Multi-task Temporal Convolutional Network for Predicting Water Quality Sensor Data
- 1.1k Downloads
Abstract
Predicting the trend of water quality is essential in environmental management decision support systems. Despite various data-driven models in water quality prediction, most studies focus on predicting a single water quality variable. When multiple water quality variables need to be estimated, preparing several data-driven models may require unaffordable computing resources. Also, the changing patterns of several water quality variables can only be revealed by processing long term historical observations, which is not well supported by conventional data-driven models. In this paper, we propose a multi-task temporal convolution network (MTCN) for predicting multiple water quality variables. The temporal convolution offers one the capability to explore the temporal dependencies among a remarkably long historical period. Furthermore, instead of providing predictions for only one water quality variable, the MTCN is designed to predict multiple water quality variables simultaneously. Data collected from the Burnett River, Queensland is used to evaluate the MTCN. Compared to training a set of single-task TCNs for each variable separately, the proposed MTCN achieves the best RMSE scores in predicting both temperature and DO in the following 48 time steps but only requires 53% of the total training time of the TCN. Therefore, the MTCN is an encouraging approach for water quality management by processing a large amount of sensor data.
Keywords
Prediction model Multi-task learning Water qualityNotes
Acknowledgement
This work was conducted within the CSIRO Digiscape Future Science Platform.
References
- 1.Ambient estuarine water quality monitoring data. https://data.qld.gov.au/dataset. Accessed 20 Nov 2017
- 2.Alizadeh, M.J., Kavianpour, M.R.: Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific ocean. Mar. Pollut. Bull. 98(1–2), 171–178 (2015)CrossRefGoogle Scholar
- 3.Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)
- 4.Huang, J.T., Li, J., Yu, D., Deng, L., Gong, Y.: Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7304–7308. IEEE (2013)Google Scholar
- 5.Ji, X., Shang, X., Dahlgren, R.A., Zhang, M.: Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China. Environ. Sci. Pollut. Res. 24(19), 16062–16076 (2017)CrossRefGoogle Scholar
- 6.Kim, S.E., Seo, I.W.: Artificial neural network ensemble modeling with conjunctive data clustering for water quality prediction in rivers. J. Hydro-Environ. Res. 9(3), 325–339 (2015)MathSciNetCrossRefGoogle Scholar
- 7.Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1003–1012. IEEE (2017)Google Scholar
- 8.Luong, M.T., Le, Q.V., Sutskever, I., Vinyals, O., Kaiser, L.: Multi-task sequence to sequence learning. arXiv preprint arXiv:1511.06114 (2015)
- 9.Manasrah, R., Raheed, M., Badran, M.I.: Relationships between watertemperature, nutrients and dissolved oxygen in the northern Gulf of Aqaba, Red Sea. Oceanologia 48(2), 237–253 (2006)Google Scholar
- 10.Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994–4003 (2016)Google Scholar
- 11.Moon, T., Ahn, T.I., Son, J.E.: Forecasting root-zone electrical conductivity of nutrient solutions in closed-loop soilless cultures via a recurrent neuralnetwork using environmental and cultivation information. Front. Plant Sci. 9, 859 (2018)CrossRefGoogle Scholar
- 12.Thorburn, P.J., et al.: Helping farmers mitigate nutrient losses to the great barrier reef through “digital agriculture”. Occasional report, Fertiliser and Lime Research Centre, Massey University, 32, 6 (2019)Google Scholar
- 13.Thorburn, P., Wilkinson, S.: Conceptual frameworks for estimating the water quality benefits of improved agricultural management practices in large catchments. Agric. Ecosyst. Environ. 180, 192–209 (2013)CrossRefGoogle Scholar
- 14.Van Den Oord, A., et al.: Wavenet: a generative model for raw audio. CoRR abs/1609.03499 (2016)Google Scholar
- 15.Wang, Y., Zhou, J., Chen, K., Wang, Y., Liu, L.: Water quality prediction method based on LSTM neural network. In: 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), pp. 1–5. IEEE (2017)Google Scholar
- 16.Zhang, Y., Fitch, P., Vilas, M.P., Thorburn, P.J.: Applying multi-layer artificial neural network and mutual information to the prediction of trends in dissolved oxygen. Front. Environ. Sci. 7, 46 (2019)CrossRefGoogle Scholar
- 17.Zhang, Y., Fitch, P., Vilas, M.P., Thorburn, P.J.: Predicting the trend of dissolved oxygen based on kPCA-RNN model in water quality monitoring. Water (2019, submitted)Google Scholar
- 18.Zhang, Y., Thorburn, P.J., Wei, X., Fitch, P.: SSIM - a deep learning approach for recovering missing time series sensor data. IEEE Internet Things J. 6(4), 6618–6628 (2019)CrossRefGoogle Scholar