Advanced Spatio-Temporal Event Detection System for Groundwater Quality Based on Deep Learning

Divas Karimanzira^1, , Linda Ritzau¹, Tobias Martin² and Thilo Fischer²

¹Department of Surface water and Maritime Systems, Fraunhofer IOSB, Am Vogelherd 90, 98693, Ilmenau

²TZW: DVGW-Technologiezentrum Wasser, Wasserwerkstraße 2, 01326 Dresden

Cite this paper:
Divas Karimanzira, Linda Ritzau, Tobias Martin and Thilo Fischer. Advanced Spatio-Temporal Event Detection System for Groundwater Quality Based on Deep Learning. Applied Ecology and Environmental Sciences. 2023; 11(3):79-90. doi: 10.12691/aees-11-3-2

Abstract

It is very important in sensor networks for monitoring, e.g. groundwater quality, to detect sensor failures and anomalous spatio-temporal events such as spills and identify affected areas. Most of the method for anomaly detection do not truly utilize spatial and temporal information. In this paper a novel method based on deep learning (DL) is proposed which truly utilize multivariate spatio-temporal information in anomalous events detection. Anomalous events are quite rare, which makes it very challenging to obtain labeled anomaly datasets. It is therefore purposeful to use an unsupervised approach for sensor anomaly and event detection with labels only being used to set thresholds on prediction errors. Two method for an unsupervised anomaly detection in multivariate spatio-temporal data using deep learning are proposed in this paper. The first framework is composed of a Long Short Term Memory (LSTM) Encoder followed by an LSTM decoder and a LSTM predictor for temporal anomaly detection. In a further step, a Deep Neural Network (DNN) based classifier is used to classify the encoded and trained latent representation to their spatial corresponding to form a temporal and spatial anomaly detector. The second framework is based on a CNN encoder and a LSTM decoder to capture both spatial and temporal features. The encoder component can use either 3D convolutions or Multichannel CNN to capture complex spatial dependencies in each spatial neighborhood. The 3D tensor input for the encoder is formed by stacking the data from the nearest spatial neighbors of each data point. Both methods produce similar results for event detection, detecting different types of anomalies (point, context, etc.). After the training phase to learn the normal system behavior, both methods are capable of detecting anomalies that have never been seen before with a very good accuracy (values ranging between 88% and 96%). To validate the accuracy and efficiency of the DL-based methods, they were compared to a modified ST-DBSCAN algorithm. The results show the superiority of the DL-based methods.

Keywords:
Groundwater Nitrate Prediction Anomaly detection Deep learning Auto encoder Spatial and temporal anomalies

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References:

[1]	Lanzolla A, Spadavecchia M. Wireless Sensor Networks for Environmental Monitoring. Sensors. 2021; 21(4): 1172.
[2]	Yu, G., Wang, J., Liu, L. The analysis of groundwater nitrate pollution and health risk assessment in rural areas of Yantai, China. BMC Public Health 20, 437 (2020).
[3]	Kenneth, O (2020), Real-Time Anomaly Detection for Multivariate Data Stream}, https://kenluck2001.github.io/blog_post/realtime_anomaly_detection_for_multivariate_data_stream.
[4]	Mensi, Antonella & Franzoni, Alessio & Tax, David & Bicego, Manuele. (2021). An Alternative Exploitation of Isolation Forests for Outlier Detection. Structural, Syntactic, and Statistical Pattern Recognition, pp.34-44, 10.1007/978-3-030-73973-7_4.
[5]	Xiaojie, li & Lv, Jian & Cheng, Dongdong. (2015). Angle-Based Outlier Detection Algorithm with More Stable Relationships. Proceedings of the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems, Volume 1 pp.433-446.
[6]	Borghesi, Andrea & Bartolini, Andrea & Lombardi, Michele & Milano, Michela & Benini, Luca. (2019). Anomaly Detection Using Autoencoders in High Performance Computing Systems. Proceedings of the AAAI Conference on Artificial Intelligence. 33. 9428-9433. 10.1609/aaai.v33i01.33019428.
[7]	Qian, S. Ying and B. Wang, "Anomaly Detection in Distributed Systems via Variational Autoencoders," 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020, pp. 2822-2829.
[8]	A. Munawar, P. Vinayavekhin and G. De Magistris, "Spatio-temporal anomaly detection for industrial robots through prediction in unsupervised feature space", Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV), pp. 1017-1025, Mar. 2017.
[9]	Kong J., Kowalczyk W., Menzel S., Bäck T. (2020) Improving Imbalanced Classification by Anomaly Detection. In: Bäck T. et al. (eds) Parallel Problem Solving from Nature – PPSN XVI. PPSN 2020. Lecture Notes in Computer Science, vol 12269. Springer, Cham.
[10]	Birant, D. and Kut, A. (2007). St-dbscan: An algorithm for clustering spatial–temporal data. Data & Knowledge Engineering, 60(1):208 – 221. Intelligent Data Mining.
[11]	Cheng, T.; Li, Z. A Multiscale Approach for Spatio-temporal Outlier Detection. Trans. GIS. 2006, 10, 253–263.
[12]	Aggarwal, C.C. Spatial Outlier Detection. In Outlier Analysis, 2nd ed.; Springer Nature: New York, NY, USA, 2017; pp. 345–367.
[13]	Malhotra, P.; Ramakrishnan, A.; Anand, G.; Vig, L.; Agarwal, P.; Shro_, G. LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection. ICML 2016, Anomaly DetectionWorkshop. arXiv 2016, arXiv:1607.00148v2.
[14]	H. Yang, B. Wang, S. Lin, D. Wipf, M. Guo and B. Guo, "Unsupervised extraction of video highlights via robust recurrent auto-encoders", Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 4633-4641, Dec. 2015.
[15]	Estiri and Murphy, Y. S. Chong and Y. H. Tay, "Abnormal event detection in videos using spatiotemporal autoencoder", Proc. Int. Symp. Neural Netw., pp. 189-196, 2017.
[16]	M. Munir, S. A. Siddiqui, A. Dengel and S. Ahmed, "DeepAnT: A deep learning approach for unsupervised anomaly detection in time series", IEEE Access, vol. 7, pp. 1991-2005, 2019.
[17]	Nogas,J. S. S. Khan and A. Mihailidis, "DeepFall: Non-invasive fall detection with deep spatio-temporal convolutional autoencoders", J. Healthcare Inform. Res., vol. 4, pp. 50-70, Mar. 2020.
[18]	Y. Karadayi, M. N. Aydin and A. S. Öǧrencí, "Unsupervised Anomaly Detection in Multivariate Spatio-Temporal Data Using Deep Learning: Early Detection of COVID-19 Outbreak in Italy," in IEEE Access, vol. 8, pp. 164155-164177, 2020.
[19]	Chong and Tay, 2017.
[20]	Pang, G., Shen, C., Cao, L. & Hengel, A. V. D. Deep learning for anomaly detection: A review. ACM Comput. Surveys (CSUR) 54, 1–38 (2021).
[21]	H. Estiri and S. N. Murphy, "Semi-supervised encoding for outlier detection in clinical observation data", Comput. Methods Programs Biomed., vol. 181, Nov. 2019.
[22]	Lv, Hui & Cui, Zhen & Wang, Biao & Yang, Jian. (2022). Spatio-Temporal Relation Learning for Video Anomaly Detection. arXiv:2209.13116 [cs.CV].
[23]	Liu T, Zhang C, Niu X, Wang L (2022) Spatio-temporal prediction and reconstruction network for video anomaly detection. PLoS ONE 17(5): e0265564.
[24]	Tian, Z., Zhuo, M., Liu, L. et al. Anomaly detection using spatial and temporal information in multivariate time series. Sci Rep 13, 4400 (2023).
[25]	P. V. Ingole and M. K. Nichat, "Landmark based shortest path detection by using Dijkestra algorithm and Haversine formula", Int. J. Eng. Res. Appl., vol. 3, no. 3, pp. 162-165, 2013.
[26]	Li, Hongfei; Calder, Catherine A.; Cressie, Noel (2007). "Beyond Moran's I: Testing for Spatial Dependence Based on the Spatial Autoregressive Model". Geographical Analysis. 39 (4): 357–375.
[27]	D. D’Avino, D. Cozzolino, G. Poggi and L. Verdoliva, "Auto encoder with recurrent neural networks for video forgery detection", Proc. IS&T Int. Symp. Electron. Imag. Media Watermarking Secur. Forensics, pp. 92-99, 2017.
[28]	P. Perera and V. M. Patel, "Learning deep features for one-class classification", IEEE Trans. Image Process., vol. 28, no. 11, pp. 5450-5463, Nov. 2019.
[29]	M. Gupta, J. Gao, C. C. Aggarwal and J. Han, "Outlier Detection for Temporal Data: A Survey", IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 9, pp. 2250-2267, Sept. 2014.
[30]	Srivastava, N., Mansimov, E., and Salakhutdinov, R. (2015): Unsupervised learning of video rep-resentations using lstms. International Conference on Machine Learning (ICML), 2015.
[31]	Ester, M., H. P. Kriegel, J. Sander, and X. Xu, "A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise". In: Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland, OR, AAAI Press, pp. 226-231. 1996.
[32]	Fernando Nogueira (2014), Bayesian Optimization: Open source constrained global optimization tool for Python, 2014, url = " https://github.com/fmfn/BayesianOptimization".
[33]	Nadia Rahmah and Imas Sukaesih Sitanggang (2016), Determination of Optimal Epsilon (Eps) Value on DBSCAN Algorithm to Clustering Data on Peatland Hotspots in Sumatra IOP Conf. Ser.: Earth and Environmental. Science. 31 012012.