Research on Water Quality Prediction Based on SARIMA-LSTM: A Case Study of Beilun Estuary

As water environment is an important part of mangrove ecosystem, an efficient prediction of water quality is the foundation for judging the health of wetland ecosystem. And it also contributes a lot to the smooth development of environmental protection work. Based on the data of water quality and weather in Beilun Estuary, this paper chooses permanganate index and the content of ammonia nitrogen, which can reflect the water quality, as forecasting targets. We propose a multi-feature prediction method called SARIMA-LSTM on the basis of seasonal autoregressive integrated moving average model and long short-term memory. Through the combination of linear and non-linear model, this method can possess a better prediction effect considering the influence of weather on water quality. And the experimental results of four models show that this method has higher accuracy, stability and reliability.

[1]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[2]  Junli Wang,et al.  Assessment of eutrophication and water quality in the estuarine area of Lake Wuli, Lake Taihu, China. , 2019, The Science of the total environment.

[3]  W. Mitsch,et al.  Hurricane and seasonal effects on hydrology and water quality of a subtropical urban stormwater wetland , 2018, Ecological Engineering.

[4]  Peter Batista Cheung,et al.  Parameter Estimation of Seasonal Arima Models for Water Demand Forecasting Using the Harmony Search Algorithm , 2017 .

[5]  B. Pradhan,et al.  A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. , 2018, The Science of the total environment.

[6]  Andrés García,et al.  Artificial neural networks as emulators of process-based models to analyse bathing water quality in estuaries. , 2019, Water research.

[7]  C. Cao,et al.  An evaluating system for wetland ecological health: Case study on nineteen major wetlands in Beijing-Tianjin-Hebei region, China. , 2019, The Science of the total environment.

[8]  Nathan L. Howell,et al.  Water quality variation with storm runoff and evaporation in playa wetlands. , 2019, The Science of the total environment.

[9]  Paulo S. G. de Mattos Neto,et al.  An intelligent hybridization of ARIMA with machine learning models for time series forecasting , 2019, Knowl. Based Syst..

[10]  Qian Zhang,et al.  Does species richness affect the growth and water quality of submerged macrophyte assemblages? , 2019, Aquatic Botany.

[11]  K. Singh,et al.  Dependence of precipitation of trace elements on pH in standard water , 2018 .

[12]  Daniel Rokitnicki-Wojcik,et al.  Characterizing daily water-level fluctuation intensity and water quality relationships with plant communities in Lake Ontario coastal wetlands , 2015 .

[13]  Zhenhong Du,et al.  Red tide time series forecasting by combining ARIMA and deep belief network , 2017, Knowl. Based Syst..

[14]  M. Russell,et al.  Contaminant profiles for surface water, sediment, flora and fauna associated with the mangrove fringe along middle and lower eastern Tampa Bay. , 2015, Marine pollution bulletin.

[15]  S. Edeki,et al.  Dataset on the assessment of water quality and water quality index of Ubogo and Egini rivers, Udu LGA, Delta State Nigeria , 2018, Data in brief.

[16]  Duo Zhang,et al.  Use Long Short-Term Memory to Enhance Internet of Things for Combined Sewer Overflow Monitoring , 2018 .

[17]  P. Arumugam,et al.  Outlier Detection and Missing Value in Seasonal ARIMA Model Using Rainfall Data , 2018 .

[18]  Wu Jing,et al.  Water Quality Prediction Model Combining Sparse Auto-encoder and LSTM Network , 2018 .

[19]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[20]  A. Gershunov,et al.  Atmospheric rivers impact California's coastal water quality via extreme precipitation. , 2019, The Science of the total environment.

[21]  Navdeep Jaitly,et al.  Hybrid speech recognition with Deep Bidirectional LSTM , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.