Real-time data from mobile platforms to evaluate sustainable transportation infrastructure

Asensio, Omar Isaac; Alvarez, Kevin; Dror, Arielle; Wenzel, Emerson; Hollauer, Catharina; Ha, Sooji

doi:10.1038/s41893-020-0533-6

Cited by 37 publications

(31 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modal shifts away from carbon-intensive to low-carbon modes of travel hold considerable potential to mitigate GHG emissions 3 . Given the urgency of moving to a 'net zero' carbon emissions economy, there is growing consensus that technological substitution via electri cation 4 will not be su cient or fast enough to transform the transport system [5][6][7] . Beyond a net reduction in travel demand, one of the more promising ways to reduce transport carbon dioxide (CO 2 ) emissions is to promote and invest in active modes of transport (e.g.…”

Section: Mainmentioning

confidence: 99%

The climate change mitigation effects of active travel

Brand

Dons

Anaya-Boig

et al. 2020

Preprint

View full text Add to dashboard Cite

Active travel (walking or cycling for transport) is considered the most sustainable form of getting from A to B. Yet the net effects of active travel on mobility-related CO2 emissions are complex and under-researched. Here we collected travel activity data in seven European cities and derived lifecycle CO2 emissions from daily travel activity. Daily mobility-related lifecycle CO2 emissions were 3.2 kgCO2 per person, with car travel contributing 70% and cycling 1%. Cyclists had 84% lower lifecycle CO2 emissions from all daily travel than non-cyclists. Lifecycle CO2 emissions decreased by -14% (95%CI -12% to -16%) per additional cycling trip and decreased by -62% (95%CI -61% to -63%) for each avoided car trip. An average person who ‘shifted travel modes’ from car to bike decreased lifecycle CO2 emissions by 3.2 (95%CI 2.0 to 5.2) kgCO2/day, and using a bike as the ‘main method of travel’ gave 7.1 (95%CI 4.8 to 10.4) kgCO2/day lower lifecycle CO2 emissions than mainly using a car or van. Investing in and promoting active travel should be a cornerstone of strategies to meet net zero carbon targets, particularly in urban areas, while also improving public health and quality of urban life.

show abstract

Section: Mainmentioning

confidence: 99%

The climate change mitigation effects of active travel

Brand

Dons

Anaya-Boig

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…To mitigate the possibility for unobserved confounding variables, we also include a proprietary Station Quality Rating provided by the platform provider that ranges between 1 and 5, where 5 indicates a high-quality station location. The Negativity Score is a standardized measure of negative sentiment derived from Asensio et al (2020). It is used to test the conjecture that negative experiences at different POIs differentially affect the likelihood that a review will be classified as Functionality through interaction effects.…”

Section: Fractional Response Modelsmentioning

confidence: 99%

“…This digital infrastructure has created an ecosystem for users to engage with each other and share information about their EV experiences. The resulting user-generated data can be useful for policy analysis and real-time infrastructure management; however, large portions of this data is in the form of unstructured text, which require computational methods to extract insights (Asensio et al, 2020;Kühl et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…In this article, we deploy recent advances in neural-net-based classification algorithms in order to learn the dominant topics of discourse within the EV community. This task of natural language processing (NLP) has been challenging because, although neural-net-algorithms have been shown to perform well in sentiment classification tasks, there are still computational issues related to underdetection particularly with highly imbalanced data (Asensio et al, 2020;. Our approach here is to implement transformer based deep neural networks such as Bidirectional Encoder Representations from Text (BERT) and Transformer-XL (XLnet), which have both yielded promising results in a number of NLP tasks (LeCun & Hinton, 2015;Vaswani et al, 2017;Devlin et al, 2018;Yang et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models

Marchetto¹,

Ha²,

Dharur³

et al. 2020

CARMA 2020 - 3rd International Conference on Advanced Research Methods and Analytics

Self Cite

View full text Add to dashboard Cite

Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured text—inhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences.

show abstract

“… 8 , 9 , 10 Prior behavioral research has shown that policies designed to enhance EV adoption have largely focused on increasing the quantity of cars and connected infrastructure as opposed to the quality of the charging experience. 11 However, a fundamental challenge to deploying large-scale EV infrastructure is regular assessments of quality.…”

Section: Introductionmentioning

confidence: 99%

Topic classification of electric vehicle consumer experiences with transformer-based deep learning

Marchetto

Dharur

et al. 2021

Patterns

Self Cite

View full text Add to dashboard Cite

Summary The transportation sector is a major contributor to greenhouse gas (GHG) emissions and is a driver of adverse health effects globally. Increasingly, government policies have promoted the adoption of electric vehicles (EVs) as a solution to mitigate GHG emissions. However, government analysts have failed to fully utilize consumer data in decisions related to charging infrastructure. This is because a large share of EV data is unstructured text, which presents challenges for data discovery. In this article, we deploy advances in transformer-based deep learning to discover topics of attention in a nationally representative sample of user reviews. We report classification accuracies greater than 91% (F1 scores of 0.83), outperforming previously leading algorithms in this domain. We describe applications of these deep learning models for public policy analysis and large-scale implementation. This capability can boost intelligence for the EV charging market, which is expected to grow to US$27.6 billion by 2027.

show abstract

Real-time data from mobile platforms to evaluate sustainable transportation infrastructure

Cited by 37 publications

References 41 publications

The climate change mitigation effects of active travel

The climate change mitigation effects of active travel

Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models

Topic classification of electric vehicle consumer experiences with transformer-based deep learning

Contact Info

Product

Resources

About