A Comparison of Machine Learning Techniques for Modeling River Flow Time Series: The Case of Upper Cauvery River Basin

Patel, Shivshanker Singh; Ramachandran, Parthasarathy

doi:10.1007/s11269-014-0705-0

Cited by 45 publications

(21 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This can be seen as a quintessential form of knowledge discovery, as no assumptions are required to perform these algorithms on unknown datasets. Furthermore, this is strongly related to machine learning that has been applied successfully in the hydrological context in papers such as [99,100]. Consequently, the resulting product has many similarities with a neuro-fuzzy system or adaptive neuro-fuzzy inference system (ANFIS) that has been applied in works such as [101].…”

Section: Causal Reasoning (Cr) Methodsmentioning

confidence: 99%

Rivers’ Temporal Sustainability through the Evaluation of Predictive Runoff Methods

et al. 2020

View full text Add to dashboard Cite

The concept of sustainability is assumed for this research from a temporal perspective. Rivers represent natural systems with an inherent internal memory on their runoff and, by extension, to their hydrological behavior, that should be identified, characterized and quantified. This memory is formally called temporal dependence and allows quantifying it for each river system. The ability to capture that temporal signature has been analyzed through different methods and techniques. However, there is a high heterogeneity on those methods’ analytical capacities. It is found in this research that the most advanced ones are those whose output provides a dynamic and quantitative assessment of the temporal dependence for each river system runoff. Since the runoff can be split into temporal conditioned runoff fractions, advanced methods provide an important improvement over classic or alternative ones. Being able to characterize the basin by calculating those fractions is a very important progress for water managers that need predictive tools for orienting their water policies to a certain manner. For instance, rivers with large temporal dependence will need to be controlled and gauged by larger hydraulic infrastructures. The application of this approach may produce huge investment savings on hydraulic infrastructures and an environmental impact minimization due to the achieved optimization of the binomial cost-benefit.

show abstract

Section: Causal Reasoning (Cr) Methodsmentioning

confidence: 99%

Rivers’ Temporal Sustainability through the Evaluation of Predictive Runoff Methods

et al. 2020

View full text Add to dashboard Cite

show abstract

“…However, apart from the k-nn (since it often requires large data sets as a nonparametric model), there is an over-fitting problem for the SETAR and ANN models. While over-fitting for the SETAR models can be avoided by the Akaike Information Criterion (Patel and Ramachandran 2015), a cross-validation procedure that implements early stopping approach was performed for the ANN models to avoid over-fitting for the training set (Lohani et al 2012). It is desirable to obtain a parsimonious model structure with a minimum error and a maximum efficiency (Srivastav et al 2007) to improve network generalization and prevent over-fitting (Hagan et al 1996).…”

Section: Study Area and Datamentioning

confidence: 99%

Impact of complexity on daily and multi-step forecasting of streamflow with chaotic, stochastic, and black-box models

Tongal

Berndtsson

2016

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Despite significant research advances achieved during the last decades, seemingly inconsistent forecasting results related to stochastic, chaotic, and black-box approaches have been reported. Herein, we attempt to address the entropy/complexity resulting from hydrological and climatological conditions. Accordingly, mutual information function, correlation dimension, averaged false nearest neighbor with E1 and E2 quantities, and complexity analysis that uses sample entropy coupled with iterative amplitude adjusted Fourier transform were employed as nonlinear deterministic identification tools. We investigated forecasting of daily streamflow for three climatologically different Swedish rivers, Helge, Ljusnan, and Kalix Rivers using self-exciting threshold autoregressive (SETAR), k-nearest neighbor (k-nn), and artificial neural networks (ANN). The results suggest that the streamflow in these rivers during the 1957-2012 period exhibited dynamics from low to high complexity. Specifically, (1) lower complexity lead to higher predictability at all leadtimes and the models' worst performances were obtained for the most complex streamflow (Ljusnan River), (2) ANN was the best model for 1-day ahead forecasting independent of complexity, (3) SETAR was the best model for 7-day ahead forecasting by means of performance indices, especially for less complexity, (4) the largest error propagation was obtained with the k-nn and ANN and thus these models should be carefully used beyond 2-day forecasting, and (5) higher number input variables except for the dominant variables made insignificant impact on forecasting performances for ANN and k-nn models.

show abstract

“…The quality of fit between observed and estimated time values was calculated using the Nash-Sutcliffe efficiency coefficient (Nash and Sutcliffe 1970;Patel and Ramachandran 2015;Liu et al 2016), as shown in Eq. 5.…”

Section: Harmony Searchmentioning

confidence: 99%

Model for Estimating the Time of Concentration in Watersheds

Almeida

Steffen

et al. 2016

Water Resour Manage

View full text Add to dashboard Cite

The time of concentration for a watershed is an essential parameter to the design of any hydrological project. In this study, a time of concentration estimation-model that uses variables obtained by monitoring rainfall-runoff events in a rural watershed of a tropical climate is proposed. In developing the model, the relationship between the time of concentration and independent variables was verified using a linear correlation matrix. Two variables with the highest correlation coefficient were selected to derive a model that can estimate the time of concentration. The Harmony Search (HS) optimization algorithm was employed to optimize the model parameters. The performance of the model was evaluated based on the Nash-Sutcliffe (NS) coefficient, which yielded a value greater than 0.80. The proposed model allows one to estimate the time of concentration using only the hydrograph of an event at the base level of a watershed, without the use of rainfall data.

show abstract

A Comparison of Machine Learning Techniques for Modeling River Flow Time Series: The Case of Upper Cauvery River Basin

Cited by 45 publications

References 29 publications

Rivers’ Temporal Sustainability through the Evaluation of Predictive Runoff Methods

Rivers’ Temporal Sustainability through the Evaluation of Predictive Runoff Methods

Impact of complexity on daily and multi-step forecasting of streamflow with chaotic, stochastic, and black-box models

Model for Estimating the Time of Concentration in Watersheds

Contact Info

Product

Resources

About