Quantifying and Forecasting Emission Reductions in Urban Mobility: An IoT-Driven Bike-Sharing Analysis

Area of Science:

• Environmental Science
• Urban Planning
• Transportation Engineering

Background:

• Growing urgency to address urban air quality and climate change.
• Need for sustainable mobility solutions to mitigate vehicular emissions.
• Limited exploration of the precise environmental impact of bike-sharing systems (BSSs).

Purpose of the Study:

• To quantify and forecast reductions in CO2 and NOx emissions from BSS usage in Madrid.
• To develop and validate an advanced predictive model integrating IoT sensor data.
• To provide a tool for urban planners and policymakers to assess and replicate BSS environmental benefits.

Main Methods:

• Integration of real-time IoT sensor data with an advanced predictive model.
• Analysis of nonlinear and seasonal mobility and emission patterns.
• Forecasting of CO2 and NOx emission reductions attributed to BSS usage.

Main Results:

• The predictive model achieved high accuracy in capturing mobility and emission patterns.
• Significant energy savings were demonstrated through the implementation of the framework.
• Quantified reductions in CO2 and NOx emissions resulting from BSS usage in Madrid.

Conclusions:

• BSSs offer confirmed environmental benefits for urban areas.
• The developed framework is a robust tool for assessing sustainable urban mobility.
• Findings support the extension and replication of BSS analysis in other cities to improve air quality.