal integration parameter updating

引用

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS 2023年第15期52卷 5117-5140页

作者： Fu, Zhao-Yang Li, Hong-Nan Li, Chao Dalian Univ Technol State Key Lab Coastal & Offshore Engn Dalian Peoples R China Shenyang Jianzhu Univ Sch Civil Engn Shenyang Peoples R China Dalian Univ Technol State Key Lab Coastal & Offshore Engn Dalian 116023 Peoples R China

integration algorithm is an important mean to solve the discrete time equations of structural dynamics in earthquake engineering. In this paper, a new model-based explicit integration algorithm, featured by optimization-based integration parameter updating, is developed for a more accurate and efficient solution of structural dynamic problems. The new integration algorithm is designed to yield minimum error and controllable numerical dispersion under the premise of stability by defining objective functions and constraints. Numerical properties of the new integration algorithm are investigated in details using the amplification matrix method for a linear elastic single degree-of-freedom system. Meanwhile, representative numerical examples and complex structure examples are analyzed and compared with other representative algorithms. As a result, the proposed algorithm yields comparable numerical characteristics with other methods, but exhibits pronounced superiority in controllable algorithmic dissipation, higher precision, and better efficiency. Therefore, the new integration algorithm possesses extensive application prospect in solving complicated linear and nonlinear structural dynamic problems.

关键词： dynamic analysis explicit method integration algorithm numerical analysis stability

来源：评论

学校读者我要写书评

暂无评论

A dual-explicit model-based integration algorithm with higher-order accuracy for structural dynamics

引用

APPLIED MATHEMATICAL MODELLING 2022年 110卷 513-541页

作者： Fu, Bo Zhang, Fu-Tai Changan Univ Sch Civil Engn Xian 710061 Peoples R China

Several model-based or structure-dependent integration algorithms with explicit displacement formulation and unconditional stability are recently developed. According to the difference equations, these algorithms can be divided into dual-explicit and semi-explicit, where the first category algorithms are explicit for both displacement and velocity, while the second category are only explicit for displacement. The well-known Chen-Ricles (CR) and Chang algorithms are two representatives of dual-explicit and semi-explicit model-based algorithms, respectively. The model-based integration algorithms are promising with excellent computing efficiency, but most of them are second-order accurate. In this paper, a new dual-explicit (NDE) algorithm with higher-order accuracy is developed. The integration parameters of the NDE algorithm are obtained by using the pole mapping and second-order Pade approximation. Numerous important numerical characteristics including the consistency and local truncation error, stability, numerical dispersion and energy dissipation and overshoot are systematically analyzed for the new algorithm. It is found that the NDE algorithm is fourth-order accurate for free vibration without damping. As for forced vibration with/without damping and free vibration with damping, the NDE algorithm is no longer fourth-order accurate, but it is still more accurate than the CR and Chang algorithms. In addition, the period error of the algorithm is extremely small. Three representative numerical examples are finally provided to demonstrate the high accuracy of the NDE algorithm. Several classical and latest model-based integration algorithms and three fourth-order accurate algorithms are also adopted for comparisons. It has been proved that the NDE algorithm has much better performance than other selected model-based algorithms. (C) 2022 Elsevier Inc. All rights reserved.

关键词： integration algorithm Explicit Model-based Accuracy Period elongation Structural dynamics

来源：评论

学校读者我要写书评

暂无评论

An explicit integration algorithm for the unified rate-dependent elastoplastic damage model applied to high-rate dynamics

引用

MATERIALS TODAY COMMUNICATIONS 2021年 26卷

作者： Huang, Ruiyuan Li, Yi Nanjing Univ Sci & Technol Natl Key Lab Transient Phys Nanjing 210094 Peoples R China China Aerodynam Res & Dev Ctr Hyperveloc Impact Res Ctr Mianyang 621000 Sichuan Peoples R China

The main purpose of this work is to present an explicit integration algorithm for the unified rate-dependent elasto-plastic damage model. In the new integration algorithm, the plastic correction is solved by the following two assumptions: Constant equivalent strain rate;the direction of the deviatoric stress tensor remains unchanged if no plastic strain occurs. When the stress tensor at the initial moment is on the yield surface, both the plastic multiplier and the equivalent plastic strain increment obtained by the plastic correction method proposed in this paper is the same as that obtained by the plastic flow method. It indirectly proves the rationality of the plastic correction method. Then, both the traditional return mapping algorithm and this new integration algorithm are applied to the modified Johnson-Cook constitutive model and Cowper-Symonds model. Simulation of the Split Hopkinson pressure bar (SHPB) experiments using the modified Johnson-Cook constitutive model and Cowper-Symonds model, respectively. The stress error and the accumulated stress error are introduced to evaluate the accuracy of the plasticity integration algorithm. Numerical simulation results show that the accuracy of the new integration algorithm is higher than the traditional return mapping algorithm.

关键词： integration algorithm Plastic multiplier Rate-dependent elasto-plastic damage model Strain rate effect Split hopkinson pressure bar (SHPB)

来源：评论

学校读者我要写书评

暂无评论

An innovative procedure to improve integration algorithm for modified Cam-Clay plasticity model

引用

COMPUTERS AND GEOTECHNICS 2020年 124卷 103604-103604页

作者： Sanei, Manouchehr Duran, Omar Devloo, Philippe R. B. Santos, Erick S. R. Univ Estadual Campinas Mech Engn Dept FEM Petr Engn Div Campinas SP Brazil Univ Paris Est Ctr Enseignement & Rech Math & Calcul Sci CERMICS ENPC Paris France Univ Estadual Campinas Civil Engn Dept FEC Campinas SP Brazil Petrobras SA Res & Dev Ctr Cenpes Rio De Janeiro RJ Brazil

An innovative numerical scheme to improve the integration algorithm for critical state elastoplasticity is presented and detailed with special consideration to the modified Cam-Clay model. The scheme is based on a rotation of the principal stresses and represents the elastoplastic model in a rotated Haigh-Westergaard space. Such an approach allows the calculation of modified Cam-Clay tobe computationally stable and easy to implement. The validity of the proposed scheme is verified by comparing the numerical results with analytic solutions.

关键词： Critical state elastoplasticity Modified Cam-Clay integration algorithm Return mapping Rotated Haigh-Westergaard space

来源：评论

学校读者我要写书评

暂无评论

Improved Krylov Precise Time integration algorithm for Structural Dynamic Equations

引用

AIAA JOURNAL 2019年第8期57卷 3548-3555页

作者： Chen, Z. L. ChengDu Univ Technol State Key Lab Geohazard Prevent & Geoenvironm Pro Chengdu 610059 Sichuan Peoples R China

An improved Krylov precise time-step integration algorithm is proposed to solve the second-order differential equations with arbitrary excitation directly and efficiently. This method could tackle the complex excitations and improve the computing efficiency by determining the bound of iterative subspace (m) accurately. The upper bound of m could be obtained by computational efficiency analysis, whereas the error estimation is employed to compute the lower bound of m. Hence, the application of the improved Krylov precise time-step integration algorithm could be extended widely by determining the bound of m. Two numerical examples are also presented to demonstrate the practicability and the applicability of the proposed method.

关键词： integration algorithm Computing Second Order Differential Equations Stiffness Matrices Computing Cost Structural Modeling

来源：评论

学校读者我要写书评

暂无评论

Combining multi-layer integration algorithm with background prior and label propagation for saliency detection

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2017年第Oct.期48卷 110-121页

作者： Xia, Chenxing Zhang, Hanling Gao, Xiuju Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Engn Ctr Network Monitoring Nanjing 210044 Jiangsu Peoples R China

In this paper, we propose a novel approach to automatically detect salient regions in an image. Firstly, some corner superpixels serve as the background labels and the saliency of other superpixels are determined by ranking their similarities to the background labels based on ranking algorithm. Subsequently, we further employ an objectness measure to pick out and propagate foreground labels. Furthermore, an integration algorithm is devised to fuse both background-based saliency map and foreground-based saliency map, meanwhile an original energy function is acted as refinement before integration. Finally, results from multiscale saliency maps are integrated to further improve the detection performance. Our experimental results on five benchmark datasets demonstrate the effectiveness of the proposed method. Our method produces more accurate saliency maps with better precision-recall curve, higher F-measure and lower mean absolute error than other 13 state-of-the-arts approaches on ASD, SED, ECSSD, iCoSeg and PASCAL-S datasets. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Corner Objectness Energy function integration algorithm Multi-layer

来源：评论

学校读者我要写书评

暂无评论

Two families of dual-explicit model-based integration algorithms with controllable numerical damping for structural dynamic problems

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2024年 218卷

作者： Fu, Bo Ilunga, Stephane Lavery Chen, Jin Changan Univ Sch Civil Engn Xian 710061 Peoples R China Shandong Jianzhu Univ Key Lab Bldg Struct Retrofitting & Underground Spa Minist Educ Jinan 250101 Peoples R China

Based on the recently proposed multi-sub-step implicit beta 1/beta 2-Bathe method and a novel mapping strategy on the error equation, this paper presents two families of dual-explicit model-based integration algorithms for solving linear and nonlinear dynamic problems. Firstly, the dualexplicit formulations of the well-known Chen and Ricles (CR) algorithm are adopted for the new algorithms. By matching the error equations of the new algorithms and the implicit beta 1/beta 2Bathe method, the model-based integration parameters of the new algorithms are then derived. After analyzing the numerical properties of the two algorithms, it can be found that they are unconditionally stable for linear and nonlinear softening dynamic problems when the governing integration parameters are within specific ranges. Besides the two algorithms' numerical dispersion and energy dissipation are identical to the parent algorithm, i.e., the beta 1/beta 2-Bathe method. The overshooting issue of the proposed algorithms is less prominent than in some representative model-based algorithms. Finally, two numerical examples are used to investigate the computational efficiency and accuracy of the new algorithms compared to the parent algorithm and some existing model-based algorithms, including those with controllable damping, i.e., the KR-alpha and MKR-alpha methods. The results show that the two families of new algorithms are less computationally expensive than the parent algorithm as they adopt dual-explicit and single-step formulation. In addition, it is also observed that the developed algorithms have a better performance of damping out the spurious effect at high modes than the KR-alpha and MKR-alpha methods.

关键词： integration algorithm Model -based Numerical damping Explicit

来源：评论

学校读者我要写书评

暂无评论

Early warning model based on support vector machine ensemble algorithm

引用

JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY 2025年第3期76卷 411-425页

作者： He, Sang-sang Hou, Wen-hui Chen, Zi-yu Liu, Hui Wang, Jian-qiang Cheng, Peng-fei Cent South Univ Sch Business Changsha 410083 Peoples R China Hunan Univ Finance & Econ Sch Engn Management Changsha Peoples R China Hunan Univ Sci & Technol Hunan Engn Res Ctr Intelligent Decis Making & Big Xiangtan Peoples R China

Support Vector Machine (SVM) is a powerful machine learning technique often applied in various early warning scenarios. When using SVM for binary classification, its output results can be converted into a probability distribution based on sample categories. Through the analysis of the results, it is found that when the probability of a sample belonging to a positive class is equivalent to the probability of a sample belonging to a negative class, there is a high possibility of misclassification of the sample. To address this issue, this study proposes a new SVM ensemble model construction method. We generate SVM sub-classifiers to extract error prone set, and utilise three different combination rules to construct ensemble model based on the output probability of the samples. The accuracy of the whole data set is improved for the classification accuracy of the easily misclassified data are improved. This research evaluated the model based on Wind turbine SCADA data and UCI benchmark datasets. According to the research results, the accuracy rate of SCADA data is as high as 97.52%, and the accuracy rate of German credit data is 77.50%. Meanwhile, the comparison with other methods also validates the effectiveness of the proposed method.

关键词： Early warning support vector machine integration algorithm ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Multiscale modeling of diffuse damage and localized cracking in quasi-brittle materials under compression with a quadratic friction law

引用

INTERNATIONAL JOURNAL OF SOLIDS AND STRUCTURES 2024年 304卷

作者： Zhao, Lun-Yang Ren, Lu Liu, Ling-Hui Lai, Yuan-Ming Niu, Fu-Jun You, Tao South China Univ Technol South China Inst Geotech Engn Sch Civil Engn & Transportat Guangzhou 510641 Peoples R China South China Univ Technol State Key Lab Subtrop Bldg & Urban Sci Guangzhou 510641 Peoples R China Univ Leoben Dept Geoenergy A-8700 Leoben Austria

The diffuse damage and localized cracking of quasi-brittle materials ( i.e. , rocks and concretes) under compression can be delineated by a matrix-microcrack system, wherein a solid matrix phase is weakened by a large number of randomly oriented and distributed microcracks, and the macroscopic cracking is formed by a progressive evolution of microcracks. Several homogenization-based multiscale models have been proposed to describe this matrix-microcrack system, but most of them are based on a linear friction law on the microcrack surface, rendering a linear strength criterion. In this paper, we propose a new quadratic friction law within the local multiscale friction-damage (LMFD) model to capture the plastic distortion due to frictional sliding along the rough microcrack surface. Following that, a macroscopic Ottosen-type nonlinear strength criterion is rationally derived with up-scaling friction-damage coupling analysis. An enhanced semi-implicit return mapping (ESRM) algorithm with a substepping scheme is then developed to integrate the complex nonlinear constitutive model. The performance of LMFD model is evaluated compared to a wide range of experimental data on plain concretes, and the robustness of ESRM algorithm is assessed through a series of numerical tests. Subsequently, to effectively describe the localized cracking process, a regularization scheme is proposed by combining the phase-field model with the established LMFD model, and the discretization independent crack localization is numerically verified.

关键词： Quasi-brittle materials Homogenization-based multiscale modeling Quadratic friction law integration algorithm Phase-field model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：