What will autonomous trucking do to U.S. trade flows? Application of the random-utility-based multi-regional input–output model

Huang, Yantao; Kockelman, Kara M.

doi:10.1007/s11116-019-10027-5

Cited by 17 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This would result in a new organization of road freight transport towards a structure similar to current multimodal freight transport networks [23]. Anticipated long-term impacts include cost savings for the trucking industry [24][25][26], which will increase road transport volumes [27]. Further, truck utilization is expected to increase [28][29][30], which could result in smaller truck fleets.…”

Section: Effects Of Digitalization On Road Freight Transportmentioning

confidence: 99%

How Will Digitalization Change Road Freight Transport? Scenarios Tested in Sweden

et al. 2020

View full text Add to dashboard Cite

Road freight transport is a key function of modern societies. At the same time, road freight transport accounts for significant emissions. Digitalization, including automation, digitized information, and artificial intelligence, provide opportunities to improve efficiency, reduce costs, and increase service levels in road freight transport. Digitalization may also radically change the business ecosystem in the sector. In this paper, the question, “How will digitalization change the road freight transport landscape?” is addressed by developing four exploratory future scenarios, using Sweden as a case study. The results are based on input from 52 experts. For each of the four scenarios, the impacts on the road freight transport sector are investigated, and opportunities and barriers to achieving a sustainable transportation system in each of the scenarios are discussed. In all scenarios, an increase in vehicle kilometers traveled is predicted, and in three of the four scenarios, significant increases in recycling and urban freight flows are predicted. The scenario development process highlighted how there are important uncertainties in the development of the society that will be highly important for the development of the digitized freight transport landscape. One example is the sustainability paradigm, which was identified as a strategic uncertainty.

show abstract

Section: Effects Of Digitalization On Road Freight Transportmentioning

confidence: 99%

How Will Digitalization Change Road Freight Transport? Scenarios Tested in Sweden

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This would result in a new organization of road freight transport towards a structure similar to current multi-modal freight transport networks [23]. Anticipated long-term impacts include trucking cost savings [24][25][26] which increase road transport volumes [27]. Also, increasing truck utilization is expected [28][29][30] which could result in smaller truck fleets.…”

Section: Effects Of Digitalization On Road Freight Transportationmentioning

confidence: 99%

Will Digitalization Change the Road Freight Transportation? - Future Scenarios with Sweden as a Case Study

Pernestål¹,

Engholm²,

Bemler³

et al. 2020

Preprint

View full text Add to dashboard Cite

Road freight transportation is a key function of modern societies. At the same time, road freight transportation accounts for significant emissions. To reach the UN sustainability goals, sustainable road freight transportation is key. Digitalization, including automation, digitized information, and AI provide opportunities to improve efficiency, reduce costs, and increase service levels in road freight transportation. Digitalization may also radically change the business ecosystem in the sector. In this paper, the question “How will digitalization change the road freight transportation landscape?” is addressed by developing four different future scenarios, using Sweden as a case study. For each of the four scenarios the impacts on the road freight transportation sector are investigated, and opportunities and barriers to reach a sustainable transportation system in each of the scenarios are discussed. In all scenarios an increase in vehicle kilometers travelled is predicted, and in three of the four scenarios significant increases of recycling and urban freight flows are predicted. The scenario development process highlighted how there are important uncertainties in the development of the society that will be highly important for the development of the digitized freight transportation landscape. One example is the sustainability paradigm, which was identified as a strategic uncertainty.

show abstract

“…Semi‐supervised learning includes expectation maximization (EM) algorithms and multi‐view learning. Thanks to computing advances, ML is being widely tested across various areas of transport data analysis, including predictions of truck‐type category (Huang & Kockelman, 2020), mode type (Pirra & Diana, 2019; Wang & Zhao, 2020; Xie et al., 2003), travel times (Zhang & Haghani, 2015), injury severity (Das et al., 2019; Delen et al., 2017; Hamad et al., 2019), traffic flow (Cui et al., 2019; Hosseini & Talebpour, 2019), trip purpose (Deng & Ji, 2010), electric vehicle‐charging schedules (Chung et al., 2019; Jahangir et al., 2019), automated‐vehicle applications—like object identification and driving response (Liang & Wang, 2021), and traveler choices of managed (and tolled) lanes (Ashraf et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

How does machine learning compare to conventional econometrics for transport data sets? A test of ML versus MLE

Kockelman

2021

Growth and Change

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) is being used regularly in many different fields. This paper compares traditional econometric methods that have better explanations of data analysis to ML methods, focusing on predicting, understanding and unpacking ML methods which have higher prediction accuracies of four key transport‐planning variables: household vehicle‐miles traveled (continuous variable), household vehicle ownership (count variable), mode choice (categorical variable), and land use change (categorical variable with strong spatial interactions). Here, the results of ten ML methods are compared to methods of ordinary least squares (OLS), multinomial logit (MNL), negative binomial and spatial auto‐regressive (SAR). The U.S.’s 2017 National Household Travel Survey and land use data sets from the Dallas‐Ft. Worth region of Texas are used. Results suggest traditional econometric methods work pretty well on the more continuous responses (VMT and vehicle ownership), but the random forest (RF), gradient boosting decision trees (GBDT), and extreme gradient boosting (XGBoost) methods delivered the best results, though the RF model required 30 to almost 60 times more computing time than XGBoost and GBDT methods. The RF, GBDT, XGBoost, light gradient boosting method (lightGBM), and catboost offer better results than other methods for the two “classification” cases, with lightGBM being the most time‐efficient. Importantly, ML methods captured the plateauing effect modelers may expect when extrapolating covariate effects.

show abstract

What will autonomous trucking do to U.S. trade flows? Application of the random-utility-based multi-regional input–output model

Cited by 17 publications

References 14 publications

How Will Digitalization Change Road Freight Transport? Scenarios Tested in Sweden

How Will Digitalization Change Road Freight Transport? Scenarios Tested in Sweden

Will Digitalization Change the Road Freight Transportation? - Future Scenarios with Sweden as a Case Study

How does machine learning compare to conventional econometrics for transport data sets? A test of ML versus MLE

Contact Info

Product

Resources

About