Anomaly detection; Groundwater; LSTM-Autoencoder; Monte Carlo; Negative Log Likelihood; SEAWAT; Uncertainty; Auto encoders; Groundwater monitoring; Log likelihood; Long short-term memory-autoencoder; Monte carlo; Negative log likelihood; Neural-networks; Environmental Monitoring; Monte Carlo Method; Neural Networks, Computer; Salinity; Environmental Science (all); Pollution; Management, Monitoring, Policy and Law
Résumé :
[en] Groundwater monitoring data can be prone to errors and biases due to various factors like borehole and equipment malfunctions, or human mistakes. These inaccuracies can jeopardize the groundwater system, leading to reduced efficiency and potentially causing partial or complete failures in the monitoring system. Traditional anomaly detection methods, which rely on statistical and time-variant techniques, struggle to handle the complex and dynamic nature of anomalies. With advancements in artificial intelligence and the growing need for effective anomaly detection and prevention across different sectors, artificial neural network methods are emerging as capable of identifying more intricate anomalies by considering both temporal and contextual aspects. Nonetheless, there is still a shortage of comprehensive studies on groundwater anomaly detection. The intricate patterns of sequential data from groundwater present numerous challenges, necessitating sophisticated modeling techniques that combine mathematics, statistics, and machine learning for viable solutions. This paper introduces a model designed for high accuracy and efficient computation in detecting anomalies in groundwater monitoring data through a probabilistic approach. We employed the Monte Carlo method and SEAWAT numerical simulation to ascertain the uncertainty in groundwater salinity. Subsequently, a Long Short-Term Memory (LSTM)-Autoencoder model was trained and evaluated, forming the basis of an anomaly detection framework. Each piece of training data was assessed by the LSTM-Autoencoder using the Negative Log Likelihood (NLL) score and a predefined threshold to determine the data’s abnormality percentage. The accuracy evaluation of the proposed LSTM-Autoencoder algorithm revealed that this approach achieved commendable performance, with an accuracy of 98.47% in anomaly detection. Graphical Abstract: (Figure presented.)
RAJABI, Mohammadmahdi ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE) ; Civil and Environmental Engineering Faculty, Tarbiat Modares University, Tehran, Iran
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Anomaly detection in groundwater monitoring data using LSTM-Autoencoder neural networks
Date de publication/diffusion :
août 2024
Titre du périodique :
Environmental Monitoring and Assessment
ISSN :
0167-6369
eISSN :
1573-2959
Maison d'édition :
Springer Science and Business Media Deutschland GmbH
Aggarwal, C. C., & Aggarwal, C. C. (2017). An introduction to outlier analysis (pp. 1–34). Springer International Publishing.
S. Alla S.K. Adari Beginning anomaly detection using python-based deep learning 2019 Apress
V. Amiri M. Nakhaei R. Lak P. Li An integrated statistical-graphical approach for the appraisal of the natural background levels of some major ions and potentially toxic elements in the groundwater of Urmia aquifer, Iran Environmental Earth Sciences 2021 80 12 432 1:CAS:528:DC%2BB3MXhvVOltbfN
Anh, D. T., Pandey, M., Mishra, V. N., Singh, K. K., Ahmadi, K., Janizadeh, S.,.. & Dang, N. M. (2023). Assessment of groundwater potential modeling using support vector machine optimization based on Bayesian multi-objective hyperparameter algorithm. Applied Soft Computing, 132, 109848.
J. Audibert P. Michiardi F. Guyard S. Marti M.A. Zuluaga Do deep neural networks contribute to multivariate time series anomaly detection? Pattern Recognition 2022 132 108945
S. Azimi M. Azhdary Moghaddam S.A. Hashemi Monfared Anomaly detection and reliability analysis of groundwater by crude Monte Carlo and importance sampling approaches Water Resources Management 2018 32 4447 4467
W. Bakx P.J. Doornenbal R.J. Van Weesep V.F. Bense G.H. Oude Essink M.F. Bierkens Determining the relation between groundwater flow velocities and measured temperature differences using active heating-distributed temperature sensing Water 2019 11 8 1619
Balasubaramanian, S., Cyriac, R., Roshan, S., Paramasivam, K. M., & Jose, B. C. (2023). An effective stacked autoencoder based depth separable convolutional neural network model for face mask detection. Array, 19, 100294.
Bengio, Y. (2012). Deep learning of representations for unsupervised and transfer learning. In Proceedings of ICML workshop on unsupervised and transfer learning (vol. 27, pp. 17–36).
A. Blázquez-García A. Conde U. Mori J.A. Lozano A review on outlier/anomaly detection in time series data ACM Computing Surveys (CSUR) 2021 54 3 1 33
Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv:1901.03407.
V. Chandola A. Banerjee V. Kumar Anomaly detection: a survey ACM Computing Surveys (CSUR) 2009 41 3 1 58
A.A. Cook G. Mısırlı Z. Fan Anomaly detection for IoT time-series data: a survey IEEE Internet of Things Journal 2019 7 7 6481 6494
DeCastro-García, N., Castañeda, Á. L. M., & Fernández-Rodríguez, M. (2020, November). RADSSo: An automated tool for the multi-CASH machine learning problem. In International Conference on Hybrid Artificial Intelligence Systems (pp. 183–194). Cham: Springer International Publishing.
D.P. Duarte R.N. Nogueira L.B. Bilro Semi-supervised Gaussian and t-distribution hybrid mixture model for water leak detection Measurement Science and Technology 2019 30 12 125109 1:CAS:528:DC%2BB3cXjtFKgu7w%3D
Farahani, M. (2021). Anomaly detection on gas turbine time-series’ data using deep LSTM-autoencoder. Master’s thesis, Umeå University.
X. Feng J. Zhong R. Yan Z. Zhou L. Tian J. Zhao Z. Yuan Groundwater radon precursor anomalies identification by EMD-LSTM model Water 2022 14 1 69 1:CAS:528:DC%2BB38Xms1Sksrs%3D
T. Finke M. Krämer A. Morandini A. Mück I. Oleksiyuk Autoencoders for unsupervised anomaly detection in high energy physics Journal of High Energy Physics 2021 2021 6 1 32
R. Ghasemlounia A. Gharehbaghi F. Ahmadi H. Saadatnejadgharahassanlou Developing a novel framework for forecasting groundwater level fluctuations using bi-directional long short-term memory (BiLSTM) deep neural network Computers and Electronics in Agriculture 2021 191 106568
Goularas, D., & Kamis, S. (2019). Evaluation of deep learning techniques in sentiment analysis from Twitter data. In 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML) (pp. 12–17). IEEE.
K. Greff R.K. Srivastava J. Koutník B.R. Steunebrink J. Schmidhuber LSTM: A search space odyssey IEEE Transactions on Neural Networks and Learning Systems 2016 28 10 2222 2232
Gu, J. (2016). Mathematical modeling of groundwater anomaly detection. Master’s thesis, Colorado State University.
Hill, D. J., Minsker, B. S., & Amir, E. (2009). Real‐time Bayesian anomaly detection in streaming environmental data. Water Resources Research, 45, W00D28.
S. Hochreiter J. Schmidhuber Long short-term memory Neural Computation 1997 9 8 1735 1780 1:STN:280:DyaK1c%2FhvVahsQ%3D%3D
J. Jeong E. Park W.S. Han K. Kim S. Choung I.M. Chung Identifying outliers of non-Gaussian groundwater state data based on ensemble estimation for long-term trends Journal of Hydrology 2017 548 135 144
J. Jeong E. Park H. Chen K.Y. Kim W.S. Han H. Suk Estimation of groundwater level based on the robust training of recurrent neural networks using corrupted data Journal of Hydrology 2020 582 124512
J. Kang C.S. Kim J.W. Kang J. Gwak Anomaly detection of the brake operating unit on metro vehicles using a one-class LSTM autoencoder Applied Sciences 2021 11 19 9290 1:CAS:528:DC%2BB3MXit1Kjt7jN
T. Keesari K.L. Ramakumar S. Chidambaram S. Pethperumal R. Thilagavathi Understanding the hydrochemical behavior of groundwater and its suitability for drinking and agricultural purposes in Pondicherry area, South India–A step towards sustainable development Groundwater for Sustainable Development 2016 2 143 153
Kim, Y., Jeong, J., Park, H., Kwon, M., Cho, C., & Jeong, J. (2022). Development of a data-driven ensemble regressor and its applicability for identifying contextual and collective outliers in groundwater level time-series data. Journal of Hydrology,612, 128127.
Kim, D., Lindquist, W. B., & Peters, C. A. (2011). Upscaling geochemical reaction rates accompanying acidic CO2‐saturated brine flow in sandstone aquifers. Water Resources Research, 47, W01505.
Langevin, C. D., Thorne Jr, D. T., Dausman, A. M., Sukop, M. C., & Guo, W. (2008). SEAWAT version 4: a computer program for simulation of multi-species solute and heat transport. US Geological Survey Techniques and Methods Book 6, Ch A22.
H. Li J.H. Son A. Hanif J. Gu A. Dhanasekar K. Carlson Colorado Water Watch: Real-time groundwater monitoring for possible contamination from oil and gas activities Journal of Water Resource and Protection 2017 9 13 1660
B. Lindemann B. Maschler N. Sahlab M. Weyrich A survey on anomaly detection for technical systems using LSTM networks Computers in Industry 2021 131 103498
X. Liu Z. Wang X. Zhang A review of the green tides in the Yellow Sea, China Marine Environmental Research 2016 119 189 196 1:CAS:528:DC%2BC28XhtVOgtbbF
J. Liu J. Gu H. Li K.H. Carlson Machine learning and transport simulations for groundwater anomaly detection Journal of Computational and Applied Mathematics 2020 380 112982
J. Liu P. Wang D. Jiang J. Nan W. Zhu An integrated data-driven framework for surface water quality anomaly detection and early warning Journal of Cleaner Production 2020 251 119145 1:CAS:528:DC%2BC1MXisVynsrbJ
S. Maleki S. Maleki N.R. Jennings Unsupervised anomaly detection with LSTM autoencoders using statistical data-filtering Applied Soft Computing 2021 108 107443
Maniyath, S. R., Pooja, G., Chandana, R., Namitha, K. S., & Lakshminarasamma, N. (2021, June). Groundwater anomaly detection using machine learning. In 2021 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C) (pp. 8–14). IEEE.
J. Mao H. Wang B.F. Spencer Jr Toward data anomaly detection for automated structural health monitoring: Exploiting generative adversarial nets and autoencoders Structural Health Monitoring 2021 20 4 1609 1626
Mikuni, V., & Nachman, B. (2023). High-dimensional and permutation invariant anomaly detection. Physics Review, D 106, 092009.
I. Mitiche T. McGrail P. Boreham A. Nesbitt G. Morison Data-driven anomaly detection in high-voltage transformer bushings with LSTM auto-encoder Sensors 2021 21 21 7426
A. Moradi Vartouni M. Teshnehlab S. Sedighian Kashi Leveraging deep neural networks for anomaly-based web application firewall IET Information Security 2019 13 4 352 361
A.E. Mulligan C. Langevin V.E. Post Tidal Boundary Conditions in SEAWAT Groundwater 2011 49 6 866 879 1:CAS:528:DC%2BC3MXhsVOrtLvK
Naddaf-Sh, S., Naddaf-Sh, M. M., Kashani, A. R., & Zargarzadeh, H. (2020, December). An efficient and scalable deep learning approach for road damage detection. In 2020 IEEE International Conference on Big Data (Big Data) (pp. 5602–5608). IEEE.
M. Nasiri H.K. Moghaddam M. Hamidi Development of multi-criteria decision making methods for reduction of seawater intrusion in coastal aquifers using SEAWAT code Journal of Contaminant Hydrology 2021 242 103848 1:CAS:528:DC%2BB3MXhsVGrurjI
A. Nayyar R. Singh A comprehensive review of simulation tools for wireless sensor networks (WSNs) Journal of Wireless Networking and Communications 2015 5 1 19 47
H.D. Nguyen K.P. Tran S. Thomassey M. Hamad Forecasting and anomaly detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management International Journal of Information Management 2021 57 102282
I.T. Nicholaus J.R. Park K. Jung J.S. Lee D.K. Kang Anomaly detection of water level using deep autoencoder Sensors 2021 21 19 6679
Oppus, C., Guico, M. L., Monje, J. C., Domingo, M. A. L. G. A., Ngo, G., Retirado, M. G., & Kwong, J. C. (2020, October). Remote and real-time sensor system for groundwater level and quality. In 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE) (pp. 152–155). IEEE.
A. Panjehfouladgaran M.M. Rajabi Contaminant source characterization in a coastal aquifer influenced by tidal forces and density-driven flow Journal of Hydrology 2022 610 127807 1:CAS:528:DC%2BB38XhsV2gtLvK
G. Papastergios A. Filippidis J.L. Fernandez-Turiel D. Gimeno C. Sikalidis Surface soil geochemistry for environmental assessment in Kavala area, northern Greece Water, Air, & Soil Pollution 2011 216 141 152 1:CAS:528:DC%2BC3MXhvVChsL0%3D
M.M. Rajabi P. Komeilian X. Wan R. Farmani Leak detection and localization in water distribution networks using conditional deep convolutional generative adversarial networks Water Research 2023 238 120012 1:CAS:528:DC%2BB3sXpsFGktrk%3D
C. Robinson L. Li D.A. Barry Effect of tidal forcing on a subterranean estuary Advances in Water Resources 2007 30 4 851 865
Russo, S., Besmer, M. D., Blumensaat, F., Bouffard, D., Disch, A., Hammes, F.,.. & Villez, K. (2021). The value of human data annotation for machine learning based anomaly detection in environmental systems. Water Research, 206, 117695.
A.U. Sahin A new parameter estimation procedure for pumping test analysis using a radial basis function collocation method Environmental Earth Sciences 2016 75 1 13
A.U. Şahin E. Çiftçi Cessation time approach incorporating parametric and non-parametric machine-learning algorithms for recovery test data Hydrological Sciences Journal 2023 68 11 1578 1590
A. Sgueglia A. Di Sorbo C.A. Visaggio G. Canfora A systematic literature review of IoT time series anomaly detection solutions Future Generation Computer Systems 2022 134 170 186
Shaukat, K., Alam, T. M., Luo, S., Shabbir, S., Hameed, I. A., Li, J.,.. & Javed, U. (2021). A review of time-series anomaly detection techniques: A step to future perspectives. In Advances in information and communication: Proceedings of the 2021 Future of Information and Communication Conference (FICC), Volume 1 (pp. 865–877). Springer International Publishing.
M. Sherif A. Kacimov A. Javadi A.A. Ebraheem Modeling groundwater flow and seawater intrusion in the coastal aquifer of Wadi Ham, UAE Water Resources Management 2012 26 751 774
Z. Song C. Lu Y. Zhang J. Chen W. Liu B. Liu L. Shu Spatiotemporal distribution and statistical analysis of abnormal groundwater level rising in Poyang Lake basin Water 2022 14 12 1906
H.M. Tornyeviadzi H. Mohammed R. Seidu Semi-supervised anomaly detection methods for leakage identification in water distribution networks: a comparative study Machine Learning with Applications 2023 14 100501
S. Veena K. Mahesh M. Rajesh S. Salmon The survey on smart agriculture using IOT International Journal of Innovative Research in Engineering (IJRIREM) 2018 5 2 63 66
Y. Wei J. Jang-Jaccard W. Xu F. Sabrina S. Camtepe M. Boulic LSTM-autoencoder-based anomaly detection for indoor air quality time-series data IEEE Sensors Journal 2023 23 4 3787 3800
G. Xintong W. Hongzhi Y. Song G. Hong Brief survey of crowdsourcing for data mining Expert Systems with Applications 2014 41 17 7987 7994
Zaib Jadoon, K., Zeeshan Ali, M., Yousafzai, H. U. K., Rehman, K. U., Shah, J. A., & Shiekh, N. A. (2023, May). Smart groundwater monitoring system for managed aquifer recharge based on enabled real-time internet of things. In EGU General assembly conference abstracts (pp. EGU-12909).
