Sakizadeh, M. (2020). Comparison of Time Series Forecasting Techniques Applied for Water Quality Prediction in Southwest Iran. , 8(4), 199-208.
M. Sakizadeh. "Comparison of Time Series Forecasting Techniques Applied for Water Quality Prediction in Southwest Iran". , 8, 4, 2020, 199-208.
Sakizadeh, M. (2020). 'Comparison of Time Series Forecasting Techniques Applied for Water Quality Prediction in Southwest Iran', , 8(4), pp. 199-208.
Sakizadeh, M. Comparison of Time Series Forecasting Techniques Applied for Water Quality Prediction in Southwest Iran. , 2020; 8(4): 199-208.

Comparison of Time Series Forecasting Techniques Applied for Water Quality Prediction in Southwest Iran

ECOPERSIA
Article 2, Volume 8, Issue 4 - Serial Number 34, 2020, Pages 199-208    PDF (622.64 K)
Document Type: Original Research
Author
M. Sakizadeh*
Environmental Sciences Department, Shahid Rajaee Teacher Training University, Tehran, Iran
Abstract
Aims: The main objective of the current study was to assess the efficiency of four-time series prediction methods to forecast the values of total dissolved solids (TDS) using a time series of over sixteen years.

Materials & Methods: The applied methods comprised of autoregressive integrated moving average (ARIMA) as the most traditional method, two neural network based techniques including multilayer perceptron (MLP) along with extreme learning machines (ELM) and a novel approach known as temporal hierarchies (TH) which was applied for the first time in water resources and water quality researches.

Findings: It was found that with respect to the forecasting accuracy, the MLP outperforms the ARIMA model for the training series where the MAPE (%) and MASE (mg/l) were reduced from 5.109 to 3.146 and 0.553 to 0.323, respectively. On the other hand, the forecasting accuracy of ELM was lower than that of MLP however the respective out-of-sample generalization ability of this model was higher with MAPE and MASE values of 6.526 and 0.683.

Conclusion: Meanwhile, it was concluded that temporal hierarchies gave the best results for the test part of time series. The main shortcoming of neural network based approaches was their reduced out-of-sample prediction due to overfitting. Based on the results, TH is a viable alternative for conventional time series forecasting techniques.
Keywords
ARIMA; Neural Network; Temporal Hierarchies; Time Series; Water Qualit
References
Statistics
Article View: 15,087
PDF Download: 23,026
Statistics
Number of Journals45
Number of Issues2,171
Number of Articles24,674
Article View24,436,537
PDF Download17,551,450