Abstract

Sandstorms (dust storms) are considered the most events which cause destructive and costly damages in lots of desert regions. These sandstorms may be a reason of huge disasters (damages) on Environmental as well as Health aspects. The aim of this paper is to develop a mathematical model for predicting the Dust Storm in Republic of Iraq using Artificial Neural Network (ANN) technique. As a case study, four construction projects in Iraqi cities were selected (Baghdad, Basrah, Samawa, and Nasiriya) in order to identifying and prediction of the sandstorms, which significantly help to reduce the effects of damages. Only one ANN model was built to predict a dust storm. The datas of this model cited from Iraqi Meteorological Organization and Seismology. Four factors were adapted to develop the model (Max. Temperature, Min. Temperature, Rain and Wind), It was found that ANN has the ability to predict the dust storm with a high accuracys off the correlation coefficient (R) which is 90.00%, with a percentage of average accuracy is 89%.

Highlights

  • One of the most natural events that happened frequently in most of the deserts regions in the world is the dust storms

  • The sandstorms always take place at the waterless environments in the world, as in Mongolia, Middle East, Iraq, North China, Australia and Central Asia, the phenomenon of sandstorms has not yet been adequately explored, because of the lacks off observations surfaces, which are especially sparse in hyper-arid low populated desert regions

  • This research results are very important for planners and academic researchers, as it represents a great addition and renewal of ideas in the field of project management, in addition to making neural networks and their applications a vital part in the lives of engineers in the areas of planning, organization and implementation, where this study provides very important information, providing an accurate formula for predict the amount of dust during construction projects

Read more

Summary

Introduction

One of the most natural events that happened frequently in most of the deserts regions in the world is the dust storms. The sandstorms always take place at the waterless environments in the world, as in Mongolia, Middle East, Iraq, North China, Australia and Central Asia, the phenomenon of sandstorms has not yet been adequately explored, because of the lacks off observations surfaces, which are especially sparse in hyper-arid low populated desert regions. They are scattered in low-arid, low-density desert areas. In Central Asia presented a study about the sandstorms systems, PEN Vol 7, No 4, December 2019, pp.1659- 1666 which based on observation through a period of five years (1951-1955). Exam, and analysis are the things which researcher begun with in previous studies, because the research processes are cumulative processes that depend on the previous ones [6]

Objective
Research aims The main objectives of this study are
Trnsfer function selection of ANN model
Parameter of momentum term of ANN models
Model Equation
Results
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call