Presenter Information

Nolen RitzelFollow
Lauren BakerFollow

Presentation Type

Poster Presentation

Abstract

Artificial Intelligence (AI) has demonstrated significant potential in engineering applications, specifically in soil gradation analysis using two-dimensional imagery. While studies have shown experimental success, AI-based soil gradation methods are not widely used in industry due to the lack of field research performed. Moreover, the current methodology is suitable but lacks advancement. The motivation behind the research was to aid in bridging this gap between experimental research and industry application by determining whether existing AI tools can and/or should be applied to bank soil in streams and rivers in the Greater Nashville Area. Several locations next to streams and rivers distributed throughout Davidson County, Tennessee were selected to collect soil samples to comprise a soil gradation profile for the Greater Nashville Area. This data, combined with a literature review of existing AI gradation tools, provided metrics to determine which existing AI tool may be most applicable to the Greater Nashville Area. Additionally, this study includes a comparative analysis between AI image analysis and standard sieve analysis for river- and stream-bank soil gradations, focusing on time and cost differences between the two methods. This analysis provides the basis for determining whether such AI tools should be applied professionally. Based on small particle size distribution from field testing, AI tools that classify fine gravel and sands would be of more use to the Greater Nashville Area. These AI tools, however, require high resolution microscopic imagery, which may be difficult to obtain in the field.

Faculty Mentor

Dr. Jordan Wilson

Share

COinS
 

AI Photography-Based Gradation Feasibility Study for Streams and Rivers in Davidson County, TN

Artificial Intelligence (AI) has demonstrated significant potential in engineering applications, specifically in soil gradation analysis using two-dimensional imagery. While studies have shown experimental success, AI-based soil gradation methods are not widely used in industry due to the lack of field research performed. Moreover, the current methodology is suitable but lacks advancement. The motivation behind the research was to aid in bridging this gap between experimental research and industry application by determining whether existing AI tools can and/or should be applied to bank soil in streams and rivers in the Greater Nashville Area. Several locations next to streams and rivers distributed throughout Davidson County, Tennessee were selected to collect soil samples to comprise a soil gradation profile for the Greater Nashville Area. This data, combined with a literature review of existing AI gradation tools, provided metrics to determine which existing AI tool may be most applicable to the Greater Nashville Area. Additionally, this study includes a comparative analysis between AI image analysis and standard sieve analysis for river- and stream-bank soil gradations, focusing on time and cost differences between the two methods. This analysis provides the basis for determining whether such AI tools should be applied professionally. Based on small particle size distribution from field testing, AI tools that classify fine gravel and sands would be of more use to the Greater Nashville Area. These AI tools, however, require high resolution microscopic imagery, which may be difficult to obtain in the field.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.