A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runoff prediction

Zhang, Xianqi; Wu, Xilong; Zhu, Guoyu; Lu, Xiaobin; Wang, Kai

doi:10.2166/ws.2022.263

Cited by 10 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, energy-related time series such as solar radiation and wind speed typically manifest seasonality and trends. To address these non-stationary characteristics, the Seasonal ARIMA (SARIMA) model has been employed, with Xianqi Z. demonstrating its high accuracy in predicting thermal energy requirements for district heating systems [36]. The SARIMA-RVFL (Random Vector Functional Link) model, designed for short-term solar photovoltaic generation predictions, and Wang H. et al 's application of the SARIMA model for monthly wind velocity forecasting have both shown improved accuracy over traditional ARIMA-based approaches [37].…”

Section: Traditional Methodsmentioning

confidence: 99%

Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns

Han,

Neira-Molina,

Khan

et al. 2024

J Cloud Comp

View full text Add to dashboard Cite

In this study, we present the EEG-GCN, a novel hybrid model for the prediction of time series data, adept at addressing the inherent challenges posed by the data's complex, non-linear, and periodic nature, as well as the noise that frequently accompanies it. This model synergizes signal decomposition techniques with a graph convolutional neural network (GCN) for enhanced analytical precision. The EEG-GCN approaches time series data as a one-dimensional temporal signal, applying a dual-layered signal decomposition using both Ensemble Empirical Mode Decomposition (EEMD) and GRU. This two-pronged decomposition process effectively eliminates noise interference and distills the complex signal into more tractable sub-signals. These sub-signals facilitate a more straightforward feature analysis and learning process. To capitalize on the decomposed data, a graph convolutional neural network (GCN) is employed to discern the intricate feature interplay within the sub-signals and to map the interdependencies among the data points. The predictive model then synthesizes the weighted outputs of the GCN to yield the final forecast. A key component of our approach is the integration of a Gated Recurrent Unit (GRU) with EEMD within the GCN framework, referred to as EEMD-GRU-GCN. This combination leverages the strengths of GRU in capturing temporal dependencies and the EEMD's capability in handling non-stationary data, thereby enriching the feature set available for the GCN and enhancing the overall predictive accuracy and stability of the model. Empirical evaluations demonstrate that the EEG-GCN model achieves superior performance metrics. Compared to the baseline GCN model, EEG-GCN shows an average R2 improvement of 60% to 90%, outperforming the other methods. These results substantiate the advanced predictive capability of our proposed model, underscoring its potential for robust and accurate time series forecasting.

show abstract

Section: Traditional Methodsmentioning

confidence: 99%

Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns

Han,

Neira-Molina,

Khan

et al. 2024

J Cloud Comp

View full text Add to dashboard Cite

show abstract

“…The ability of the SARIMA model to handle a larger range of data and accurately determined seasonality, as claimed by Shahriar et al ( 2021), was confirmed. The use of historical data, as in the study by Zhang et al (2022), contributed to the careful analysis of the time series and the identification of potential fluctuations that may occur when modelling future estimates. Similar findings were also confirmed in the study by Liu et al (2022), which focused on maintenance and safety.…”

Section: Discussionmentioning

confidence: 99%

Changes in real income of households in the Czech Republic due to the Russian invasion of Ukraine

Vochozka,

Škapa,

Apanovych

2023

JESI

View full text Add to dashboard Cite

The objective of the paper was to assess the impact of the invasion of Ukraine by the Russian Federation on real household income in the Czech Republic. The research methods used in the study include content analysis, seasonal modification of SARIMA, and discounting method, specifically NPV. Data were collected from publicly available sources of the Czech Statistical Office. Based on a content analysis of the macroeconomic indicators under study, inflation and gross monthly household income were selected to examine further development of real household income in the Czech Republic. Based on historical data, the SARIMA model made statistically relevant forecasts of the selected variables for the "pre-war" year 2022. Comparing real and forecast data, it was confirmed that the Russian invasion of Ukraine (from 24 th February 2022 onwards) has shown how vulnerable the European financial system is to external shocks, which can be observed in significant inflationary changes. The ability of the SARIMA model to handle a larger range of data and accurately determined seasonality was demonstrated in forecasting the development of real household income. The identified economic consequences of deviations of the real and forecast figures in the "pre-war" period showed new realities in turbulent economic conditions. In order to further expand the research, combining the applied method with other analytical tools can be recommended. Moreover, it is advisable to include new relevant variables in the model. This would allow understanding better and forecasting the development of real household income in the context of current economic events.

show abstract

“…Recently, various intelligent optimization algorithms (Adnan et al., 2021; Yuan et al., 2018; X. Zhang et al., 2022) and signal processing techniques, such as ensemble empirical mode decomposition (EEMD) (W. C. Wang et al., 2015), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) (Feng et al., 2022) and variational mode decomposition (VMD) (B. J. Li, Sun, Li, et al., 2022; B. J. Li, Sun, Liu, et al., 2022; Wu et al., 2023) is introduced to runoff prediction. For example, Y. Xu et al.…”

Section: Introductionmentioning

confidence: 99%

Robust Runoff Prediction With Explainable Artificial Intelligence and Meteorological Variables From Deep Learning Ensemble Model

Wu,

Wang,

Dong

et al. 2023

Water Resources Research

View full text Add to dashboard Cite

Accurate runoff forecasting plays a vital role in issuing timely flood warnings. Whereas, previous research has primarily focused on historical runoff and precipitation variability while disregarding other factors’ influence. Additionally, the prediction process of most machine learning models is opaque, resulting in low interpretability of model predictions. Hence, this study develops an ensemble deep learning model to forecast runoff from three hydrological stations. Initially, time‐varying filtered based empirical mode decomposition (TVFEMD) is employed to decompose the runoff series into several internal mode functions (IMFs). Subsequently, the complexity of each IMF component is evaluated by the multi‐scale permutation entropy (MPE), and the IMFs are classified into high‐ and low‐frequency portions based on entropy values. Considering the high‐frequency portions still exhibit great volatility, robust local mean decomposition (RLMD) is adopted to perform secondary decomposition of the high‐frequency portions. Then, the meteorological variables processed by the Relief algorithm and variance inflation factor (VIF) features are employed as inputs, the individual subsequences of secondary and preliminary decomposition as outputs to the bidirectional gated recurrent unit (BiGRU) and extreme learning machine (ELM) models. Random forests (RF) are introduced to nonlinear ensemble the individual predicted sub‐models to obtain the final prediction results. The proposed model outperforms other models in various evaluation metrics. Meanwhile, due to the opaque nature of machine learning models, shapley is employed to assess the contribution of each selected meteorological variable to the long‐term trend of runoff. The proposed model could serve as an essential reference for precise flood prediction and timely warning.

show abstract

A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runoff prediction

Cited by 10 publications

References 28 publications

Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns

Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns

Changes in real income of households in the Czech Republic due to the Russian invasion of Ukraine

Robust Runoff Prediction With Explainable Artificial Intelligence and Meteorological Variables From Deep Learning Ensemble Model

Contact Info

Product

Resources

About