Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Archives of Hydro-Engineering and Environmental Mechanics

2 2022

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Flood Frequency Analysis and Hydraulic Design of Bridge at Mashan on River Kunhar

Riaz Khuram, Aslam Hafiz Muhammad Shahzad, Yaseen Muhammad Waseem, Ahmad Hafiz Haseeb, Khoshkonesh Alireza, Noshin Sadaf

Archives of Hydro-Engineering and Environmental Mechanics

2022

Vol. 69, nr 1

1--12

Kunhar River hydrology and hydraulic design of a bridge on this river are being studied using HEC-Geo-RAS and Hydrologic Engineering Centers River Analysis System (HEC-RAS). The river flows in the northern part of Pakistan and is 170 km long. On both sides of the river, there are residential settlements. The river hydraulics is studied by using 30-metre remotely sensed shuttle radar topographic mission - digital elevation model (SRTM DEM) and Arc Map. 32 cross-sections are imported from Geographic Information System (GIS) to HEC-RAS. On historical peak flow results, the extreme value frequency distribution is applied, and a flood is determined for a 100-year return period, with a discharge estimated as 2223 cubic metres. Three steady flow profiles are adopted for HEC-RAS, the first is for the maximum historical peak data, the second is for the 100-year return period, and the third profile is for the latter 100-year period with a safety factor of 1.28. With remote sensing-based assessments, the proposed location for a bridge is determined and then verified with a field survey which was physically conducted. The maximum water height estimated in the river is about 4.26 m. This bridge will facilitate about 50 thousand population of Masahan and its surroundings. It will create a shortest link between Khyber Pakhtunkhwa and Azad Kashmir and thus will enhance tourism and trade activities.

Artificial Intelligence Based Flood Forecasting for River Hunza at Danyor Station in Pakistan

Yaseen Muhammad Waseem, Awais Muhammad, Riaz Khuram, Rasheed Muhammad Babar, Waqar Muhammad, Rasheed Sajid

Archives of Hydro-Engineering and Environmental Mechanics

2022

Vol. 69, nr 1

59--77

Floods can cause significant problems for humans and can damage the economy. Implementing a reliable flood monitoring warning system in risk areas can help to reduce the negative impacts of these natural disasters. Artificial intelligence algorithms and statistical approaches are employed by researchers to enhance flood forecasting. In this study, a dataset was created using unique features measured by sensors along the Hunza River in Pakistan over the past 31 years. The dataset was used for classification and regression problems. Two types of machine learning algorithms were tested for classification: classical algorithms (Random Forest, RF and Support Vector Classifier, SVC) and deep learning algorithms (Multi-Layer Perceptron, MLP). For the regression problem, the result of MLP and Support Vector Regression (SVR) algorithms were compared based on their mean square, root mean square and mean absolute errors. The results obtained show that the accuracy of the RF classifier is 0.99, while the accuracies of the SVC and MLP methods are 0.98; moreover, in the case of flood prediction, the SVR algorithm outperforms the MLP approach.