Quantifying the Uncertainties in Data-Driven Models for Reservoir Inflow Prediction

2020 ◽  
Vol 34 (4) ◽  
pp. 1479-1493 ◽  
Author(s):  
Xiaoli Zhang ◽  
Haixia Wang ◽  
Anbang Peng ◽  
Wenchuan Wang ◽  
Baojian Li ◽  
...  
Teknik ◽  
2016 ◽  
Vol 37 (2) ◽  
pp. 94
Author(s):  
Dyah Ari Wulandari ◽  
Hary Budieny ◽  
Dwi Kurniani

Dalam perhitungan inflow waduk sering digunakan persamaan neraca air waduk yang menggunakan data seri laporan harian operasi waduk, evaporasi dan curah hujan diwaduk, dan lengkung H-V-A waduk. Pada pengamatan data series laporan harian operasi waduk dan pengukuran kapasitas tampungan waduk, dapat terjadi kesalahan yang disebabkan karena kesalahan faktor manusia maupun faktor alat, hal ini akan menyebabkan kesalahan pula pada besarnya inflow waduk yang dihasilkan. Lebih lanjut di dalam perencanaan, data series inflow waduk ini diperlukan sebagai input pada pemodelan optimasi operasi waduk dan sedimentasi waduk, sehingga keakuratan datanya sangat diperlukan. Tujuan penelitian ini adalah untuk mengevaluasi tingkat akurasi penggunaan neraca air waduk dalam memprediksi inflow waduk. Untuk mengetahui tingkat akurasi dilakukan dengan membandingkan antara inflow waduk dari anak sungai hasil pengukuran dan hasil hitungan dengan persamaan neraca air waduk. Kemudian dilakukan variasi periode pengukuran dan kurva H- V-A yang digunakan. Berdasarkan penelitian yang dilakukan maka pada periode perhitungan yang lebih lama menghasilkan tingkat error yang lebih kecil. Pemakaian kurva waduk yang berbeda menghasilkan inflow yang berbeda. Tingkat error yang didapat masih cukup besar, diatas 30 %, sehingga perhitungan inflow waduk dari anak sungai dengan menggunakan metode neraca air waduk kurang akurat. [Title: Accuracy of Reservoir Inflow Prediction Using Reservoir Water Balance] In the calculation of reservoir inflow often used reservoir water balance equation using the data series of daily reports reservoir operation, evaporation and precipitation, and H-V-A curve. In observation of the data series of daily reports of reservoir operation and measurement of reservoir storage capacity, the errors may occur due to human error factor and factor appliance. This will cause an error on the reservoir inflow generated. Further, in the planning, this series data of reservoir inflow is required as input to the modeling of reservoir operation optimization and reservoir sedimentation, so the accuracy of the data are required. The purpose of this study was to evaluate the use of the reservoir water balance accuracy rate in predicting inflow. To determine the level of accuracy, the effort is done by comparing the inflow tributary reservoirs of measurement and the count with the reservoir water balance. Then perform variations of the measurement period and curves H-V-A is used. Based on the research conducted in the period longer calculation produces a smaller error. The different H-V-A curve results in the different inflow. Error rate obtained is still quite large, above 30%, so the calculation of tributary inflow reservoirs using reservoir water balance method is less accurate.  


2020 ◽  
Vol 10 (10) ◽  
pp. 3470
Author(s):  
Donghee Lee ◽  
Hwansuk Kim ◽  
Ilwon Jung ◽  
Jaeyoung Yoon

Reliable long-range reservoir inflow forecast is essential to successfully manage water supply from reservoirs. This study aims to develop statistical reservoir inflow forecast models for a reservoir watershed, based on hydroclimatic teleconnection between monthly reservoir inflow and climatic variables. Predictability of such a direct relationship has not been assessed yet at the monthly time scale using the statistical ensemble approach that employs multiple data-driven models as an ensemble. For this purpose, three popular data-driven models, namely multiple linear regression (MLR), support vector machines (SVM) and artificial neural networks (ANN) were used to develop monthly reservoir inflow forecasting models. These models have been verified using leave-one-out cross-validation with expected error S as a measure of forecast skill. The S values of the MLR model ranged from 0.21 to 0.55, the ANN model ranged from 0.20 to 0.52 and the SVM from 0.21 to 0.56 for different months. When used as an ensemble, Bayesian model averaging was more accurate than simple model averaging and naïve forecast for four target years tested. These were considered to be decent prediction skills, indicating that teleconnection-based models have the potential to be used as a tool to make a decision for reservoir operation in preparing for droughts.


2019 ◽  
Vol 33 (15) ◽  
pp. 5121-5136 ◽  
Author(s):  
Adnan Bashir ◽  
Muhammad Ahmed Shehzad ◽  
Ijaz Hussain ◽  
Muhammad Ishaq Asif Rehmani ◽  
Sajjad Haider Bhatti

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Muhammad Ahmed Shehzad ◽  
Adnan Bashir ◽  
Muhammad Noor Ul Amin ◽  
Saima Khan Khosa ◽  
Muhammad Aslam ◽  
...  

Reservoir inflow prediction is a vital subject in the field of hydrology because it determines the flood event. The negative impact of the floods could be minimized greatly if the flood frequency is predicted accurately in advance. In the present study, a novel hybrid model, bootstrap quadratic response surface is developed to test daily streamflow prediction. The developed bootstrap quadratic response surface model is compared with multiple linear regression model, first-order response surface model, quadratic response surface model, wavelet first-order response surface model, wavelet quadratic response surface model, and bootstrap first-order response surface model. Time series data of monsoon season (1 July to 30 September) for the year 2010 of the Chenab river basin are analyzed. The studied models are tested by using performance indices: Nash–Sutcliffe coefficient of efficiency, mean absolute error, persistence index, and root mean square error. Results reveal that the proposed model, i.e., bootstrap quadratic response surface shows good performance and produces optimum results for daily reservoir inflow prediction than other models used in the study.


Sign in / Sign up

Export Citation Format

Share Document