{"title":"FDTD Medium Dimension Selection Guidelines for GPR Synthetic Data Generation","authors":"Noushin Khosravi Largani;Seyed Zekavat;Himan Namdari","doi":"10.1109/LGRS.2024.3510683","DOIUrl":null,"url":null,"abstract":"Ground-penetrating radar (GPR) has been traditionally used for subsurface assessment. In many applications, such as precision agriculture via drone-borne radar, it is critical to use machine learning (ML) techniques to map GPR received signals into soil subsurface moisture and texture. Supervised ML methods need a large number of labeled data for their training process which is expensive and time-consuming to attain through actual field measurements. The gprMax software, which is created based on the finite difference time domain (FDTD) method, has been introduced as a reliable tool to emulate soil media and create synthetic labeled data. Proper selection of gprMax soil medium dimensions is critical to the generation of reliable synthetic data. The selection of large soil medium dimensions for gprMax emulations leads to synthetic data consistent with realistic scenarios. However, larger medium dimensions lead to higher computation complexity. This letter investigates and validates a proper selection of medium dimensions that maintains a tradeoff across the accuracy and computational complexity of creating synthetic data. The results of this study are critical to researchers who adopt gprMax or any FDTD-oriented emulations for soil subsurface assessment. To maintain a tradeoff between accuracy and complexity, the letter confirms that the minimum medium surface dimension should be in the order of 1.5 times the maximum wavelength.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-4"},"PeriodicalIF":0.0000,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10777481/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Ground-penetrating radar (GPR) has been traditionally used for subsurface assessment. In many applications, such as precision agriculture via drone-borne radar, it is critical to use machine learning (ML) techniques to map GPR received signals into soil subsurface moisture and texture. Supervised ML methods need a large number of labeled data for their training process which is expensive and time-consuming to attain through actual field measurements. The gprMax software, which is created based on the finite difference time domain (FDTD) method, has been introduced as a reliable tool to emulate soil media and create synthetic labeled data. Proper selection of gprMax soil medium dimensions is critical to the generation of reliable synthetic data. The selection of large soil medium dimensions for gprMax emulations leads to synthetic data consistent with realistic scenarios. However, larger medium dimensions lead to higher computation complexity. This letter investigates and validates a proper selection of medium dimensions that maintains a tradeoff across the accuracy and computational complexity of creating synthetic data. The results of this study are critical to researchers who adopt gprMax or any FDTD-oriented emulations for soil subsurface assessment. To maintain a tradeoff between accuracy and complexity, the letter confirms that the minimum medium surface dimension should be in the order of 1.5 times the maximum wavelength.