UNEP GEMS/Water Capacity Development Centre - Masters by Research Theses

Permanent URI for this collection


Recent Submissions

Now showing 1 - 2 of 2
  • Item
    Automated crack classification for underground tunnel infrastructure using deep learning
    (University College Cork, 2021-11-01) O'Brien, Darragh; Li, Zili; Osborne, John; Irish Centre for Applied Geoscience; CERN
    One early sign of tunnel structure deterioration originates in the form of cracking, and therefore crack detection and resultant classification is integral for tunnel structural inspection and maintenance. Conventionally tunnel cracks are manually recorded and classified by trained professionals, which is costly, time-consuming and inevitably subjective. Recent advances in the deep learning space have allowed for automatic cracks detection algorithms to be developed and subsequently utilized in surface structural health assessment of surface buildings, bridges, roads and other civil infrastructure. Nevertheless, these methods of development underperform when implemented for a tunnel structure in an underground environment due to the disparity of illumination combined with the congested image data caused by pipes, steel mesh, wires, and other tunnel amenities. This thesis develops an intuitive crack directional classification approach that increases the accuracy, reduces time and subjectivity in comparison to traditional inspection methods. The detection of cracks by utilising CNN’s is antiquity investigated by in literature however little of the writings develop the algorithm further for classification purposes. The novel of this research is centred on the development of a crack classification algorithm that adheres to the directional classification rationale. The output information of the crack classification is correlated to the structural movement of the lining providing a deeper understanding of the tunnel behaviors. To surmount these challenges, this thesis constructs a Convolution Neural Network (CNN) image-based crack detection method accompanied by an innovative crack classification for underground infrastructure environment. Conventional CNN’s are developed from scratch, the proposed CNN incorporates transfer learning in the form of the VGG16 model with weights transferred from ImageNet. The transfer model was trained under various scenarios to determine the optimal model for the operational task in the tunnel environment. The various models are trained using over 10’000 images validated on 2’500 images all of which are 256 x 256 pixels in size, these models are all subsequently tested using 30 images 3072 x 4096 pixels in size. The transfer learning model used outperforms that of the traditional CNN training method of training from scratch. The optimum transfer model accomplished testing metrics of 96.6%,87.3%,92.4%,89.3% for Accuracy, Precision, Recall and F1 score respectively. The proposed CNN appraises images regarding the existence and subsequent location of cracks. Detected cracks are subjected to the secondary classification CNN where the crack is categorized into one of the four crack classes which include the three directional classes of Horizontal, vertical and diagonal with the last crack classes incorporated to represent complex crack regions. The secondary classification CNN attains an Accuracy of 92.3% a Precision of 83.9% a Recall value of 82.3 % and an F1 score of 81.5%. The performance of the manufactured integrated detection and classification method is analysed by performing a field test to evolve the research from a controlled theoretical setting into a realistic tunnel environment. The field test is performed on three separate tunnel sections with an amassed distance of 150 meters with the section testing the robustness, speed and ultimately prospect of application in the CERN inspection scenario. The outcome from this testing demonstrates that the established CNN crack detector/classifier can effectively overwhelm the unfavourable tunnel environment and accomplish results to a high standard.
  • Item
    In support of the sustainable development goals: citizen science monitoring of ambient water quality
    (University College Cork, 2019-10-04) Quinlivan, Lauren; Chapman, Deborah; Sullivan, Timothy
    The United Nations has voiced its support for the use of citizen science to aid ambient water quality monitoring for the Sustainable Development Goals. Engaging the efforts of both professional scientists and members of the general public, citizen science has gained significant attention in recent years as a means of increasing the spatial and temporal coverage of data collection. However little research has been conducted on the use of citizen science in water quality monitoring for the UN Sustainable Development Goals to allow for the establishment of any sort of monitoring framework involving citizen science. A literature review as part of this thesis discusses the current state of knowledge on volunteer involvement in water quality monitoring and identifies the challenges and opportunities for applying citizen science to the monitoring of ambient water quality under the Sustainable Development Goals. Considerable potential exists for citizen science to contribute to the SDGs yet concerns over data collection, use and organisational issues like lack of volunteer motivation and interest continue to plague the realm of volunteer monitoring and inhibit its use in many fields. Based on the conclusions drawn from the literature, this thesis aimed to address each key issue which currently presents a challenge for the application of citizen science to the monitoring of ambient water quality for the Sustainable Development Goals. In support of work towards the achievement of Sustainable Development Goal 6: “Clean Water and Sanitation”, this thesis tested the use of simple and inexpensive field equipment by citizen scientists for monitoring the SDG Indicator 6.3.2: “Proportion of bodies of water with good ambient water quality”. Data generated by 26 citizen scientists were compared with the results produced by an accredited laboratory. The results compared well for most parameters, suggesting that citizen science may be able to contribute towards monitoring ambient water quality for the Sustainable Development Goals as long as data quality is maintained. This thesis also examined the effects of participation in an SDG-focused citizen science water quality monitoring programme on volunteers’ attitudes and interests. The positive results support conclusions from other studies suggesting that experience of partaking in citizen science may increase volunteer interest and positively influence attitudes towards global environmental issues, though the resulting influence on behaviour will require further investigation. Lastly, through a focus on waterbodies of known water quality in southwest Ireland, this thesis aimed to assess one potential method for incorporating citizen science data into the reporting methodology for the ambient water quality indicator. The investigation reported mixed results, revealing that the incorporation of citizen science data into the reporting methodology through the method employed would be relatively simple, however more recent data is needed from professional organisations on the quality of the waterbodies examined before the accuracy of the data may be determined. Through an examination of the three most significant barriers to the application of citizen science to the UN ambient water quality indicator this body of research concludes that, if implemented correctly, citizen science may prove an essential resource for supporting the achievement of the Sustainable Development Goal Indicator 6.3.2 on ambient water quality.