检索结果-内蒙古大学图书馆

A novel finer soil strength mapping framework based on machine learning and remote sensing images

COMPUTERS & GEOSCIENCES 2024年 182卷

作者： Wang, Ruizhen Wan, Siyang chen, Weitao Qin, xuwen Zhang, Guo Wang, Lizhe China Univ Geosci Key Lab Geol Survey & Evaluat Minist Educ Wuhan 430074 Peoples R China China Univ Geosci Fac Comp Sci Wuhan 430074 Peoples R China China Geol Survey Basic Survey Dept 45 Fuwai St Beijing 100037 Peoples R China

Soil strength is an important factor for assessing the vehicle trafficability in the wilds and making reliable offroad path planning. Rating Cone index (RCI) has been widely used as an indicator of soil strength for mobility assessment. Currently, regional RCI are mainly obtained by using Soil Moisture Strength Prediction (SMSP) Model based on the Unified Soil Classification System (USCS) soil types and soil moisture at critical depth. However, USCS classification is inaccessible directly in most soil databases. And current soil moisture products are of coarse spatial resolution and only reliable in soil surface layer. It is costly to arrange ground survey for USCS soil type and the fine soil moisture in deeper layers cannot be obtained directly. To fill this gap, a novel framework is proposed to generate finer RCI-based soil strength map. To gain USCS soil classification in an un-surveyed study site, RF, GBDT, XGBoost and LCE ensemble learning models were trained with data from gSSURGO Database which contains USCS soil types and soil properties, and then make prediction on data from SoilGrids Database by using same properties. Then, to obtain the finer soil moisture of critical depth, these treebased models were constructed with ground observation data, Sentinel-2 images, topographical data and soil properties with higher spatial resolution. The SMSP model is finally used to generate the finer daily soil strength map for the study site. The proposed framework highly improved the resolution and reliability of existing soil strength map generating methods, and can provide detailed soil strength information.

关键词： Soil strength Rating cone index Machine learning Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Submarine Continental Slopes Stability Prediction of Natural Gas HydratesBased on Machine Learning

Submarine Continental Slopes Stability Prediction of Natural...

引用

Offshore Technology Conference, OTC 2025

作者： chen, Yu He, Yufa Wang, Yixuan Zhou, Yunjian Fu, Qiang Qin, xuwen Liu, Dingyuan Tian, Zheng Zhang, Kexin CNOOC Research Institute Ltd State Key Laboratory of Offshore Natural Gas Hydrates Beijing China Huairou Laboratory Beijing China China Aero Geophysical Survey and Remote Sensing Center for Natural Resources Beijing China

ISBN: (纸本)9781959025610

In the process of extracting naturally-occurring oceanic gas hydrates, the dissociation of hydrates can causea reduction in soil strength. This reduction has the potential to trigger slope failure and submarine landslides,which present a catastrophic threat to offshore facilities and hydrate production. This research aims to create a robust and accurate machine-learning model that can efficiently predict stability of submarine continental slopes where gas hydrates are widespread. By collecting and analyzing 144 relevant cases, a comprehensive dataset was constructed, incorporating slope basic data, overlying and underlying layer data, and geological parameters of the hydrate layer. After conducting a correlation coefficient analysis between the characteristic parameters of the dataset and the output, the key characteristic parameters were determined. To model the dataset and assess its performance, four machine learning techniques were employed: Random Forest(RF), XGBoost, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Formation physical parameters, geotechnical parameters, and NGH parameters were taken as input parameters, and the stability of NGH slopes was taken as prediction indicator. Evaluation metrics such as the ROC and confusion matrix were employed to comprehensively evaluate these models’ classification ability. Among these algorithms,the RF algorithm achieves the best prediction accuracy and AUC value, demonstrating its potential in submarine continental slopes stability prediction of natural gas hydrates. Additionally, sensitive analysis using Gini impurity calculations revealed that hydrate decomposition degree is the most significant factor affecting slope stability, followed by the burial depth and thickness of the hydrate layer. The slope angle,cohesion, and internal friction angle also have significant impacts. This study provides a new perspective for predicting submarine continental slopes stability with NGH and offers a scientific

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Transform Sequential Data to Image for Detecting Covert Timing Channel

引用

International Journal of Network Security 2024年第2期26卷 224-234页

作者： Huang, xuwen chen, Yonghong Zhuang, Xiaolong Lin, Yuwei School of Computer Science and Technology Huaqiao University China Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University Xiamen Fujian 361000 China

The network covert timing channel utilizes inter-packet delay to encode binary data to achieve information leakage and other purposes. In recent years, Covert Timing Channels (CTCs) have been demonstrated to be applicable across various protocols and networks, posing a significant threat to network security. Simultaneously, new CTCs have challenged the efficacy of CTC detection schemes. The recent ϵ-κlibur and ϵ-κlibur-O channels exhibit structural and characteristic similarities to legitimate channels, rendering ML-based detection methods like GAS and Snap ineffective. In this paper, we investigate an approach based on Gramian Angular Field (GAF), Markov Transition Field (MTF), and Recurrence Plot (RP) image processing. We further employ the knowledge-distilled and compressed image classification model MobileVit for detection. Our approach achieves a detection rate 98.24% for seven different channels within a sampling window of 64 IPDs. Experimental results demonstrate our proposed scheme’s generality, sensitivity, and effectiveness. © 2024, Femto Technique Co.. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Lithological Unit Classification Based on Geological Knowledge-Guided Deep Learning Framework for Optical Stereo Mapping Satellite Imagery

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2023年 61卷 1页

作者： Zhou, Gaodian chen, Weitao Qin, xuwen Li, Jun Wang, Lizhe China Univ Geosci Fac Comp Sci Minist Educ Wuhan 430074 Peoples R China China Univ Geosci Minist Educ Key Lab Geol Survey & Evaluat Wuhan 430074 Peoples R China

Lithological unit classification (LUC) refers to the classification of different types of rocks within an area, and it has been widely used in many fields, such as resource surveys and infrastructure planning. However, traditional field surveys require a lot of resources and time. Since remote sensing technology can rapidly acquire information without regional limitations, many researchers have focused on classifying lithological units with remote sensing images. However, in an area covered by vegetation, the beneficial information directly provided by remote sensing images is limited. Moreover, lithological interpretation often requires geological prior knowledge for guidance, which cannot be provided by remote sensing images. Thus, this study designed a dual-branch deep learning model to extract geological prior knowledge from geological information, and improve the accuracy of LUC. In the process of feature transmission of the model, a Dense Attention residual-atrous spatial pyramid pooling (DA-ASPP) module was proposed to maximize the preservation of lithological units ' features. The DA-ASPP integrates the idea of dense connection into ASPP for multiscale object feature preservation and adds residual structure into the channel attention mechanism to screen out the representative features of lithological units. The study area was located in southeastern Hubei Province, China, with seven categories of lithological units. A total of seven deep learning networks were compared. The proposed method achieved a mean intersection over union (IOU) of 44.61% with a Macro-F1 of 56.54%, which were better than those of comparison models. Moreover, the visualization results demonstrated the superiority of the proposed model in LUC.

关键词： Dense attention residual dual branches lithological unit classification (LUC) prior knowledge remote sensing.

来源：评论

学校读者我要写书评

暂无评论

A bioorthogonal assembly based on metallophilic interactions for selective imaging and PDT treatment of cancer cells

引用

INORGANIC CHEMISTRY FRONTIERS 2022年第10期9卷 2290-2297页

作者： Da, xuwen Yu, Fei-Hu Zhang, Chao Wang, Zhanhua Jian, Yao Hou, Yuanjun chen, Yong Wang, Xuesong Zhou, Qianxiong Chinese Acad Sci Tech Inst Phys & Chem Key Lab Photochem Convers & Optoelect Mat Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Precise control of luminescence and singlet oxygen generation is important for selective photo-theranostic applications. In this work, bioorthogonal assembly based on d(10)MIDLINE HORIZONTAL ELLIPSISd(10) metallophilic interactions was first proposed for selective cancer cell imaging and photodynamic therapy (PDT) treatment as a proof of concept. [Au(NHC)(2)](+) (NHC = N-heterocyclic carbene) cations loaded on hyaluronic acid were selectively taken up by cancer cells. The subsequent incubation with [MX2](-) (M = Au or Cu and X = halide or arylacetylide) anions led to the bioorthogonal assembly of C3 + A5/A10 in cancer cells with luminescence turn-on and singlet oxygen generation upon irradiation. This work not only demonstrates that d(10)MIDLINE HORIZONTAL ELLIPSISd(10) metallophilic interactions can be readily harnessed for developing bioorthogonal assembly to realize precise cancer cell imaging and PDT, but also can stimulate the development of supramolecular interaction based bioorthogonal chemistry.

关键词： Cancer cells

来源：评论

学校读者我要写书评

暂无评论

基于物流管理的防窜码前关联软件设计与实现

引用

物流技术 2019年第6期38卷 84-88,115页

作者：陈延文陈旭文管永天水师范学院电子信息与电气工程学院甘肃天水741001 兰州达嘉喷码标识设备有限公司甘肃兰州730050

为解决食品饮料行业中的包装赋码与关联问题,设计了基于物流管理的防窜码前关联软件系统,介绍了该系统的功能模块与结构、流程以及软硬件接口、运行设计,最后结合系统的逻辑设计进一步说明了该软件系统的工作原理与特点。

关键词：物流管理防窜码前关联研华PCI卡

来源：评论

学校读者我要写书评

暂无评论

Effect of grinding depth on the rotating bending fatigue properties of 40Cr steel

引用

FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES 2022年第4期45卷 1292-1295页

作者： Zhou, Honggen chen, Jianzhi Bai, Xiaoxiang Li, Guochao Guan, Xiaoyan Du, Qin Li, Ning Jing, xuwen Jiangsu Univ Sci & Technol Sch Mech Engn Zhenjiang 212003 Jiangsu Peoples R China Beijing North Vehicle Grp Co Ltd Beijing Peoples R China

来源：评论

学校读者我要写书评

暂无评论

Investigation of mechanical and electronic properties of a novel quaternary transition-metal nitride Ti0.25W0.25V0.25Ta0.25N

引用

MATERIALS CHEMISTRY AND PHYSICS 2023年 310卷

作者： Xie, Quanmin Liu, xuwen Zhang, Zheng Nian, Xinzhe chen, Lei Jianghan Univ State Key Lab Precis Blasting Wuhan 430056 Peoples R China Jianghan Univ Hubei Key Lab Blasting Engn Wuhan 430056 Peoples R China Sichuan Jiaoda Engn Detect & Consulting Co Ltd Chengdu Peoples R China Baoji Univ Arts & Sci Coll Phys & Optoelect Technol Baoji 721016 Peoples R China

Multi-element transition-metal nitrides possessing combinations of outstanding mechanical and physical properties have attracted increasing attention due to its potential applications. Here, a new transition-metal nitride alloying four metal elements of Ti, W, V and Ta is proposed, in which the doping ratios of these four metal elements are equal. Using an improved structure searching method, the potential structures with low enthalpies were fully explored. An orthorhombic structure was firstly disclosed and verified to be its ground-state phase. It is the most energetically favorable structure in the pressure of 0 similar to 100 GPa. The phonon spectrum calculations demonstrated its lattice dynamical stability. Systematic study of its mechanical properties showed the orthorhombic structure not only possessed a large hardness of 32.4 GPa but also behaved a large indentation shear strength of about 30 GPa, greatly exceeding its well-known fcc-B1 phase (about 15 GPa). Meanwhile, we also compared the orthorhombic phase to its disordered structure within B1 phase by generating special quasirandom structures (SQS) with a 3 x 3 x 3 supercell (216 atoms), which can be viewed as its high-entropy phase. The results displayed this SQS system had comparable hardness and strength but greatly improved ductility and toughness relative to the ordered B1 phase.

关键词： Transition-metal nitride First-principles Mechanical properties Ideal strength Electronic structure

来源：评论

学校读者我要写书评

暂无评论

Pilot-scale catalytic ozonation pretreatment for improving the biodegradability of fixed-bed coal gasification wastewater

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2021年 148卷 13-19页

作者： chen, Xiaoya Wang, Chunrong Jiang, Longxin Li, Haiyan Wang, Jianbing He, xuwen China Univ Min & Technol Beijing Sch Chem & Environm Engn Beijing 100083 Peoples R China

Achieving zero liquid dischargeis a requirement for the development of the coal chemical industry;high pollutant concentration, strong biotoxicity, and poor biodegradability (BOD5/COD=0.1-0.2) make fixed-bed coal gasification wastewater difficult to treat. This study synthesized a Fe-Mn/lava catalyst (FMLC) and performed a pilot-scale test on catalytic ozonation for the pretreatment of fixed-bed coal gasification wastewater. The effects of ozone and catalyst dosages were investigated, and the changes in the organics, biotoxicity, and biodegradability of wastewater were analyzed using three-dimensional fluorescence spectroscopy, BOD5/COD, and specific oxygen uptake rate (SOUR). Energy consumption was also calculated. The removal efficiencies (at a flow rate of 1.0 m(3)/h, ozone dosage of 179 g/h, and catalyst dosage of 40 kg/m(3)) of COD and BOD5 were 61.77% and 16.98%, respectively, after 30 days of continuous operation. Toxic refractory macromolecular organic pollutants were transformed into small, biodegradable substances. BOD5/COD increased from 0.16 to 0.35, and SOUR decreased from 2.8460 to 2.3180 mgO(2)/(gMLSS.h). The operating cost was 1.24 kWh/kg COD. Catalytic ozonation as a pretreatment technology markedly improved biodegradability, reduced biotoxicity, and looks to be promising for treating fixed-bed coal gasification wastewater. (C) 2020 Published by Elsevier B.V. on behalf of Institution of Chemical Engineers.

关键词： Fixed-bed coal gasification wastewater Pilot-scale Catalytic ozonation Fe-Mn/lava catalyst Pretreatment Biodegradability

来源：评论

学校读者我要写书评

暂无评论

Efficient removal and recovery of phosphorus from industrial wastewater in the form of vivianite

引用

ENVIRONMENTAL RESEARCH 2023年第1期228卷 115848页

作者： Zhang, Yangzhong Qin, Jiafu chen, Zhenguo chen, Yongxing Zheng, xuwen Guo, Lu Wang, Xiaojun South China Univ Technol Sch Environm & Energy Guangzhou 510006 Peoples R China South China Normal Univ Sch Environm Guangzhou 510006 Peoples R China Hua An Biotech Co Ltd Foshan 528300 Peoples R China

With the shortage of phosphorus resources, the concept of phosphorus recovery from wastewater is generally proposed. Recently, phosphorus recovery from wastewater in the form of vivianite has been widely reported, which could be used as a slow-release fertilizer as well as the production of lithium iron phosphate for Li-ion batteries. In this study, chemical precipitation thermodynamic modeling was applied to evaluate the effect of solution factors on vivianite crystallization with actual phosphorus containing industrial wastewater. The modeling results showed that the solution pH influences the concentration of diverse ions, and the initial Fe2+ concentration affects the formation area of vivianite. The saturation index (SI) of vivianite increased with the initial Fe2+ concentration and Fe:P molar ratio. pH 7.0, initial Fe2+ concentration 500 mg/L and Fe:P molar ratio 1.50 were the optimal conditions for phosphorus recovery. Mineral Liberation Analyzer (MLA) accurately determined the purity of vivianite was 24.13%, indicating the feasibility of recovering vivianite from industrial wastewater. In addition, the cost analysis showed that the cost of recovering phosphorus by the vivianite process was 0.925 USD/kg P, which can produce high-value vivianite products and realize "turn waste into treasure".

关键词： Phosphorus recovery Vivianite Crystallization zone Resource recycling

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：