Optimizing Laboratory Investigations of Saline Intrusion by Incorporating Machine Learning Techniques

被引:10
|
作者
Etsias, Georgios [1 ]
Hamill, Gerard A. [1 ]
Benner, Eric M. [1 ]
Aguila, Jesus F. [1 ]
McDonnell, Mark C. [1 ]
Flynn, Raymond [1 ]
Ahmed, Ashraf A. [2 ]
机构
[1] Queens Univ Belfast, Sch Nat & Built Environm, Belfast BT9 5AG, Antrim, North Ireland
[2] Brunel Univ, Coll Engn Design & Phys Sci, London UB8 3PH, England
基金
英国工程与自然科学研究理事会;
关键词
saltwater intrusion; sandbox; artificial neural networks; image analysis; classification; regression; FRESH-WATER LENSES; AUTOMATED IMAGE-ANALYSIS; VARIABLE-DENSITY FLOW; SALTWATER INTRUSION; SEAWATER INTRUSION; COASTAL AQUIFERS; CONTAMINANT TRANSPORT; AGE-STRATIFICATION; REACTIVE TRANSPORT; GROUNDWATER-FLOW;
D O I
10.3390/w12112996
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Deriving saltwater concentrations from the light intensity values of dyed saline solutions is a long-established image processing practice in laboratory scale investigations of saline intrusion. The current paper presents a novel methodology that employs the predictive ability of machine learning algorithms in order to determine saltwater concentration fields. The proposed approach consists of three distinct parts, image pre-processing, porous medium classification (glass bead structure recognition) and saltwater field generation (regression). It minimizes the need for aquifer-specific calibrations, significantly shortening the experimental procedure by up to 50% of the time required. A series of typical saline intrusion experiments were conducted in homogeneous and heterogeneous aquifers, consisting of glass beads of varying sizes, to recreate the necessary laboratory data. An innovative method of distinguishing and filtering out the common experimental error introduced by both backlighting and the optical irregularities of the glass bead medium was formulated. This enabled the acquisition of quality predictions by classical, easy-to-use machine learning techniques, such as feedforward Artificial Neural Networks, using a limited amount of training data, proving the applicability of the procedure. The new process was benchmarked against a traditional regression algorithm. A series of variables were utilized to quantify the variance between the results generated by the two procedures. No compromise was found to the quality of the derived concentration fields and it was established that the proposed image processing technique is robust when applied to homogeneous and heterogeneous domains alike, outperforming the classical approach in all test cases. Moreover, the method minimized the impact of experimental errors introduced by small movements of the camera and the presence air bubbles trapped in the porous medium.
引用
收藏
页码:1 / 21
页数:21
相关论文
共 50 条
  • [31] Incorporating Active Learning into Machine Learning Techniques for Sensory Evaluation of Food
    Nhat-Vinh Lu
    Roengchai Tansuchat
    Takaya Yuizono
    Van-Nam Huynh
    International Journal of Computational Intelligence Systems, 2020, 13 : 655 - 662
  • [32] Incorporating Active Learning into Machine Learning Techniques for Sensory Evaluation of Food
    Nhat-Vinh Lu
    Tansuchat, Roengchai
    Yuizono, Takaya
    Van-Nam Huynh
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2020, 13 (01) : 655 - 662
  • [33] Optimizing intrusion detection using intelligent feature selection with machine learning model
    Aljehane, Nojood O.
    Mengash, Hanan A.
    Hassine, Siwar B. H.
    Alotaibi, Faiz A.
    Salama, Ahmed S.
    Abdelbagi, Sitelbanat
    ALEXANDRIA ENGINEERING JOURNAL, 2024, 91 : 39 - 49
  • [34] Review of Machine Learning Techniques for Optimizing Energy of Home Appliances
    Kaur, Jasmeet
    Bala, Anju
    INFORMATION AND COMMUNICATION TECHNOLOGY FOR COMPETITIVE STRATEGIES, 2019, 40 : 255 - 263
  • [35] Optimizing classification efficiency with machine learning techniques for pattern matching
    Belal A. Hamed
    Osman Ali Sadek Ibrahim
    Tarek Abd El-Hafeez
    Journal of Big Data, 10
  • [36] Optimizing Solar Panel Tilt Using Machine Learning Techniques
    Kulkarni, Sakshi
    Duraphe, Kshitij
    Chandwani, Laveen
    Jaiswal, Sakshi
    Kakade, Suhas
    Kulkarni, Rohan
    2021 IEEE 3RD GLOBAL POWER, ENERGY AND COMMUNICATION CONFERENCE (IEEE GPECOM2021), 2021, : 190 - 195
  • [37] A Detailed Investigation and Analysis of Using Machine Learning Techniques for Intrusion Detection
    Mishra, Preeti
    Varadharajan, Vijay
    Tupakula, Uday
    Pilli, Emmanuel S.
    IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2019, 21 (01): : 686 - 728
  • [38] Optimizing classification efficiency with machine learning techniques for pattern matching
    Hamed, Belal A.
    Ibrahim, Osman Ali Sadek
    Abd El-Hafeez, Tarek
    JOURNAL OF BIG DATA, 2023, 10 (01)
  • [39] Intrusion Detection in Computer Networks Using Combination of Machine Learning Techniques
    Mazraeh, Saeed
    Modhej, Adel
    Neysi, Sajedeh Hasan Nejad
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2016, 16 (08): : 122 - 126
  • [40] Web Attack Intrusion Detection System Using Machine Learning Techniques
    Baklizi, Mahmoud Khalid
    Atoum, Issa
    Alkhazaleh, Mohammad
    Kanaker, Hasan
    Abdullah, Nibras
    Al-Wesabi, Ola A.
    Otoom, Ahmed Ali
    INTERNATIONAL JOURNAL OF ONLINE AND BIOMEDICAL ENGINEERING, 2024, 20 (03) : 24 - 38