Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques

Lohani, A. K.; Kumar, Rakesh; Singh, Rudra Pratap

doi:10.1016/j.jhydrol.2012.03.031

Cited by 180 publications

(76 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Synthetic data sets can be simulated using autoregressive models, which have been used widely in hydrological time series analysis (e.g. Salas, 1980;Hosking, 1984;Maidment, 1992;Modarres, 2007;Lohani et al, 2012;Malamud and Turcotte, 2012). Thus, we simulate a large data set of synthetic daily mean discharges by using autoregressive (AR) models following Maidment (1993).…”

Section: Methodsmentioning

confidence: 99%

An analysis of changes in flood quantiles at the gauge Neu Darchau (Elbe River) from 1875 to 2013

2016

View full text Add to dashboard Cite

Abstract. Within this investigation, we focus on a detailed analysis of the discharge data of the gauge Neu Darchau (Elbe River). The Elbe River inflows onto the North Sea. The gauge Neu Darchau is the most downstream discharge gauge of the Elbe River before it becomes an estuary. We follow the questions, whether the discharge characteristics of the Elbe River have changed over the last decades and how much common flood quantiles (i.e. 100-year flood) are affected by the latest extreme events in 2002, 2006, 2011, and 2013. Hence, we conduct (i) trend and seasonality analysis and (ii) an assessment of time-dependencies of flood quantiles by using quasi non-stationary extreme value statistics with both block maxima and peak-over-threshold approaches. The (iii) significance of the changes found in flood quantiles are assessed by using a stochastic approach based on autoregressive models and Monte Carlo simulations. The results of the trend analyses do show no clear evidences for any significant trends in daily mean discharges and increasing flood frequencies. With respect to the extreme events in 2002, 2006, 2011, and 2013 our results reveal, that those events do not lead to extraordinary changes in the 100-year floods. Nevertheless, in the majority an increase in the 100-year floods over the recent decades can be stated. Although these changes are not significant, for many time series of the 100-year flood quantiles there is a clear tendency towards the upper confidence band.

show abstract

Section: Methodsmentioning

confidence: 99%

An analysis of changes in flood quantiles at the gauge Neu Darchau (Elbe River) from 1875 to 2013

2016

View full text Add to dashboard Cite

show abstract

“…Data-driven models aim at studying the characteristics of the data itself, as well as the relationship between inputs and outputs of the models, such as regression models [11,12], time series analysis [13][14][15], artificial neural networks [16,17], fuzzy algorithms [18][19][20], and gray system theory [21]. Despite the lack of hydrological physical process analysis, data-driven models have been proven to be simple and effective for streamflow forecasting.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Models Combining EMD/EEMD and ARIMA for Long-Term Streamflow Forecasting

Wang

Qiu

2018

Water

View full text Add to dashboard Cite

Long-term streamflow forecast is of great significance for water resource application and management. However, accurate monthly streamflow forecasting is challenging due to its non-stationarity and uncertainty. Time series analysis methods have been proved to perform well in stationary time series forecasting, which can be derived from decomposition of the non-stationary sequence. As common decomposition methods in time domain, Empirical Mode Decomposition (EMD) and Ensemble Empirical Mode Decomposition (EEMD) are selected to decompose the components with different time-scale characteristics in the original hydrological time series in this study. The derived components are proved to be stationary by the stationarity test. Thus, Autoregressive Integrated Moving Average (ARIMA) model, a simple and effective time series analysis method, is used to forecast the components. A hybrid EMD/EEMD-ARIMA model is proposed in this study for long-term streamflow forecasting, which is applied to the upper stream of the Yellow River. The original daily streamflow time series of six years at the Tangnaihai station are firstly decomposed by EMD/EEMD into several stationary or simple non-stationary sub-series to explore detailed data information with different time scales. ARIMA models with appropriate parameters are then established for each subsequence to forecast the stream flow of the next year. Predicted ten-day and monthly stream flow is finally obtained combing the predictions of all the components. The EMD-ARIMA hybrid model performs best in forecasting high and moderate value of streamflow and fits best with the observation compared with EEMD-ARIMA and ARIMA models. The results not only verify the effectiveness of the proposed hybrid EMD/EEMD-ARIMA model in exploiting comprehensive information to improve the prediction but also indicate that the EMD-ARIMA model with end points disposal performs the best and can be used for long-term hydrological forecasting.

show abstract

“…The conceptual model requires comprehensive and detailed topography, hydrology and meteorology data. A statistical model has also been developed for hydrological modelling; usually by using time series data (Kar, Lohani, Goel, & Roy, 2010;Lohani, Kumar, & Singh, 2012). Statistical models generally require a set of historical observation data to determine the system's parameters.…”

Section: Introductionmentioning

confidence: 99%

Application of Vector Auto Regression Model for Rainfall-River Discharge Analysis

et al. 2015

View full text Add to dashboard Cite

River discharge quantity is highly depended on rainfall and initial condition of river discharge; hence, the river discharge has auto-correlation relationships. This study used Vector Auto Regression (VAR) model for analysing the relationship between rainfall and river discharge variables. VAR model was selected by considering the nature of the relationship between rainfall and river discharge as well as the types of rainfall and discharge data, which are in form of time series data. This research was conducted by using daily rainfall and river discharge data obtained from three weirs, namely Sojomerto and Juwero, in Kendal Regency and Glapan in Demak Regency, Central Java Province. Result of the causality tests shows significant relationship of both variables, those on the influence of rainfall to river discharge as well as the influence of river discharge to rainfall variables. The significance relationships of river discharge to rainfall indicate that the rainfall in this area has moved downstream. In addition, the form of VAR model could explain the variety of the relationships ranging between 6.4% -70.1%. These analyses could be improved by using rainfall and river discharge time series data measured in shorter time interval but in longer period. Keywords: rainfall, river discharge, VAR AbstrakBesar kecilnya debit sungai sangat tergantung pada hujan dan kondisi awal dari debit itu sendiri, sehingga terdapat hubungan auto-correlation. Sementara itu, proses pengalihragaman dari hujan menjadi debit aliran pada sungai membutuhkan waktu (lag) antara terjadinya hujan dan kenaikan debit sungai. Penelitian ini menggunakan model Vector Auto Regression (VAR) untuk menganalisis hubungan antara curah hujan dan debit. Model VAR dipilih dengan mempertimbangkan bentuk hubungan antara kedua variabel dan tipe data hujan maupun debit yang keduanya merupakan data deret waktu (time series). Data curah hujan dan data debit harian diperoleh dari tiga bendung yaitu Bendung Sojomerto, Bendung Juwero di Kabupaten Kendal dan Bendung Glapan di Kabupaten Demak, Provinsi Jawa Tengah. Hasil uji kausalitas menunjukkan hubungan yang signifikan baik antara pengaruh variabel curah hujan terhadap debit maupun pengaruh debit terhadap curah hujan. Hubungan kausalitas yang signifikan antara debit terhadap curah hujan mengindikasikan bahwa karakteristik hujan di wilayah ini bergeser dari hulu ke hilir. Model VAR yang terbentuk dapat menjelaskan keragaman hubungan antara kedua variabel antara 6,4% -70,1%. Hasil penelitian menunjukkan bahwa model statistik berpeluang digunakan dalam peramalan hubungan hujan dan debit sungai. Analisis ini dapat dipertajam dengan menggunakan data deret waktu pada interval waktu yang lebih rapat dan periode yang lebih panjang.Kata Kunci: hujan, debit sungai, VAR.

show abstract

Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques

Cited by 180 publications

References 58 publications

An analysis of changes in flood quantiles at the gauge Neu Darchau (Elbe River) from 1875 to 2013

An analysis of changes in flood quantiles at the gauge Neu Darchau (Elbe River) from 1875 to 2013

Hybrid Models Combining EMD/EEMD and ARIMA for Long-Term Streamflow Forecasting

Application of Vector Auto Regression Model for Rainfall-River Discharge Analysis

Contact Info

Product

Resources

About