A comprehensive comparison of four input variable selection methods for artificial neural network flow forecasting models

Snieder, Everett; Shakir, R.; Khan, Usman T.

doi:10.1016/j.jhydrol.2019.124299

Cited by 57 publications

(28 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of the available data for each watershed, 60% is used for training, 20% for validation, and 20% for testing (the independent dataset). used, which is common practice for ANN-based flow forecasting models (Snieder et al, 2020;Abbot and Marohasy, 2014;Fernando et al, 2009;Banjac et al, 2015).…”

Section: Base Model Descriptionmentioning

confidence: 99%

“…Real-time data-driven flow forecasting models frequently use antecedent input variables (also referred to as autoregressive inputs) for predictions. Several studies have attributed poor model prediction on high flows to model over-reliance on antecedent input variables (Snieder et al, 2020;Abrahart et al, 2007;de Vos and Rientjes, 2009;Tongal and Booij, 2018). Consequently, the model predictions are similar to the most recent antecedent conditions, sometimes described as a lagged prediction (Tongal and Booij, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy

Snieder¹,

Abogadil²,

Khan³

2020

Preprint

View full text Add to dashboard Cite

Abstract. Data-driven flow forecasting models, such as Artificial Neural Networks (ANNs), are increasingly used for operational flood warning systems. However, flow distributions are highly imbalanced, resulting in poor prediction accuracy on high flows, both in terms of amplitude and timing error. Resampling and ensemble techniques have shown to improve model performance of imbalanced datasets such as streamflow. In this research, we systematically evaluate and compare three resampling: random undersampling (RUS), random oversampling (ROS), and SMOTER; and four ensemble techniques: randomised weights and biases, bagging, adaptive boosting (AdaBoost), least squares boosting (LSBoost); on their ability to improve high flow prediction accuracy using ANNs. The methods are implemented both independently and in combined, hybrid techniques. While some of these combinations have been explored in the broader machine learning literature, this research contains many of the first instances of these algorithms to address the imbalance problem inherent in flood and high flow forecasting models. Specifically, the implementation of ROS, and new approaches for SMOTER, LSBOOST, and SMOTER-AdaBoost are presented in this research. Data from two Canadian watersheds (the Bow River in Alberta, and the Don River in Ontario), representing distinct hydrological systems, are used as the basis for the comparison of the methods. The models are evaluated on overall performance and on high flows. The results of this research indicate that resampling produces marginal improvements to high flow prediction accuracy, whereas ensemble methods produce more substantial improvements, with or without a resampling method. Compared to simple ANN flow forecast models, the use of ensemble methods is recommended to reduce the amplitude and timing error in highly imbalanced flow datasets.

show abstract

Section: Base Model Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy

Snieder¹,

Abogadil²,

Khan³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Input variable selection is often done on an ad hoc basis [3], or using expert judgement and simple linear models [107]. Research in other geoscience fields suggests that input selection be done using a systematic approach based on a rigorous input ranking [108]. Formal input selection methods are used to determine which inputs from the larger input dataset are most useful in terms of relevance to the desired output prediction while minimizing redundancies between input variables [108].…”

Section: Rock Engineering Problem Mlas Opportunitiesmentioning

confidence: 99%

“…Research in other geoscience fields suggests that input selection be done using a systematic approach based on a rigorous input ranking [108]. Formal input selection methods are used to determine which inputs from the larger input dataset are most useful in terms of relevance to the desired output prediction while minimizing redundancies between input variables [108]. The framework for input selection has not been formalized and rarely receives the requisite attention [109][110][111].…”

Section: Rock Engineering Problem Mlas Opportunitiesmentioning

confidence: 99%

An Overview of Opportunities for Machine Learning Methods in Underground Rock Engineering Design

2019

View full text Add to dashboard Cite

Machine learning methods for data processing are gaining momentum in many geoscience industries. This includes the mining industry, where machine learning is primarily being applied to autonomously driven vehicles such as haul trucks, and ore body and resource delineation. However, the development of machine learning applications in rock engineering literature is relatively recent, despite being widely used and generally accepted for decades in other risk assessment-type design areas, such as flood forecasting. Operating mines and underground infrastructure projects collect more instrumentation data than ever before, however, only a small fraction of the useful information is typically extracted for rock engineering design, and there is often insufficient time to investigate complex rock mass phenomena in detail. This paper presents a summary of current practice in rock engineering design, as well as a review of literature and methods at the intersection of machine learning and rock engineering. It identifies gaps, such as standards for architecture, input selection and performance metrics, and areas for future work. These gaps present an opportunity to define a framework for integrating machine learning into conventional rock engineering design methodologies to make them more rigorous and reliable in predicting probable underlying physical mechanics and phenomenon.

show abstract

“…The first method is the model-free method (Bowden, 2005;Snieder et al, 2020) which employs a measure of the correlation coefficient criterion (Badrzadeh et al, 2013;Siqueira et al, 2018;Pal et al, 2013) to characterize the correlation between a potential model input and the output variable. The second method is the model-based method (Snieder et al, 2020) which usually utilizes the model and search strategies to determine the optimal input subset. Common search strategies include forward selection and backward elimination (May et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Multistep-ahead daily inflow forecasting using the ERA-Interim reanalysis data set based on gradient-boosting regression trees

Liao

Liu

et al. 2020

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Inflow forecasting plays an essential role in reservoir management and operation. The impacts of climate change and human activities have made accurate inflow prediction increasingly difficult, especially for longer lead times. In this study, a new hybrid inflow forecast framework – using the ERA-Interim reanalysis data set as input and adopting gradient-boosting regression trees (GBRT) and the maximal information coefficient (MIC) – is developed for multistep-ahead daily inflow forecasting. Firstly, the ERA-Interim reanalysis data set provides more information for the framework, allowing it to discover inflow for longer lead times. Secondly, MIC can identify an effective feature subset from massive features that significantly affects inflow; therefore, the framework can reduce computational burden, distinguish key attributes from unimportant ones and provide a concise understanding of inflow. Lastly, GBRT is a prediction model in the form of an ensemble of decision trees, and it has a strong ability to more fully capture nonlinear relationships between input and output at longer lead times. The Xiaowan hydropower station, located in Yunnan Province, China, was selected as the study area. Six evaluation criteria, namely the mean absolute error (MAE), the root-mean-squared error (RMSE), the Pearson correlation coefficient (CORR), Kling–Gupta efficiency (KGE) scores, the percent bias in the flow duration curve high-segment volume (BHV) and the index of agreement (IA) are used to evaluate the established models utilizing historical daily inflow data (1 January 2017–31 December 2018). The performance of the presented framework is compared to that of artificial neural network (ANN), support vector regression (SVR) and multiple linear regression (MLR) models. The results indicate that reanalysis data enhance the accuracy of inflow forecasting for all of the lead times studied (1–10 d), and the method developed generally performs better than other models, especially for extreme values and longer lead times (4–10 d).

show abstract

A comprehensive comparison of four input variable selection methods for artificial neural network flow forecasting models

Cited by 57 publications

References 34 publications

Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy

Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy

An Overview of Opportunities for Machine Learning Methods in Underground Rock Engineering Design

Multistep-ahead daily inflow forecasting using the ERA-Interim reanalysis data set based on gradient-boosting regression trees

Contact Info

Product

Resources

About