Jimi Oke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jimi Oke has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
- Mohammed Abdalazeem Mohammed
Department of Civil and Environmental Engineering, University of Massachusetts Amherst, Amherst, USA
8 shared publications - Eleni Christofa
Department of Civil and Environmental Engineering, University of Massachusetts, Amherst, MA
6 shared publications - Eric J. Gonzales
Department of Civil and Environmental Engineering, University of Massachusetts, Amherst, USA
3 shared publications - Mahsa Arabi
Department of Civil and Environmental Engineering, University of Massachusetts Amherst, MA, United States of America
3 shared publications - Peiyao Zhao
Department of Chemical Engineering, University of Massachusetts Amherst, MA, United States of America
3 shared publications - Tolu Oke
Department of Civil and Environmental Engineering, University of Massachusetts Amherst, Amherst, USA
3 shared publications
Latest Publications
- 11 September 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (3) , 33
Discovery of Electric Bus Driving Maneuver Regimes from Vehicle Trajectory Data Using Deep Autoencoder and Gaussian Mixture Model
- 11 September 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (3) , 33
Discovery of Electric Bus Driving Maneuver Regimes from Vehicle Trajectory Data Using Deep Autoencoder and Gaussian Mixture Model
- 11 July 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (2) , 26
A Scenario Discovery Approach to Transit Network Optimization for Improved Access in Areas of Persistent Poverty
- 11 July 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (2) , 26
A Scenario Discovery Approach to Transit Network Optimization for Improved Access in Areas of Persistent Poverty
- Open Access
- 4 July 2026
- Published by Elsevier in Next Sustainability
- Vol. 8
Early action in transportation, electricity grid, commercial and residential buildings is essential for deep and near net-zero decarbonization
- 4 July 2026
- Published by Elsevier in Next Sustainability
- Vol. 8
Open AccessEarly action in transportation, electricity grid, commercial and residential buildings is essential for deep and near net-zero decarbonization
- 3 May 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (2) , 13
A Functional Bus Stop Typology: Explainable Machine Learning on Transit Data to Inform Policymaking
- 3 May 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (2) , 13
A Functional Bus Stop Typology: Explainable Machine Learning on Transit Data to Inform Policymaking
- Open Access
- 30 April 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (2) , 12
Correction: Bus Stop Typology Reveals Crash Risk Environments
- 30 April 2026
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (2) , 12
Open AccessCorrection: Bus Stop Typology Reveals Crash Risk Environments
- Open Access
- 1 March 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (3) , 031008
Scenario discovery framework aids robust regional emissions mitigation planning
We present a comprehensive accounting and scenario discovery framework for sector-specific regional greenhouse gas emissions. Three regions in Connecticut, namely Bridgeport, Hartford, and New Haven, served as case studies. Our inventory approach combines bottom-up and top-down approaches, relying on readily available data sources. Via scenario discovery, we explore a range of plausible emissions outcomes in a stylized parameter space under reasonably bounded assumptions, which results in robust decarbonization scenarios at three levels ( Mild , Moderate , and Major ). The data-driven scenario narratives, accompanied by sensitivity analyses, highlight the importance of truck mileage, grid emissions factors, residential fossil fuel use, and commercial emissions for mitigation planning. Our results demonstrate that regional variability and multisectoral approaches are relevant for robust mitigation. Ultimately, we expect that this framework can be readily deployed to other regions and can serve as an exploratory screening tool to identify key areas of focus for equitable and effective emissions mitigation planning.
- 1 March 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (3) , 031008
Open AccessScenario discovery framework aids robust regional emissions mitigation planning
We present a comprehensive accounting and scenario discovery framework for sector-specific regional greenhouse gas emissions. Three regions in Connecticut, namely Bridgeport, Hartford, and New Haven, served as case studies. Our inventory approach combines bottom-up and top-down approaches, relying on readily available data sources. Via scenario discovery, we explore a range of plausible emissions outcomes in a stylized parameter space under reasonably bounded assumptions, which results in robust decarbonization scenarios at three levels ( Mild , Moderate , and Major ). The data-driven scenario narratives, accompanied by sensitivity analyses, highlight the importance of truck mileage, grid emissions factors, residential fossil fuel use, and commercial emissions for mitigation planning. Our results demonstrate that regional variability and multisectoral approaches are relevant for robust mitigation. Ultimately, we expect that this framework can be readily deployed to other regions and can serve as an exploratory screening tool to identify key areas of focus for equitable and effective emissions mitigation planning.
- Open Access
- 15 January 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (2)
Maps are good but are simpler maps better? Insights on urban bicycling in the US
Bicycles are critical to health and sustainability, and promise to play a key role in the decarbonization of passenger transportation worldwide. Yet, while infrastructure investments are well studied, the relationship between bicycle maps (availability and features) and bicycle usage remains largely unexamined. Using the United States as a case study, we surveyed 684 urban counties, finding that only 45% have publicly available bicycle maps online. From these maps, we observed five features: Level of Infrastructure , Amenity Locations , Level of Stress , Transit Location , and Interactive features. Based on these binary features, we clustered the counties via a Bernoulli mixture model to obtain a typology of three map types. Then using socioeconomic indicators from the American Community Survey as predictors, along with map-related features, we fitted three XGBoost models to predict county-level bicycle mode share, with R 2 test ranging from 0.45 to 0.58, indicating moderate explanatory power. The models indicate that map availability has a positive association with bicycle usage. Furthermore, we find that detailed maps are associated with lower bicycle usage, while the reverse is the case for simple maps. Finally, of the 5 map features identified, Level of Infrastructure and Transit Locations are the most relevant in explaining bicycle usage but with a negative association. Ultimately, producing maps that emphasize simple and legible design may represent a low-cost strategy to complement infrastructure investments and promote bicycle usage for healthier communities and climate change mitigation.
- 15 January 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (2)
Open AccessMaps are good but are simpler maps better? Insights on urban bicycling in the US
Bicycles are critical to health and sustainability, and promise to play a key role in the decarbonization of passenger transportation worldwide. Yet, while infrastructure investments are well studied, the relationship between bicycle maps (availability and features) and bicycle usage remains largely unexamined. Using the United States as a case study, we surveyed 684 urban counties, finding that only 45% have publicly available bicycle maps online. From these maps, we observed five features: Level of Infrastructure , Amenity Locations , Level of Stress , Transit Location , and Interactive features. Based on these binary features, we clustered the counties via a Bernoulli mixture model to obtain a typology of three map types. Then using socioeconomic indicators from the American Community Survey as predictors, along with map-related features, we fitted three XGBoost models to predict county-level bicycle mode share, with R 2 test ranging from 0.45 to 0.58, indicating moderate explanatory power. The models indicate that map availability has a positive association with bicycle usage. Furthermore, we find that detailed maps are associated with lower bicycle usage, while the reverse is the case for simple maps. Finally, of the 5 map features identified, Level of Infrastructure and Transit Locations are the most relevant in explaining bicycle usage but with a negative association. Ultimately, producing maps that emphasize simple and legible design may represent a low-cost strategy to complement infrastructure investments and promote bicycle usage for healthier communities and climate change mitigation.
- Open Access
- 1 January 2026
- Published by IOP Publishing in Environmental Research Letters
- Vol. 21 (2) , 024014
Typology of U.S. transit systems reveals energy data gap and potential for diesel-based emissions reductions
We present a typology of 2205 U.S. transit systems, derived from 167 operational indicators in the National Transit Database, to reveal distinct patterns. Using kernel principal component analysis and Gaussian mixture modeling, we identify five distinct transit system types: Metro Bus–Rail , Mid-Sized Urban , Hybrid Multimodal , Urban Specialized , and Diverse Operations . We also discover a gap in diesel consumption reporting (76% of systems), which are predominantly of the Mid-Sized Urban type. To bridge this critical data gap, we apply extreme gradient boosting to predict the diesel consumption for 1674 underreported systems. We then estimate lifecycle emissions, accounting for regional grid carbon intensity. The result highlights significant variability in diesel consumption and emissions across transit types, with Metro Bus–Rail systems contributing the highest emissions. To evaluate decarbonization potential, we simulate fleet electrification and grid decarbonization. Our scenario analyses indicate that up to 82% of 10.27 MMTCO 2 e diesel-based transit emissions can be eliminated through fleet electrification, with further grid decarbonization eliminating the remainder. These findings provide actionable insights for policymakers to prioritize electrification, optimize resource allocation, and support sustainable transit strategies in the U.S.
- 1 January 2026
- Published by IOP Publishing in Environmental Research Letters
- Vol. 21 (2) , 024014
Open AccessTypology of U.S. transit systems reveals energy data gap and potential for diesel-based emissions reductions
We present a typology of 2205 U.S. transit systems, derived from 167 operational indicators in the National Transit Database, to reveal distinct patterns. Using kernel principal component analysis and Gaussian mixture modeling, we identify five distinct transit system types: Metro Bus–Rail , Mid-Sized Urban , Hybrid Multimodal , Urban Specialized , and Diverse Operations . We also discover a gap in diesel consumption reporting (76% of systems), which are predominantly of the Mid-Sized Urban type. To bridge this critical data gap, we apply extreme gradient boosting to predict the diesel consumption for 1674 underreported systems. We then estimate lifecycle emissions, accounting for regional grid carbon intensity. The result highlights significant variability in diesel consumption and emissions across transit types, with Metro Bus–Rail systems contributing the highest emissions. To evaluate decarbonization potential, we simulate fleet electrification and grid decarbonization. Our scenario analyses indicate that up to 82% of 10.27 MMTCO 2 e diesel-based transit emissions can be eliminated through fleet electrification, with further grid decarbonization eliminating the remainder. These findings provide actionable insights for policymakers to prioritize electrification, optimize resource allocation, and support sustainable transit strategies in the U.S.
- 17 December 2025
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (1) , 2
Robust Forecasting Framework for Energy-Informed Planning in Urban Rail Transit Systems
- 17 December 2025
- Published by Springer Nature in Data Science for Transportation
- Vol. 8 (1) , 2
Robust Forecasting Framework for Energy-Informed Planning in Urban Rail Transit Systems
- 28 November 2025
- Published by Springer Nature in Data Science for Transportation
- Vol. 7 (3) , 27
Bus Stop Typology Reveals Crash Risk Environments
- 28 November 2025
- Published by Springer Nature in Data Science for Transportation
- Vol. 7 (3) , 27
Bus Stop Typology Reveals Crash Risk Environments