Qualitatively and quantitatively explore injury severity of light motor vehicle drivers involved in heavy goods vehicle crashes

Abstract

ABSTRACT Crashes involving heavy goods trucks (HGVs) are of significant concern as it poses a higher risk of fatality to light motor vehicles (LMVs). The study constructs three Deep Forest models with different Cascade structures to explore the relationship between HGV-LMV crash severity and risk factors. Based on the HGV-LMV crash data in Shandong province, China, motorcycles, electric vehicles, and sedans are defined as the LMV. According to the comparison results, the Deep Forest with Cascade LightGBM is significantly better. Through model interpretability tools, the study found that motorcycle and electric vehicle drivers aged 58 to 86, and LMV drivers with 1 to 3 years of driving experience are more likely suffering severity and fatal injury (SFI) in HGV-LMV crashes. And, disobey traffic sign, illegal turning, overtaking, changing lane, and crashes happened on non-motorway, national and provincial roads have an positive effect on SFI.