東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Machine Learning Tools to Identify S...

Albakri, Hamzeh,

Linked to FindBook

Google Book

Amazon

博客來

Machine Learning Tools to Identify Soil Properties Using Subsurface Ground Penetrating Radar /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine Learning Tools to Identify Soil Properties Using Subsurface Ground Penetrating Radar // Hamzeh Albakri.
Author:	Albakri, Hamzeh,
Description:	1 electronic resource (83 pages)
Notes:	Source: Masters Abstracts International, Volume: 86-12.
Contained By:	Masters Abstracts International86-12.
Subject:	Geophysics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31934104
ISBN:	9798280761391

Machine Learning Tools to Identify Soil Properties Using Subsurface Ground Penetrating Radar /
Albakri, Hamzeh,

Machine Learning Tools to Identify Soil Properties Using Subsurface Ground Penetrating Radar /Hamzeh Albakri. - 1 electronic resource (83 pages)

Source: Masters Abstracts International, Volume: 86-12.

The traditional approach to measuring soil density normally requires core sampling, a process that involves soil extraction from different depths for further analysis in the laboratory, this has been considered extremely time-consuming and labor-intensive. Core sampling disrupts the structure of the soil itself, apart from the fact that a great deal of care must be exercised during its transportation for correct analysis. Therefore, core sampling methods, which are inefficient, have driven the search for more effective approaches to measuring soil density.The Ground Penetrating Radar is a non-destructive testing technique that utilizes electromagnetic waves to map subsurface features, in this thesis, The SIR-4000 GPR antenna produced by Geophysical Survey Systems Inc. was used to study a variety of soil properties by exploring methods to investigate soil moisture content and soil density. The variation of the Dielectric and amplitude values obtained from the GPR system served as key data points in the study. Furthermore, the data was interpreted further using RADAN 7 post-processing software. The software facilitated the analysis of the raw ground-penetrating radar data by enabling the visualization and processing of the dielectric and amplitude readings.The primary objective of this study is to produce a predictive model for estimating soil density using GPR data in different conditions. Two sequential models were created to achieve this, utilizing GPR amplitude data in conjunction with moisture & dielectric values. The first model consists of two parts (Model 1. A) to predict the dielectric constant and (Model 1. B) to predict the moisture content, on the other hand, (Model 2) predicts Density from the input of the first model. Training Model 1. A Model 1. B and Model 2 yielded R2 Values of 0.885, 0.97, and 0.753, respectively.

English

ISBN: 9798280761391Subjects--Topical Terms:

535228
Geophysics.
Subjects--Index Terms:

Machine learning

Machine Learning Tools to Identify Soil Properties Using Subsurface Ground Penetrating Radar /
LDR:03331nmm a22004333i 4500 001 2435801
005 20251029060354.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798280761391
035 $a (MiAaPQD)AAI31934104
035 $a AAI31934104
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Albakri, Hamzeh, $e author. $3 3826237
245 1 0 $a Machine Learning Tools to Identify Soil Properties Using Subsurface Ground Penetrating Radar / $c Hamzeh Albakri.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (83 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-12.
500 $a Advisors: Hamoush, Sameer A. Committee members: Abu-Lebdeh, Taher; Megri, Ahmed; Yi, Sun.
502 $b M.S. $c North Carolina Agricultural and Technical State University $d 2025.
520 $a The traditional approach to measuring soil density normally requires core sampling, a process that involves soil extraction from different depths for further analysis in the laboratory, this has been considered extremely time-consuming and labor-intensive. Core sampling disrupts the structure of the soil itself, apart from the fact that a great deal of care must be exercised during its transportation for correct analysis. Therefore, core sampling methods, which are inefficient, have driven the search for more effective approaches to measuring soil density.The Ground Penetrating Radar is a non-destructive testing technique that utilizes electromagnetic waves to map subsurface features, in this thesis, The SIR-4000 GPR antenna produced by Geophysical Survey Systems Inc. was used to study a variety of soil properties by exploring methods to investigate soil moisture content and soil density. The variation of the Dielectric and amplitude values obtained from the GPR system served as key data points in the study. Furthermore, the data was interpreted further using RADAN 7 post-processing software. The software facilitated the analysis of the raw ground-penetrating radar data by enabling the visualization and processing of the dielectric and amplitude readings.The primary objective of this study is to produce a predictive model for estimating soil density using GPR data in different conditions. Two sequential models were created to achieve this, utilizing GPR amplitude data in conjunction with moisture & dielectric values. The first model consists of two parts (Model 1. A) to predict the dielectric constant and (Model 1. B) to predict the moisture content, on the other hand, (Model 2) predicts Density from the input of the first model. Training Model 1. A Model 1. B and Model 2 yielded R2 Values of 0.885, 0.97, and 0.753, respectively.
546 $a English
590 $a School code: 1544
650 4 $a Geophysics. $3 535228
650 4 $a Engineering. $3 586835
650 4 $a Soil sciences. $3 2122699
653 $a Machine learning
653 $a Soil properties
653 $a Map subsurface features
653 $a Ground Penetrating Radar
690 $a 0543
690 $a 0467
690 $a 0537
690 $a 0481
710 2 $a North Carolina Agricultural and Technical State University. $b Civil Engineering. $e degree granting institution. $3 3826238
720 1 $a Hamoush, Sameer A. $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-12.
790 $a 1544
791 $a M.S.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31934104