Machine Learning for Occupational Slip-Trip-Fall Incidents Classification Within Commercial Grain Elevators

Publication Date

July 2021

Document Type

Contribution to a Book

Publication Title

In: Arezes P.M., Boring R.L. (eds) Advances in Safety Management and Human Performance. AHFE 2021. Lecture Notes in Networks and Systems, vol 262. Springer, Cham.



The grain handling industry plays a significant role in U.S. agriculture by storing, distributing, and processing a variety of agricultural commodities. Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to severe injuries, due to the nature of the activities and workplace. One of the leading causes of occupational incidents in all industries, including grain elevators, is slip, trip, and fall (STF). Therefore, prediction of STF incidents prior to occurrence is significant in occupational safety analysis. Despite high frequency of STF incidents at work, exploring their dominant factors via machine learning algorithms in agro-manufacturing environments is relatively new or unaddressed. Safety professionals may utilize the prediction and analysis of determinant factors of occupational incidents for actionable prevention and safety mitigation planning and practices. The objective of this research is to describe the slip-trip-fall (STF) injuries and trends in a population of agribusiness operations workers within commercial grain elevators in the Midwest of the United States, identify risk factors for STF injuries, and develop prevention strategies for STF hazards.


occupational safety, occupational incident analysis, machine learning, decision trees, bootstrap forest, safety management