scholarly journals Modelling of runoff and sediment yield using ANN, LS-SVR, REPTree and M5 models

2017 ◽  
Vol 48 (6) ◽  
pp. 1489-1507 ◽  
Author(s):  
Birendra Bharti ◽  
Ashish Pandey ◽  
S. K. Tripathi ◽  
Dheeraj Kumar
Keyword(s):  
Sediment Yield ◽  
Sunshine Duration ◽  
Least Square ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Hydrological Process ◽  
M5 Model Tree ◽  
Yield Data ◽  
Input Variables ◽  
Runoff And Sediment Yield

Abstract In this study, the performance evaluation of five machine learning models, namely, ANNLM, ANNSCG, least square-support vector regression (LS-SVR), reduced error pruning tree (REPTree) and M5, was carried out for predicting runoff and sediment in the Pokhariya watershed, India using hydro-meteorological variables as input. The input variables were selected using the trial-and-error procedure which represents the hydrological process in the watershed. The seven input variables to all the models comprised a combination of rainfall, average temperature, relative humidity, pan evaporation, sunshine duration, solar radiation and wind speed. The monthly runoff and sediment yield data were used to calibrate and validate all models for the years 2000 to 2008. Evaluation of models' performances were carried out using four statistical indices, i.e., Nash–Sutcliffe coefficient (NSE), coefficient of determination (R2), percent bias (PBIAS) and RMSE-observations standard deviation ratio (RSR). Comparative analysis showed that the ANNLM model marginally outperformed the LS-SVR model and all the other models investigated during calibration and validation for runoff modelling whereas the LS-SVR model surpassed the artificial neural networks (ANN) model and other models for sediment yield modelling. Moreover, M5 model tree is better in simulating sediment yield and runoff than its near counterpart, the REPTree model, and marginally inferior when compared to LS-SVR and ANN models.

scholarly journals Enhancing Monthly Lake Levels Forecasting Using Heuristic Regression Techniques with Periodicity Data Component: Application of Lake Michigan

2021 ◽  
Author(s):  
Vahdettin DEMIR
Keyword(s):  
Lake Michigan ◽  
Absolute Error ◽  
Least Square ◽  
Multivariate Adaptive Regression Splines ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Lake Levels ◽  
M5 Model Tree ◽  
Comparison Results ◽  
Periodicity Component

Abstract This paper investigates the accuracy of three different techniques with periodicity component for estimation of monthly lake levels. The compared methods are Least Square Support Vector Regression (LSSVR) Multivariate Adaptive Regression Splines (MARS) and M5 Model Tree (M5-Tree). Data from Lake Michigan, located in the USA, is used in the analysis. In the first stage of the study, three different techniques were applied to forecast monthly lake-levels variations up to 8- mount ahead of time intervals. In the second stage, the influence of the periodicity component was applied (month number of the year, e.g., 1, 2, 3, …12) as an external sub-set in modeling monthly lake levels. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) were utilized are used for evaluating the accuracy of models. In both stages, the comparison results indicate that the MARS model generally performs superior to the LSSVR, and M5-Tree models. Furthermore, it has been discovered that including periodicity as an input to the models improves their accuracy in projecting monthly lake levels.

Utilization of Classification Techniques for the Determination of Liquefaction Susceptibility of Soils

2016 ◽  
pp. 124-160 ◽  
Author(s):  
J. Jagan ◽  
Prabhakar Gundlapalli ◽  
Pijush Samui
Keyword(s):  
Support Vector Machine ◽  
Earthquake Engineering ◽  
Relevance Vector Machine ◽  
Least Square ◽  
Support Vector ◽  
Ground Acceleration ◽  
Geotechnical Earthquake Engineering ◽  
Liquefaction Susceptibility ◽  
Input Variables

The determination of liquefaction susceptibility of soil is a paramount project in geotechnical earthquake engineering. This chapter adopts Support Vector Machine (SVM), Relevance Vector Machine (RVM) and Least Square Support Vector Machine (LSSVM) for determination of liquefaction susceptibility based on Cone Penetration Test (CPT) from Chi-Chi earthquake. Input variables of SVM, RVM and LSSVM are Cone Resistance (qc) and Peak Ground Acceleration (amax/g). SVM, RVM and LSSVM have been used as classification tools. The developed SVM, RVM and LSSVM give equations for determination of liquefaction susceptibility of soil. The comparison between the developed models has been carried out. The results show that SVM, RVM and LSSVM are the robust models for determination of liquefaction susceptibility of soil.

scholarly journals Estimating Daily Dew Point Temperature Using Machine Learning Algorithms

Water ◽  
2019 ◽  
Vol 11 (3) ◽  
pp. 582 ◽  
Author(s):  
Sultan Noman Qasem ◽  
Saeed Samadianfard ◽  
Hamed Sadri Nahand ◽  
Amir Mosavi ◽  
Shahaboddin Shamshirband ◽  
...  
Keyword(s):  
Meteorological Parameters ◽  
Gene Expression Programming ◽  
Machine Learning Algorithms ◽  
Dew Point ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
M5 Model Tree ◽  
Point Temperature ◽  
Dew Point Temperature ◽  
Input Parameters

In the current study, the ability of three data-driven methods of Gene Expression Programming (GEP), M5 model tree (M5), and Support Vector Regression (SVR) were investigated in order to model and estimate the dew point temperature (DPT) at Tabriz station, Iran. For this purpose, meteorological parameters of daily average temperature (T), relative humidity (RH), actual vapor pressure (Vp), wind speed (W), and sunshine hours (S) were obtained from the meteorological organization of East Azerbaijan province, Iran for the period 1998 to 2016. Following this, the methods mentioned above were examined by defining 15 different input combinations of meteorological parameters. Additionally, root mean square error (RMSE) and the coefficient of determination (R2) were implemented to analyze the accuracy of the proposed methods. The results showed that the GEP-10 method, using three input parameters of T, RH, and S, with RMSE of 0.96°, the SVR-5, using two input parameters of T and RH, with RMSE of 0.44, and M5-15, using five input parameters of T, RH, Vp, W, and S with RMSE of 0.37 present better performance in the estimation of the DPT. As a conclusion, the M5-15 is recommended as the most precise model in the estimation of DPT in comparison with other considered models. As a conclusion, the obtained results proved the high capability of proposed M5 models in DPT estimation.

scholarly journals Ranking of hybrid wavelet-AI models by TOPSIS method for estimation of daily flow discharge

2020 ◽  
Vol 20 (8) ◽  
pp. 3156-3171
Author(s):  
Hiwa Farajpanah ◽  
Morteza Lotfirad ◽  
Arash Adib ◽  
Hassan Esmaeili-Gisavandani ◽  
Özgur Kisi ◽  
...  
Keyword(s):  
Fuzzy Inference ◽  
Gene Expression Programming ◽  
Least Square ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Topsis Method ◽  
M5 Model Tree ◽  
Inference System ◽  
Flow Discharge ◽  
Discharge Temperature

Abstract This research uses the multi-layer perceptron–artificial neural network (MLP-ANN), radial basis function–ANN (RBF-ANN), least square support vector machine (LSSVM), adaptive neuro-fuzzy inference system (ANFIS), M5 model tree (M5T), gene expression programming (GEP), genetic programming (GP) and Bayesian network (BN) with five types of mother wavelet functions (MWFs: coif4, db10, dmey, fk6 and sym7) and selects the best model by the TOPSIS method. The case study is the Navrood watershed in the north of Iran and the considered parameters are daily flow discharge, temperature and precipitation during 1991 to 2018. The derived results show that the best method is the hybrid of the M5T model with sym7 wavelet function. The MWFs were decomposed by discrete wavelet transform (DWT). The combination of AI models and MWFs improves the correlation coefficient of MLP, RBF, LSSVM, ANFIS, GP, GEP, M5T and BN by 8.05%, 4.6%, 8.14%, 8.14%, 22.97%, 7.5%, 5.75% and 10% respectively.

scholarly journals Runoff and sediment yield modeling in a medium-size mediterranean watershed

2013 ◽  
Vol 44 (2s) ◽  
Author(s):  
Ossama M.M. Abdelwahab ◽  
Tiziana Bisantino ◽  
Fabio Milillo ◽  
Francesco Gentile
Keyword(s):  
Sediment Yield ◽  
Soil Conservation ◽  
Management Practices ◽  
Southern Italy ◽  
Medium Size ◽  
Validation Process ◽  
Yield Data ◽  
Event Scale ◽  
Prediction Capability ◽  
Runoff And Sediment Yield

The AnnAGNPS model was used to estimate runoff, peak discharge and sediment yield at the event scale in the Carapelle watershed, a Mediterranean medium-size watershed (506 km2) located in Apulia, Southern Italy. The model was calibrated and validated using five years of runoff and sediment yield data measured at a monitoring station located at Ordona – Ponte dei Sauri Bridge. A total of 36 events was used to estimate the output of the model during the period 2007-2011, in comparison to the corresponding observations at the watershed outlet. The model performed well in predicting runoff, as was testified by the high values of the coefficients of efficiency and determination during the validation process. The peak flows predictions were satisfactory especially for the high flow events; the prediction capability of sediment yield was good, even if a slight over-estimation was observed. Finally, the model was used to evaluate the effectiveness of different Management practices (MPs) on the watershed (converting wheat to forest, using vegetated streams, crop rotation corn/soybean, no tillage). While the maximum reduction in sediment yield was achieved converting wheat to forest, the best compromises between soil conservation and agriculture resulted to be crop rotations.

scholarly journals Rapid Identification of Pork Adulterated in the Beef and Mutton by Infrared Spectroscopy

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Ling Yang ◽  
Ting Wu ◽  
Yun Liu ◽  
Juan Zou ◽  
Yunmao Huang ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Mahalanobis Distance ◽  
Scatter Correction ◽  
Partial Least Square ◽  
Least Square ◽  
Detection Methods ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Distance Method ◽  
Identification Method

Consumers concern about food adulteration. Pork meat is the principal adulterated species of beef and mutton. The conventional detection methods have their own limitations; therefore, we sought to develop an efficient and economical identification method using an infrared spectroscopy technique for meat. The Mahalanobis distance method was used to remove outliers in spectrum data. Interferences were eliminated using multiple scatter correction, standard normal variate, Savitzky-Golay smoothing, and normalization. The partial least square discriminant analysis (PLS-DA) and support vector machine (SVM) were used to establish identification models. In the Mahalanobis distance method, the coefficient of test sets was increased from 0.93 to 0.99; the RMSEC and RMSECV were decreased from 0.17 to 0.09 and 0.21 to 0.11 accordingly. The coefficient of determination in-between the calibration and testing sets in PLS-DA reached 0.99 and 0.99, RMSEC was 0.06, and both the RMSECV and RMSEP were 0.08. In contrast, in SVM, methods were 0.97 and 0.96. The RMSEC, RMSECV, and RMSEP were 0.15, 0.17, and 0.24, respectively. In summary, using a combination of infrared spectroscopy technology with PLS-DA was a better identification method than the SVM method that can be used as an effective method to identify pork, beef, and mutton meat samples.

Comparative Evaluation of Artificial Intelligence Models for Drilling Rate of Penetration Prediction

2021 ◽  
Author(s):  
Ololade Adetifa ◽  
Ibiye Iyalla ◽  
Kingsley Amadi
Keyword(s):  
Artificial Intelligence ◽  
Least Square ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Artificial Intelligent ◽  
Rate Of Penetration ◽  
Drilling Data ◽  
Intelligent Models ◽  
Prediction Capability

Abstract Rate of penetration is an important parameter in drilling performance analysis. The accurate prediction of rate of penetration during well planning leads to a reduction in capital and operating costs which is vital given the recent downturn in oil prices. The industry is seen to embrace the use of novel technologies and artificial intelligence in its bid to be sustainable which is why this study focuses on the use of artificial intelligent models in predicting the rate of penetration. The predictive performance of three data-driven models [artificial neural network (ANN), extreme learning machine (ELM) and least-square support vector machine (LS-SVM)] were evaluated using actual drilling data based on three performance evaluation criteria [mean square error (MSE), coefficient of determination (R2) and average absolute percentage error (AAPE)]. The models were validated using the physics based Bourgoyne and Young's model. The results show that all three models performed to an acceptable level of accuracy based on the range of the actual drilling data because, although the ELM had the least MSE (1317.44) and the highest R2 (0.52 i.e. 52% prediction capability) the LS-SVM model had a smaller spread of predicted ROP when compared with the actual ROP and the ANN had the least AAPE (38.14). The results can be improved upon by optimizing the controllable predictors. Validation of the model's performance with the Bourgoyne and Young's model resulted in R2 of 0.29 or 29% prediction capability confirming that artificial intelligent models outperformed the physics-based model.

Sign in / Sign up

Export Citation Format

Share Document