Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: suspended sediment load

Sortuj według:

Ogranicz wyniki do:

Selection of level and type of decomposition in predicting suspended sediment load using wavelet neural network

Reddy Beeram Satya Narayana, Pramada S. K., Roshni Thendiyath

Acta Geophysica

2022

Vol. 70, no 2

847--857

The advancements in artificial intelligence play a significant role in solving the problems of researchers and engineers to develop prediction models with higher accuracy over the analytical and numerical models. The wavelet ensemble artificial intelligence model has a widespread application in forecasting hydrological datasets. The signal decomposition type, level and the mother wavelet affect the model performance in wavelet-based approaches. The present analysis focuses on studying the significance of the level and type of decomposition in wavelet transform for pre-processing the input variables to predict the target variable. In this work, to forecast seasonal suspended sediment load of the Kallada River basin in Kerala, two types of decomposition with decomposition levels ranging from 2 to 7 were adopted using seasonal flow data (wet and dry seasons). To rank the WANN models, compromise programming was adopted using the results based on statistical performance indicators and compared with the performance of the conventional FFNN model. From the accuracy assessment and ranking, type-2 with 5th level decomposition can capture the actual periodicity of the signal and predict the suspended sediment load with higher accuracy. It also shows the capability to predict the extreme events of time series.

A comparative study of artificial intelligence models for predicting monthly river suspended sediment load

Rezaei Khalil, Vadiati Meysam

Journal of Water and Land Development

2020

no. 45

107--118

When high precision modelling is required, for example, with the estimation of suspended sediment load (SSL), data-driven models are preferred over physically-based numerical models for their real-time, short-horizon prediction ability. The investigation of SSL, as an important index in engineering practices assessment, like design and operation of the hydraulic structures not only shows the hydrological behaviour of the river, but also illustrates the valuable information about the water quality deterioration, surface-groundwater interaction and land-use changes of the watershed. The following data-driven methods were compared in order to predict SSL at the Seyra gauging station on the Karaj River in Iran: Fuzzy logic (FL), two adaptive neuro-fuzzy inference systems (i.e., ANFIS-GP and ANFIS-FCM models), an artificial neural network (ANN), and least squares support vector machine (LSSVM). Monthly average river flow and SSL data for 50 years were obtained from the Tehran Regional Water Authority (TRWA). The data was first divided into training, validation and test sets and the SSL was then predicted using the ANN, FL, ANFIS, and LSSVM models. The reliability of the applied models was evaluated by the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). The results showed that the ANFIS models outperformed the ANN, FL, and LSSVM models for predicting SSL using the given input and output data. Overall, the performances of the artificial intelligence models used in the present study were satisfactory in predicting the non-linear behaviour of the SSL.