Characterization of components of water supply systems from GPR images and tools of intelligent data analysis.

Ayala-Cabrera, David

doi:10.4995/thesis/10251/59235

Cited by 2 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let us understand the GPR radargram (𝐴) as a set 𝐴𝑓 formed by the triple {𝑔, 𝑓𝑙, 𝑟} of groups (families) as in Ayala-Cabrera [10] . Where 𝑔 corresponds to the families of objects embedded into the images, 𝑓𝑙 to the medium and 𝑟 represents the noise.…”

Section: Methodsmentioning

confidence: 99%

GPR image interpretation advancement for smarter technical management of water leakage in urban water infrastructures

Ayala-Cabrera

Izquierdo

2021

Earth Resources and Environmental Remote Sensing/Gis Applications XII

View full text Add to dashboard Cite

This paper combines such powerful non-destructive technique as ground penetrating radar (GPR) with intelligent data analysis in order to acquire new knowledge on mapping/monitoring/verification systems aimed at initially facilitating the evaluation of the health of the buried assets of water distribution system (WDS) infrastructures in urban areas. Preprocessing techniques based on a multi-agent approach coupled with a suitable analysis of the properties of the obtained groups of objects found, as well as a classification supported by machine learning techniques, are presented in this work. The work is based on GPR image studies conducted under controlled laboratory conditions using a commercial antenna. The buried objects correspond to pipes of various materials commonly used in WDSs. Furthermore, GPR images of various pipes either empty or full of water, as well as leaking water, are also included in the dataset of the study. The dataset is divided into two subsets that pursue: 1) the development of the methodology; i.e. capturing objects in GPR images to favour the feature extraction process, and 2) the evaluation of the feasibility of implementation of the proposed classification, as well as the response of the methodology to various environmental interactions recorded in the images. The results of this work are promising in the sense of promoting the inclusion of powerful tools such as GPR towards the provision of smarter tools that adequately support technical management in WDSs, and, eventually, that of other surrounding infrastructure(s).

show abstract

Section: Methodsmentioning

confidence: 99%

GPR image interpretation advancement for smarter technical management of water leakage in urban water infrastructures

Ayala-Cabrera

Izquierdo

2021

Earth Resources and Environmental Remote Sensing/Gis Applications XII

View full text Add to dashboard Cite

show abstract

“…Labeling is an essential task in machine learning, in particular when the classification is conducted via supervised learning. This pre-preprocessing activity is conducted on various occasions manually as a preamble for the classification (via machine learning methods) of the embedded objects into the GPR images (e.g., subsoil background [20], metallic and no-metallic pipes [31], among others). In order to reduce the dependency on personnel with high experience in interpreting GPR images and minimize the human errors that the manual labeling can generate, the analysis of densities is proposed as an alternative in this paper.…”

Section: Semi-automatic Labeling and Refinementmentioning

confidence: 99%

“…A raw GPR image may be used to detect and characterize a variety of subsurface assets (e.g. pipes of drinking water [20], gas [21], among others), but it is not easily interpretable, particularly for unskilled personnel as mentioned above. Although the raw GPR images are difficult to interpret, they contain a wealth of data that can be processed to extract useful information [22].…”

Section: Introductionmentioning

confidence: 99%

Advancing towards semi-automatic labeling of GPR images to improve visualizations of pipes and leaks in water distribution networks using multi-agent systems and machine learning techniques

Stanton,

Ayala-Cabrera

2022

Proceedings - 2nd International Join Conference on Water Distribution System Analysis (WDSA)& Computing and Control in the

View full text Add to dashboard Cite

Critical infrastructures such as water distribution networks (WDNs) require reliable and affordable information at a reasonable cost to address challenges that can negatively affect their operation. Inadequate knowledge about WDN assets and their state of health presents challenges for essential activities such as network modeling, operation, assessment, and maintenance. This work seeks to increase the availability of WDN asset data through improved interpretability of GPR images. The semi-automatic labeling approach presented here expands upon existing multi-agent image-cleaning methods and feature characterization techniques. The division of a pre-processed image, in the form of a matrix, into a grid of smaller blocks allowed the identification of relevant features using density of nonzero values in the blocks; this approach, conducted manually in this proof of concept, can provide a basis for training an intelligent system (e.g., a convolutional neural network) to extract the families of interest and eliminate noise. Thus, this research expands this methodology to advance towards automatic detection of pipes and leaks and easily visualize the data. In this paper, 3D visualizations of WDN assets have been created to demonstrate the usefulness of this semi-automatic process in delivering easily-interpretable GPR data for managers and operators of WDNs.

show abstract

Characterization of components of water supply systems from GPR images and tools of intelligent data analysis.

Cited by 2 publications

References 58 publications

GPR image interpretation advancement for smarter technical management of water leakage in urban water infrastructures

GPR image interpretation advancement for smarter technical management of water leakage in urban water infrastructures

Advancing towards semi-automatic labeling of GPR images to improve visualizations of pipes and leaks in water distribution networks using multi-agent systems and machine learning techniques

Contact Info

Product

Resources

About