Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Predicting Bridge Damage During Earthquake Using Machine Learning Algorithms
The more the magnitude of the earthquake, the more is the damage. During an earthquake, the mobility of the soft soil gets augmented and because most of the bridges are built on soft soil, there are even more chances of the bridge behaving like a ship in the sea. The stability of the bridges is the most crucial task to avoid all disasters. Many bridges collapse during earthquake because their mobility, and sustainability cannot stand the magnitude of the earthquake. In this paper, we have proposed a method to predict whether a bridge will sustain damage or not after an earthquake by using factors like magnitude of the earthquake, distance to epicenter of the bridge, bridge type, material used to make bridge and many more, using many classification algorithms like Logistic Regression, Decision Tree, Random Forest, XGBoost, and KNN. This prediction in turn will help to improve bridge sustainability during an earthquake, which in turn will help in saving many lives.
Predicting Bridge Damage During Earthquake Using Machine Learning Algorithms
The more the magnitude of the earthquake, the more is the damage. During an earthquake, the mobility of the soft soil gets augmented and because most of the bridges are built on soft soil, there are even more chances of the bridge behaving like a ship in the sea. The stability of the bridges is the most crucial task to avoid all disasters. Many bridges collapse during earthquake because their mobility, and sustainability cannot stand the magnitude of the earthquake. In this paper, we have proposed a method to predict whether a bridge will sustain damage or not after an earthquake by using factors like magnitude of the earthquake, distance to epicenter of the bridge, bridge type, material used to make bridge and many more, using many classification algorithms like Logistic Regression, Decision Tree, Random Forest, XGBoost, and KNN. This prediction in turn will help to improve bridge sustainability during an earthquake, which in turn will help in saving many lives.
Predicting Bridge Damage During Earthquake Using Machine Learning Algorithms
Garg, Yash (Autor:in) / Masih, Arpit (Autor:in) / Sharma, Utkarsh (Autor:in)
28.01.2021
1005296 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch