UCC team develops new methods to predict transport demand
Researchers from University College Cork (UCC) have developed new ways to predict future demand for transport, one of the biggest drivers of global greenhouse gas emissions.
SUSTAINABILITY & CLIMATE
Check out our Sustainability and Climate Change Hub[1] where you will find the latest news, features, opinions and analysis on this topic from across the various Irish Examiner topic desks and their team of specialist writers and columnists.
Teaming up US Ivy League university Columbia, the researchers have come up with new modelling to account for transport patterns among people and freight, amid the expected global population growth of two billion people by 2050.
Published in the prestigious Scientific Reports journal[2], the researchers projected demand for air, road, and rail transport in both people and freight in Organisation for Economic Co-operation and Development (OECD) countries. The study used what the researchers said is a “novel custom deep learning neural network architecture called TrebuNet”.
Machine learning is where AI evolves with minimal human interference, while deep learning is an offset of machine learning that uses artificial neural networks to mimic the human brain.
Transport is proving to be one of the biggest conundrums for countries globally as they grapple with how to reduce greenhouse gas emissions in the coming years. One fifth of total greenhouse gas emissions come from the sector.
UCC and Columbia said countries across the world will more accurately be able to estimate future transport demands due to the research.
Siddharth Joshi, who led the research as part of his PhD in Energy Engineering at UCC, said: “This study provides insights into development of a novel machine learning architecture that increases the accuracy in the estimation of transport energy service demands. The innovative machine learning architecture and its benefits are measurable for the energy modelling community and is transferable to different disciplines.”
UCC Professor of Energy Engineering, Brian Ó Gallachóir, said energy markets would also benefit from the research as well as transport.
“Not only are the accurate transport demand projections important for energy system models and climate policy, but they also act as backbone for understanding the future direction of global energy markets,” he said.
Decarbonising transport in line with global net-zero 2050 targets requires urgent climate action, said senior research fellow with Columbia University, Dr James Glynn. “This helps us remove uncertainty in decarbonisation pathways,” he added.
The research was funded by Science Foundation Ireland and the National Natural Science Foundation China. According to the Sustainable Energy Authority of Ireland (SEAI), transport is “by far the largest source of energy-related carbon emissions” in the country.
The SEAI said that before the covid pandemic, it was responsible for more than 40% of energy-related carbon emissions in 2019.
“During 2020, transport was the sector whose energy use was most impacted by the public health restrictions taken to combat covid, and transport energy use fell by 26%. By the middle of 2021, transport activity and energy use had mostly returned to pre-pandemic levels. Transport accounted for 34% of energy-related CO2 emissions in 2021,” it said.
The Climate Action Plan 2023 calls for the transport sector to reduce its emissions by 50% by 2030.
References
- ^ Sustainability and Climate Change Hub (www.irishexaminer.com)
- ^ Scientific Reports journal (www.nature.com)