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.
In this paper, we will discuss the performance of Bayesian computational approaches for estimating the parameters of a Logistic Regression model. Markov Chain Monte Carlo (MCMC) algorithms was the base estimation procedure. We present two algorithms: Random Walk Metropolis (RWM) and Hamiltonian Monte Carlo (HMC). We also applied these approaches to a real data set.
Diyala river is the most important tributaries in Iraq, this river suffering from pollution, therefore, this research aimed to predict organic pollutants that represented by biological oxygen demand BOD, and inorganic pollutants that represented by total dissolved solids TDS for Diyala river in Iraq, the data used in this research were collected for the period from 2011-2016 for the last station in the river known as D17, before the river meeting Tigris river in Baghdad city. Analysis Neural Network ANN was used in order to find the mathematical models, the parameters used to predict BOD were seven parameters EC, Alk, Cl, K, TH, NO3, DO, after removing the less importance parameters. While the parameters that used to predict TDS were fourte
... Show MoreFinger vein recognition and user identification is a relatively recent biometric recognition technology with a broad variety of applications, and biometric authentication is extensively employed in the information age. As one of the most essential authentication technologies available today, finger vein recognition captures our attention owing to its high level of security, dependability, and track record of performance. Embedded convolutional neural networks are based on the early or intermediate fusing of input. In early fusion, pictures are categorized according to their location in the input space. In this study, we employ a highly optimized network and late fusion rather than early fusion to create a Fusion convolutional neural network
... Show MoreThe majority of the environmental outputs from gas refineries are oily wastewater. This research reveals a novel combination of response surface methodology and artificial neural network to optimize and model oil content concentration in the oily wastewater. Response surface methodology based on central composite design shows a highly significant linear model with P value <0.0001 and determination coefficient R2 equal to 0.747, R adjusted was 0.706, and R predicted 0.643. In addition from analysis of variance flow highly effective parameters from other and optimization results verification revealed minimum oily content with 8.5 ± 0.7 ppm when initial oil content 991 ppm, tempe
ArcHydro is a model developed for building hydrologic information systems to synthesize geospatial and temporal water resources data that support hydrologic modeling and analysis. Raster-based digital elevation models (DEMs) play an important role in distributed hydrologic modeling supported by geographic information systems (GIS). Digital Elevation Model (DEM) data have been used to derive hydrological features, which serve as inputs to various models. Currently, elevation data are available from several major sources and at different spatial resolutions. Detailed delineation of drainage networks is the first step for many natural resource management studies. Compared with interpretation from aerial photographs or topographic maps, auto
... Show MoreThis study is dedicated to solving multicollinearity problem for the general linear model by using Ridge regression method. The basic formulation of this method and suggested forms for Ridge parameter is applied to the Gross Domestic Product data in Iraq. This data has normal distribution. The best linear regression model is obtained after solving multicollinearity problem with the suggesting of 10 k value.
Today, the prediction system and survival rate became an important request. A previous paper constructed a scoring system to predict breast cancer mortality at 5 to 10 years by using age, personal history of breast cancer, grade, TNM stage and multicentricity as prognostic factors in Spain population. This paper highlights the improvement of survival prediction by using fuzzy logic, through upgrading the scoring system to make it more accurate and efficient in cases of unknown factors, age groups, and in the way of how to calculate the final score. By using Matlab as a simulator, the result shows a wide variation in the possibility of values for calculating the risk percentage instead of only 16. Additionally, the accuracy will be calculate
... Show MoreThe stress(Y) – strength(X) model reliability Bayesian estimation which defines life of a component with strength X and stress Y (the component fails if and only if at any time the applied stress is greater than its strength) has been studied, then the reliability; R=P(Y<X), can be considered as a measure of the component performance. In this paper, a Bayesian analysis has been considered for R when the two variables X and Y are independent Weibull random variables with common parameter α in order to study the effect of each of the two different scale parameters β and λ; respectively, using three different [weighted, quadratic and entropy] loss functions under two different prior functions [Gamma and extension of Jeffery
... Show More