Sustainable Modes Research Articles

Are californians willing to use shared automated vehicles (SAV) & renounce existing vehicles? An empirical analysis of factors determining SAV use & household vehicle ownership

Future smart transportation systems are anticipated to integrate automation and sharing of vehicles. Responding to the expected changes in shared mobility services, this study used representative data from over 4100 households in California to examine consumers' affinity to use shared automated vehicles (SAV) and their willingness to renounce existing vehicle(s) in the presence of SAVs - two interlinked factors determining the long-term success of SAVs. Results of the study showed that around 50 % of the households reported willingness to use SAVs but unwillingness to renounce their current vehicle(s). As innovators, another 9.1 % stated their affinity to use SAVs and renounce existing vehicle(s) but with heterogeneity across vehicle ownership levels. Random parameter logit models revealed that households using existing vehicles to work for ride hailing companies were significantly less likely to use SAVs and renounce their current vehicle(s). Households who had high awareness about self-driving cars, possessed full electric vehicles, used sustainable work travel modes (bike, e-bike, bikeshare), had greater number of leased vehicles and ridesharing trips were more likely to use SAVs and renounce current vehicle(s). Significant unobserved preference heterogeneity was recorded in the effects of behavioral and sociodemographic correlates. The study contributes by shedding new light on the behavioral determinants of the vehicle ownership impacts of SAVs. We discuss policy implications of the key findings.

Comprehensive Analysis of Physicochemical, Functional, Thermal, and Morphological Properties of Microgreens from Different Botanical Sources.

Due to the significant increase in global pollution and a corresponding decrease in agricultural land, there is a growing demand for sustainable modes of modern agriculture that can provide nutritious food. In this regard, microgreens are an excellent option as they are loaded with nutrients and can be grown in controlled environments using various vertical farming approaches. Microgreens are salad crops that mature within 15-20 days, and they have tender leaves with an abundant nutritive value. Therefore, this study aims to explore the physicochemical, techno-functional, functional, thermal, and morphological characteristics of four botanical varieties of microgreens, including carrot (Daucus carota), spinach (Spinacia oleracea), bathua (Chenopodium album), and Bengal gram (Cicer arietinum), which are known for their exceptional nutritional benefits. Among the four botanical varieties of microgreens studied, bathua microgreens demonstrated the highest protein content (3.40%), water holding capacity (1.58 g/g), emulsion activity (56.37%), and emulsion stability (53.72%). On the other hand, Bengal gram microgreens had the highest total phenolic content (32.2 mg GAE/g), total flavonoid content (7.57 mg QE/100 g), and DPPH activity (90.60%). Fourier transform infrared spectroscopy analysis of all microgreens revealed the presence of alkanes, amines, and alcohols. Moreover, X-ray diffraction analysis indicated low crystallinity and high amorphousness in the microgreens. Particle size analysis showed that the median, modal, and mean sizes of the microgreens ranged from 110.327 to 952.393, 331.06 to 857.773, and 97.567 to 406.037 μm, respectively. As per the observations of the results, specific types of microgreens can be utilized as an ingredient in food processing industry, including bakery, confectionery, and more, making them a promising nutritive additive for consumers. This study sheds light on various food-based analytical parameters and offers a foundation for future research to fully harness the potential of microgreens as a novel and sustainable food source, benefiting both the industry and consumers alike.

Carbon footprint effects of shifting from flights to night trains for Swedish tourism

Changes in travel behaviour are needed to tackle the climate impact associated with long-distance flights, including a switch to sustainable transport modes. In this paper, we analyse scenarios of carbon footprint reduction associated with a switch from flights to night trains for holidays in Europe for the case of Sweden, including outbound, inbound and domestic tourism. We use a prospective lifecycle assessment framework combined with results from a stated preference experiment to determine the impact of future mode shift behaviours. Our results indicate that a mode shift could be triggered by progressive night train policies resulting in (i) fewer transfers and (ii) price levels similar to those of flights. The shifts from flights to night trains could result in 9% lower cumulative carbon footprint in relation to a baseline travel demand scenario for the period 2025–2050. Decarbonization of long-distance travel in line with the Paris Agreement would likely require a combination of many different types of measures including a shift to low-carbon fuels.

Exploring Melbourne Metro Train Passengers’ Pre-Boarding Behaviors and Perceptions

The focus on sustainable transportation has increased interest in promoting sustainable modes of transport, such as rail. Understanding train passengers’ behaviors and perceptions is essential to enhance their travel experience and increase train ridership. Pre-boarding behaviors and perceptions are crucial in shaping the overall train travel experience. However, there are limited studies that have developed a systematic framework for investigating train passengers’ pre-boarding behaviors and perceptions. This paper examines the train passenger’s pre-boarding behaviors and perceptions about the station and platform. The study adopts a mixed-methods approach by developing a pre-boarding decision framework and combining it with questionnaire surveys to explore passengers’ behaviors and perceptions on the platform before boarding. A total of 429 valid responses from Melbourne metro train users were used for analysis. Descriptive statistics and correlation techniques were applied to identify patterns and relationships. The findings reveal common pre-boarding behaviors and perceptions. Furthermore, the study uncovers factors influencing these behaviors and perceptions, such as passenger demographics, travel patterns, and specific trip characteristics. For example, carrying large items and travel frequency significantly impact passengers’ travel experience in the pre-boarding phase. Waiting time, group travel, carrying small items, gender, and age group also significantly impact some pre-boarding behavior variables. Travel time, on the other hand, makes no significant impact on any of the pre-boarding variables that we examined. This research provides valuable insights for rail service operators and policymakers to enhance the pre-boarding experience, optimize station design, and improve passenger satisfaction.

Flexible Learning in Higher Education Institution: Experiences of Instructors in a Private Higher Institution

This research investigates instructors' experiences at Agusan del Sur College concerning Flexible Learning in the New Normal. The study adopts a mixed-method approach integrating quantitative and qualitative components. Participants are 30 full-time instructors across nine departments. The findings reveal that instructors need more training and technical competencies to conduct online courses, affecting the effectiveness of hybrid classes. Technical problems, including slow internet connections and unannounced power interruptions, despite these challenges, instructors value the flexibility inherent in Flexible Learning, spanning modalities, assessment methods, and instructional delivery, promoting greater student responsibility and time management, ultimately enhancing engagement and attentiveness. Moreover, smartphones and mobile applications serve as prevalent educational tools and eLearning resources, and there remains a preference for face-to-face classes over online learning. The study also underscores the positive impact of Flexible Learning, encompassing synchronous and asynchronous platforms, in enhancing digital and technological competencies, with 45.4% of students and 48.8% of instructors reporting its benefits. Additionally, instructors with 0-5 years of teaching experience exhibit excellent proficiency in Flexible Learning modalities and assessment methods. In conclusion, this research suggests that Flexible Learning could constitute a sustainable mode of delivery in higher education institutions, contingent on instructors receiving adequate training and support to navigate the challenges the New Normal poses effectively.

Construction of Social Practice Bases for University Students Oriented to The Cultivation of Practical Skills

The social practice teaching base for college students oriented to the cultivation of practical ability is an important position for the cultivation of applied talents and an important guarantee for the realization of collaborative education between schools and enterprises. Schools set applied talents as the cultivation goal, in addition to fully ensuring the teaching activities of theoretical knowledge, it is more important to highlight the teaching practice links, and should pay much attention to the training and improvement of students' practical ability in the process of practical teaching, and explore the establishment of sustainable management mode and operation mechanism to achieve win-win situation. Combined with the characteristics of applied talent training, the training process of talents in business administration, marketing and other majors is constantly enhanced to cultivate the practical ability of talents. The aim is to train students' practical operation ability and cultivate comprehensive management talents who can adapt to the development of the times.

Unravelling the relationship between ride-sourcing services and conventional modes in the city of Toronto: A stated preference study

The introduction of ride-sourcing services often has a disruptive impact on transportation networks. The availability of these services tends to produce negative externalities, including the replacement of trips made by more sustainable modes, increases in trip rates, and increases in vehicle-kilometers travelled. However, these services can also improve the accessibility of individuals without access to a private vehicle and help supplement spatial and temporal gaps in the transit network. Consequently, it is essential to understand the determinants of ride-sourcing adoption and usage to inform policies that mitigate the negative externalities of these services while capitalizing on their benefits. This study uses data from a web-based survey to examine the adoption and utilization of ride-sourcing in Toronto. Specifically, this study combines descriptive analysis with the estimation of econometric models to analyze ride-sourcing use and the relationship between ride-sourcing and conventional modes. The results offer insights into the nature of ride-sourcing use in Toronto and highlight how the relationship between ride-sourcing and conventional modes can vary across the population and trip purposes. This study aims to contribute to the literature by offering insights into the use of exclusive and shared ride-sourcing and examining the extent to which the relationship between ride-sourcing and conventional modes differs based on trip purposes.

Multi-Level Fuzzy Comprehensive Evaluation for Water Resources Carrying Capacity in Xuzhou City, China

Water resources, as an essential natural resource, plays an irreplaceable role in the ecological environment, social economy, and human survival. Water resource carrying capacity (WRCC), as an important indicator of sustainable development, has been widely used to assess the capacity of water resources to support economic and social development. Using Xuzhou City as a case study, the sustainable capacity of water resources in the current (from 2012 to 2020) and future (projected scenarios in 2025 and 2030) stages were investigated by constructing a multi-level fuzzy-based evaluation model. The results indicated that the average WRCC score is 0.4388 in Xuzhou City, ranging from 0.2908 to 0.6330, with a significant decline in the score value of 0.4644 in 2019 but an apparent improvement in WRCC from 2012 to 2020. However, the continued pressure on water resources sustainable development is unchanged in Xuzhou, according to the projected assessment of WRCC in 2025 and 2030. Overall, the WRCC in Xuzhou City will be overloaded under future development scenarios, i.e., sustainable development mode (Scenario A), water conservation mode (Scenario B), rapid socioeconomic development mode (Scenario C), and adjustment of industrial structure mode (Scenario D). Thus, several measures, such as industrial restructuring and water conservation and utilization, should be conducted to enhance the carrying capacity of regional water resources and ensure the quality and sustainability of regional social and economic development. The results can provide a reference for the rational utilization of water resources in Xuzhou and are of some significance in promoting the city’s coordinated socioeconomic growth.

Structure-based pharmacophore modeling and DFT studies of Indian Ocean-derived red algal compounds as PI3Kα inhibitors.

Phosphoinositide kinases (PIKs) are a type of lipid kinase that acts as an upstream activator of oncogenic signaling. Presently accessible therapeutic compounds have downsides, such as toxicity and dubious efficacy, as well as lengthy treatment durations, which have bred resistance. Here we attempt to screen the Indian Ocean-derived red algal compounds to be used as a promising lead for PI3Kα inhibitor development. Experimental structure of the PI3K alpha Isoform-Specific Inhibitor alpelisib complex-based pharmacophore model was constructed and used as key to mark off the suitable lead compounds from the pool of marine-derived red algal compounds of Indian Ocean. Besides, the study encompasses pharmacophore scaffold screening as well as physicochemical and pharmacokinetic parameter assessment. We employed molecular docking and molecular dynamics simulation to assess the binding type and stability of 21 red algal derivatives. Twelve compounds demonstrated a sustained binding mode within the PI3Kα binding pocket with an optimal protein backbone root-mean-square deviation, also prompted hydrogen bonding throughout the simulations, and also implies that these MNPs have firmly mediated the interaction with prime hinge region residues in the PI3Kα ATP binding pocket. DFT studies revealed that proposed compounds had the greatest occupied molecular orbital electrophilicity index, basicity, and dipole moment, all of which attributed their stability as well as binding affinity at the PI3Kα active site. Our study's findings revealed that CMNPD31054, CMNPD4798, CMNPD27861, CMNPD4799, CMNPD27860, CMNPD9533, CMNPD3732, CMNPD4221, CMNPD31058, CMNPD31052, CMNPD29281, and CMNPD31055 can be used as lead compounds for PI3KΑ isoform inhibitors design.

Studying the Joint Effects of Perceived Service Quality, Perceived Benefits, and Environmental Concerns in Sustainable Travel Behavior: Extending the TPB

The importance of the sustainability concept has gained increasing attention from scholars and practitioners. In this context, the aim of this study was to examine the determinants of intention to continue to use the new Metro in Qatar, which is considered a sustainable mode of travel. Therefore, in this paper, a special attention was paid to certain variables, such as environmental concern, perceived quality, and perceived benefits. A quantitative method approach was employed, in which data were collected based on self-administered questionnaires. A total of 1334 Qatar residents responded to the survey questionnaire, and Structural Equation Modeling (SEM) was used for hypothesis testing. The results confirmed the direct effects of perceived behavioral control, social influence, and attitudes on the intention of residents to continue to use the Metro network in their travel. Moreover, perceived behavioral control was found to play a mediating role, enhancing the indirect relationship between perceived benefits and intention to continue to use the Metro network. More importantly, environmental concerns significantly and positively affected the attitudes and perceived behavioral control of travelers; furthermore, these variables presented a mediated influence—through service quality—on the intention to continue to use the Metro network. This study enriched the sustainability behavior literature by examining the influences of crucial factors. Thus, this study is considered of great value for policy-makers who hope to maximize the awareness level of environmental sustainability among the population, in order to encourage them to embrace changes in their lifestyle towards becoming more environmentally responsible.

ANALISIS PEMILIHAN MODA TRANSPORTASI UMUM MENUJU STASIUN GAMBIR MENGGUNAKAN TRANSPORTASI ONLINE DAN BUS TRANSJAKARTA

Public transportation acts as a sustainable mode of transportation to reduce the increasing level of pollution and traffic congestion. Public transportation has many types, in Jakarta, for example, online transportation and Transjakarta buses. This study aims to analyze the characteristics of online transportation travellers and Transjakarta buses, analyze the chances of choosing between the two modes of public transportation, and determine the level of service according to the community. Data collection using questionnaires distributed at Gambir station. Characteristics of travelers were analyzed using descriptive statistics. The probability of choosing a mode is analyzed using the binary logit difference model with the help of multiple linear regression equations. The level of service of the two modes of public transportation was analyzed using a Likert scale. The results showed that the characteristics of online transportation travellers are dominated by female, of productive age, highly educated, worked as an employee, earned quite a lot of money, traveled for vacation or recreational purposes, and the reason for choosing the mode was getting to the destination quickly. The characteristics of Transjakarta bus travellers are dominated by male, productive age, highly educated, work as an employee, earn quite high, travel for vacation or recreational purposes, and the reason for choosing the mode is the low price. The dominant choice of public transportation mode is online transportation. The level of online transportation services for the security and convenience aspects is in the good category, and the ease and reliability aspects are in the very good category.Keywords: characteristics of travellers, transportation mode, likert scale

Unlocking the Potential of Digital, Situation-Aware Nudging for Promoting Sustainable Mobility

The context ultimately decides on mobility options and thus shapes mobility behavior. Nudges are an increasingly used strategy for promoting sustainable modes of everyday mobility. However, in most cases, the design of nudges and the triggers for issuing these interventions neglect the user's specific context and are thus less relevant to the recipient. Digital nudges communicated through mobile devices offer situation awareness, which is facilitated by geographic information systems (GIS). Using the geographic reference as the “primary key” allows for connecting the current location information of recipients with static and real-time environmental data that define the contextual situation. We describe a framework for triggering situation-aware nudges and provide a functional proof-of-concept. Through linking concepts from behavioral economics and psychology with methods from GIS science and Human-Computer-Interaction (HCI), we illuminate new opportunities for promoting sustainable mobility.

Deep trip generation with graph neural networks for bike sharing system expansion

Bike sharing is emerging globally as an active, convenient, and sustainable mode of transportation. To plan successful bike-sharing systems (BSSs), many cities start from a small-scale pilot and gradually expand the system to cover more areas. For station-based BSSs, this means planning new stations based on existing ones over time, which requires prediction of the number of trips generated by these new stations across the whole system. Previous studies typically rely on relatively simple regression or machine learning models, which are limited in capturing complex spatial relationships. Despite the growing literature in deep learning methods for travel demand prediction, they are mostly developed for short-term prediction based on time series data, assuming no structural changes to the system. In this study, we focus on the trip generation problem for BSS expansion, and propose a graph neural network (GNN) approach to predicting the station-level demand based on multi-source urban built environment data. Specifically, it constructs multiple localized graphs centered on each target station and uses attention mechanisms to learn the correlation weights between stations. We further illustrate that the proposed approach can be regarded as a generalized spatial regression model, indicating the commonalities between spatial regression and GNNs. The model is evaluated based on realistic experiments using multi-year BSS data from New York City, and the results validate the superior performance of our approach compared to existing methods. We also demonstrate the interpretability of the model for uncovering the effects of built environment features and spatial interactions between stations, which can provide strategic guidance for BSS station location selection and capacity planning.

Identifying profiles of ride-sourcing users in the Metro Vancouver Region for a better understanding of ride-sourcing behaviour

Ride-sourcing has the potential to attract demand from more sustainable modes, alter activity patterns, and worsen congestion; however, it can also help increase the mobility and accessibility of those who cannot drive. Understanding how and why these services are used can help inform policies that address the negative externalities of these services while taking advantage of their benefits. This study examines the use of ride-sourcing services, which were introduced just before the COVID-19 pandemic, in the Metro Vancouver Region. Using data from a web-based survey, this study applies latent class cluster analysis to identify profiles of ride-sourcing users based on the purposes for which they use ride-sourcing. To the authors’ knowledge, this is only the second study to identify latent segments of ride-sourcing users and the first to do so based on the purposes of their ride-sourcing trips. Additionally, the decision to use ride-sourcing and the profile to which an individual belongs are jointly modelled using a two-stage multinomial logistic regression model. The results suggest the impacts of ride-sourcing use on other modes and the frequency of ride-sourcing use may differ based on the profile to which the user belongs. Besides, the findings of this study highlight the influence of socio-demographic attributes, the use of other shared mobility services, and attitudinal factors on the utilization of ride-sourcing. This study aims to contribute to the literature by offering further insights into the heterogeneity among ride-sourcing users, which can help inform a more targeted approach to addressing the negative externalities of these services.

Impact of corridor highway system on communities: Built environment and travel mode choices

Conventional corridor management has focused on travel speed and efficiency while ignoring interactions between highway corridors and surrounding areas. This study investigates the interaction between the corridor highway system and the built environment around highways by estimating sustainable mode choices with respect to the land use characteristics of surrounding corridor highways throughout 29 regions in the U.S. The results indicate that the D variables at the corridor level matter. D variables at the corridor level, such as activity density, job-population balance, percentage of accessible jobs within 10 min by car, intersection density, percentage of 4-way intersections, and transit stop density, were highly associated with internal capture, walking trips, and transit use. The neighborhoods with higher activity density, job-population balance, intersection density, and better employment accessibility by transit experienced reduced VMT. The likelihood of internal trips, walking trips, and transit use decreased with household size and income; the opposite signs were found with VMT. The regional gasoline price had significant effects on all trips. In conclusion, this study provides planning and transportation researchers and practitioners with new evidence on the importance of built environmental characteristics (D variables) to encourage sustainable mode choices in the proximate neighborhoods of corridor highways.

A pedagogical approach optimization toward sustainable architectural technology education applied by massive open online courses

PurposeThe application of massive open online courses (MOOCs) helps integrate sustainable development goals (SDGs) into architectural curricula. The essence of MOOC development is building an education platform that promotes the sharing and continuing of global education resources.Design/methodology/approachThis study establishes a four-dimensional evaluation model based on the four characteristics of MOOCs. The quadrilateral area evaluation method is used to create an evaluation radar chart to comprehensively evaluate satisfaction and demand in the traditional teaching model of architectural technology. This study discusses whether the curriculum is suitable for the development of MOOCs and how to optimize the sustainable pedagogical mode according to its characteristics to meet future teaching needs and realize the sustainable development of education.FindingsSatisfaction evaluation found that current education is not open enough from the students' perspective; therefore, MOOCs enhance students' participation and significantly reduce future learning costs. Through demand evaluation, it was found that both teachers and students believed that the lack of direct and effective communication between them and the difficulty in ensuring the learning effect were problems that must be addressed in MOOCs.Originality/valueThis study focused on the sustainability of MOOCs in curriculum development. It emphasizes the combination of MOOCs' teaching modes and the course itself and provides specific guidance and suggestions for improving the course. It uses an evaluation method for objective analysis and visualization.

An exploration of the preferences and mode choice behavior between autonomous demand-responsive transit and traditional buses

With the advancement in autonomous driving techniques, autonomous demand-responsive transit (ADRT) is a newly emerging sustainable transport mode for the future, which will provide more flexible services to public users. ADRT offers benefits such as flexible stops and routes and comfortable seats, but it also involves risks due to the vehicles being driverless. This paper particularly investigates users’ preferences and attitudes towards ADRT, and mode choice behavior between ADRT buses and traditional buses. A survey with Likert scale statements and stated preference (SP) choice scenarios is designed and conducted to explore users’ attitudes towards the safety risks of autonomous vehicles (AVs), social concerns, service flexibility concerns when using AVs, interest in new things, and shuttle mode choices. An integrated choice and latent variable (ICLV) model is adopted to explore users’ psychological factors through latent variables and to integrate them into mode choice behavioral modeling. Estimated results indicate that users’ attitudes towards AV safety risks, their social concerns, and their flexibility concerns with ADRT strongly influence their mode choices and are strongly related to sociodemographic and travel-related factors such as age, gender, income, education, number of family members. In general, a young age, a high education level, a higher income, private car ownership, and better knowledge of AVs are positively related to attitudes towards ADRT. Females, users from large families, and users with driving licenses or long commuting times are less willing to adopt ADRT. The study's outcomes highlight significant heterogeneities among users and can be highly valuable for policymakers, such as government authorities, in providing social support and designing policies targeting specific population groups. This will be beneficial in attracting more users to this emerging mobility service and contributing to sustainable urban development.

Promoting Sustainable Transport in Developing Countries: A Case Study of University Students in Tehran

One of the ways to address the modern traffic-related problems is to encourage people to use sustainable travel modes more regularly. Transportation planners need to find the factors that affect people’s opinions toward using these modes. In this study, we investigated these factors using a case study of a developing country by distributing an online survey among the students of four universities in Tehran. The number of complete responses received was 134 from SUT, 63 for UT, 31 from AUT, and 204 from IUST, summing up to 432 responses. A binomial logistic regression model was used to find the paramount factors affecting the selection of cycling and public transportation. Our model found five and four statistically significant factors affecting preferences toward using bicycle and public transport, respectively. Several novel outcomes resulted from our study. First, expressing prestige to others resulted in the reduction of the preference of students toward cycling by 80%. Second, while a high number of the respondents are not currently using bikes to commute, a noticeable number of them are amongst the ones that will cycle in their daily commutes in an ideal condition. Third, in Iran, a religious approach is present in the society, which results in lower rates of public transport usage among females. Finally, while long commuting distance is the main barrier to cycling, travel time plays a bigger role in the preferences toward using public transportation. In the end, some practical solutions are suggested to encourage the usage of these modes. They include providing safe bicycle lanes and more space in the public transportation systems.

Assessing the Impact of Public Behavior and Industrial Emissions on Ambient Air Quality in Pakistan

Air pollution is a growing environmental concern worldwide, and Pakistan is no exception. The study investigates the impact of industrial emissions, as well as public behavior, on air pollution in Pakistan. For this purpose, a questionnaire-based survey was conducted among a sample size of 100 participants, including students, professors, and government employees. The goal was to assess their attitudes, practices, and understanding regarding air pollution, as well as their perception and contribution to the relevant issues and their role concerning industries and vehicles. The findings revealed significant insights into the prevailing situation. The respondents recognized the contributions of industrial emissions to pollution levels. However, a substantial portion of the participants exhibited limited knowledge regarding specific pollutants and their sources. These responses clarified certain facets regarding public behavior, including transportation choices, waste management practices, and energy-efficient technologies. It was evident that sustainable modes of transportation, such as cycling or public transportation, were underutilized, with personal vehicles being the primary choice. Furthermore, significant challenges were identified as a lack of proper waste management practices and the low adoption of energy-efficient technologies. Based on these findings, it is crucial to implement targeted interventions and raise awareness to address air pollution in Pakistan effectively. The study highlighted that there is adire need for increased education and public outreach initiatives to improve knowledge regarding air pollutants and their sources. Policies that support environmentally friendly transportation choices and encourage industry adoption of cleaner technologies should also be developed.

Using Deep Learning and Google Street View Imagery to Assess and Improve Cyclist Safety in London

Cycling is a sustainable mode of transportation with significant benefits for society. The number of cyclists on the streets depends heavily on their perception of safety, which makes it essential to establish a common metric for determining and comparing risk factors related to road safety. This research addresses the identification of cyclists’ risk factors using deep learning techniques applied to a Google Street View (GSV) imagery dataset. The research utilizes a case study approach, focusing on London, and applies object detection and image segmentation models to extract cyclists’ risk factors from GSV images. Two state-of-the-art tools, You Only Look Once version 5 (YOLOv5) and the pyramid scene parsing network (PSPNet101), were used for object detection and image segmentation. This study analyzes the results and discusses the technology’s limitations and potential for improvements in assessing cyclist safety. Approximately 2 million objects were identified, and 250 billion pixels were labeled in the 500,000 images available in the dataset. On average, 108 images were analyzed per Lower Layer Super Output Area (LSOA) in London. The distribution of risk factors, including high vehicle speed, tram/train rails, truck circulation, parked cars and the presence of pedestrians, was identified at the LSOA level using YOLOv5. Statistically significant negative correlations were found between cars and buses, cars and cyclists, and cars and people. In contrast, positive correlations were observed between people and buses and between people and bicycles. Using PSPNet101, building (19%), sky (15%) and road (15%) pixels were the most common. The findings of this research have the potential to contribute to a better understanding of risk factors for cyclists in urban environments and provide insights for creating safer cities for cyclists by applying deep learning techniques.