登入選單

返回Google圖書搜尋

An Optimization-Machine Learning Methodology to Managing Disruption of Rail-Truck Intermodal Hazmat Shipments

Arash Moradi RadAtiq w SiddiquiManish Verma

出版	SSRN, 2022
URL	http://books.google.com.hk/books?id=mingzwEACAAJ&hl=&source=gbs_api

註釋

Rail-truck intermodal networks serve as major freight infrastructure, transporting both regular and hazardous material. Disruptions in its service legs or at intermodal terminals can result in significant increase in cost and risk, which can be mitigated by first understanding the criticality of transportation infrastructure and then developing strategies to offset the adverse impact. We propose an optimization-machine learning methodology that enables us to categorize the infrastructure based on impact levels, which informs the development of appropriate mitigation strategy. The proposed methodology was applied to a realistic rail-truck intermodal network in United States and to conclude that: post-disruption consideration should be incorporated in the transportation planning problem; machine learning algorithms can efficiently categorize network elements with a high degree of accuracy; and efficient pro-active post-disruption management can avoid significant increase in either cost or risk.