Preferred Language
Articles
/
ixaF44sBVTCNdQwCV-Nn
Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem
...Show More Authors

Prediction of daily rainfall is important for flood forecasting, reservoir operation, and many other hydrological applications. The artificial intelligence (AI) algorithm is generally used for stochastic forecasting rainfall which is not capable to simulate unseen extreme rainfall events which become common due to climate change. A new model is developed in this study for prediction of daily rainfall for different lead times based on sea level pressure (SLP) which is physically related to rainfall on land and thus able to predict unseen rainfall events. Daily rainfall of east coast of Peninsular Malaysia (PM) was predicted using SLP data over the climate domain. Five advanced AI algorithms such as extreme learning machine (ELM), Bayesian regularized neural networks (BRNNs), Bayesian additive regression trees (BART), extreme gradient boosting (xgBoost), and hybrid neural fuzzy inference system (HNFIS) were used considering the complex relationship of rainfall with sea level pressure. Principle components of SLP domain correlated with daily rainfall were used as predictors. The results revealed that the efficacy of AI models is predicting daily rainfall one day before. The relative performance of the models revealed the higher performance of BRNN with normalized root mean square error (NRMSE) of 0.678 compared with HNFIS (NRMSE = 0.708), BART (NRMSE = 0.784), xgBoost (NRMSE = 0.803), and ELM (NRMSE = 0.915). Visual inspection of predicted rainfall during model validation using density-scatter plot and other novel ways of visual comparison revealed the ability of BRNN to predict daily rainfall one day before reliably.

Scopus Clarivate Crossref
View Publication
Publication Date
Wed Sep 01 2021
Journal Name
Baghdad Science Journal
On Comparison Study between Double Sumudu and Elzaki Linear Transforms Method for Solving Fractional Partial Differential Equations
...Show More Authors

        In this paper, double Sumudu and double Elzaki transforms methods are used to compute the numerical solutions for some types of fractional order partial differential equations with constant coefficients and explaining the efficiently of the method by illustrating some numerical examples that are computed by using  Mathcad 15.and graphic in Matlab R2015a.

View Publication Preview PDF
Scopus (4)
Scopus Clarivate Crossref
Publication Date
Sun Dec 07 2014
Journal Name
Baghdad Science Journal
The Modified Quadrature Method for solving Volterra Linear Integral Equations
...Show More Authors

In this paper the modified trapezoidal rule is presented for solving Volterra linear Integral Equations (V.I.E) of the second kind and we noticed that this procedure is effective in solving the equations. Two examples are given with their comparison tables to answer the validity of the procedure.

View Publication Preview PDF
Crossref
Publication Date
Sun Nov 01 2020
Journal Name
International Journal Of Nonlinear Analysis And Applications
Two Efficient Methods For Solving Non-linear Fourth-Order PDEs
...Show More Authors

This paper studies a novel technique based on the use of two effective methods like modified Laplace- variational method (MLVIM) and a new Variational method (MVIM)to solve PDEs with variable coefficients. The current modification for the (MLVIM) is based on coupling of the Variational method (VIM) and Laplace- method (LT). In our proposal there is no need to calculate Lagrange multiplier. We applied Laplace method to the problem .Furthermore, the nonlinear terms for this problem is solved using homotopy method (HPM). Some examples are taken to compare results between two methods and to verify the reliability of our present methods.

Scopus (10)
Scopus
Publication Date
Sat Dec 01 2018
Journal Name
Ain Shams Engineering Journal
A semi-analytical iterative method for solving differential algebraic equations
...Show More Authors

View Publication
Crossref (8)
Crossref
Publication Date
Mon Sep 23 2019
Journal Name
Baghdad Science Journal
New Approach for Solving Three Dimensional Space Partial Differential Equation
...Show More Authors

This paper presents a new transform method to solve partial differential equations, for finding suitable accurate solutions in a wider domain. It can be used to solve the problems without resorting to the frequency domain. The new transform is combined with the homotopy perturbation method in order to solve three dimensional second order partial differential equations with initial condition, and the convergence of the solution to the exact form is proved. The implementation of the suggested method demonstrates the usefulness in finding exact solutions. The practical implications show the effectiveness of approach and it is easily implemented in finding exact solutions.

       Finally, all algori

... Show More
View Publication Preview PDF
Scopus (22)
Crossref (10)
Scopus Clarivate Crossref
Publication Date
Mon Mar 08 2021
Journal Name
Baghdad Science Journal
B-splines Algorithms for Solving Fredholm Linear Integro-Differential Equations
...Show More Authors

Algorithms using the second order of B -splines [B (x)] and the third order of B -splines [B,3(x)] are derived to solve 1' , 2nd and 3rd linear Fredholm integro-differential equations (F1DEs). These new procedures have all the useful properties of B -spline function and can be used comparatively greater computational ease and efficiency.The results of these algorithms are compared with the cubic spline function.Two numerical examples are given for conciliated the results of this method.

View Publication Preview PDF
Publication Date
Sun Jul 04 2021
Journal Name
(al-qadisiyah-journal Of Pure Science(qjps
Reliable Iterative Method for solving Volterra - Fredholm Integro Differential Equations
...Show More Authors

The aim of this paper is to propose a reliable iterative method for resolving many types of Volterra - Fredholm Integro - Differential Equations of the second kind with initial conditions. The series solutions of the problems under consideration are obtained by means of the iterative method. Four various problems are resolved with high accuracy to make evident the enforcement of the iterative method on such type of integro differential equations. Results were compared with the exact solution which exhibits that this technique was compatible with the right solutions, simple, effective and easy for solving such problems. To evaluate the results in an iterative process the MATLAB is used as a math program for the calculations.

View Publication
Publication Date
Fri Jan 01 2016
Journal Name
Results In Physics
An efficient iterative method for solving the Fokker–Planck equation
...Show More Authors

View Publication
Crossref (8)
Crossref
Publication Date
Tue Sep 30 2014
Journal Name
Iosr Journal Of Mathematics
Modification Adomian Decomposition Method for solving Seventh OrderIntegro-Differential Equations
...Show More Authors

In this paper, a method based on modified adomian decomposition method for solving Seventh order integro-differential equations (MADM). The distinctive feature of the method is that it can be used to find the analytic solution without transformation of boundary value problems. To test the efficiency of the method presented two examples are solved by proposed method.

View Publication
Publication Date
Sun Sep 05 2010
Journal Name
Baghdad Science Journal
Volterra Runge- Kutta Methods for Solving Nonlinear Volterra Integral Equations
...Show More Authors

In this paper Volterra Runge-Kutta methods which include: method of order two and four will be applied to general nonlinear Volterra integral equations of the second kind. Moreover we study the convergent of the algorithms of Volterra Runge-Kutta methods. Finally, programs for each method are written in MATLAB language and a comparison between the two types has been made depending on the least square errors.

View Publication Preview PDF
Crossref