Prediction of dust storms in construction projects using intelligent artificial neural network technology

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 or 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%.

Wind disasters adaptation in cities in a changing climate: A systematic review

“…Additionally, model simulation is useful in better designing or choosing adaptation measures by simulating functions of controlling processes [ 136 ] and effects of adaptive actions [ 137 ]. The model forecasting range from indicators such as wind speed [ 138 ] and water level [ 139 ] to events such as dust storms [ 140 ], cyclones [ 141 ], and floods [ 142 ]. Forecasting is indispensable to alarm approaching disasters, and it allows more time for people to evacuate from dangerous zones, thus avoiding unnecessary losses of human lives.…”

Machine Learning Applications to Dust Storms: A Meta-Analysis

“…Therefore, machine learning provides the potential to understand past patterns of dust storms to predict future events. Many studies have applied machine learning algorithms to dust storm detection and prediction, including artificial neural network (ANN), support vector machine (SVM), random forests, CNN, logistic regression, and naïve Bayes (Kh Zamim et al, 2019;Lee et al, 2021;Nabavi et al, 2018).…”

“…Dust storms are monitored by observing the associated weather conditions and land surface properties. The first method consists of ground observation studies (Ali et al, 2019;Dar et al, 2022;Ebrahimi-khusfi et al, 2021a;Ebrahimi-khusfi et al, 2021b;Iranmanesh et al, 2017;Kh zamim et al, 2019;Lu et al, 2006;Murayziq et al, 2017;Shaiba et al, 2018;Tiancheng et al, 2019;Xie et al, 2015;Zhang et al, 2015). This is the standard approach used to identify the specific features of a small region.…”

“…Some studies used three classes to classify dust storm intensity: {dusty, mid-dust, heavy dust storm}. Others used more ( Ali et al, 2019;Kh zamim et al, 2019;Murayziq et al, 2017;Nabavi et al, 2018;Rivas-perea et al, 2010). Some studies used a range of 0 to 9 to estimate the probability of a dust storm occurring (Qing-dao-er-ji et al, 2020;Rivas-perea et al, 2015;Tiancheng et al, 2019;Zhang et al, 2014).…”

“…However, it could be better in generalization if it is applied with large datasets to enhance the validation (Aryal, 2022b;Ebrahimi-khusfi et al, 2021b) ANN better performs classifying dust pixels than the threshold-based method over brightness surfaces as it can distinguish between a dust storm and sandy land (El-ossta et al, 2013). Also, applying the ANN technique is advantageous when handling internal relations to identify the effects of different meteorological variables without requiring feature selection (Kh zamim et al, 2019;Lee et al, 2021). However, it leads to uncertainty and ambiguity due to differences in the hyperparameters, such as learning rate, the number of hidden layers, and the number of neurons (Chacon-murguía et al, 2011;Lu et al, 2006).…”