Image: © New Africa/Stock.adobe.com
TrebuNet, the machine learning tool built by Cork scientists, can help governments remove uncertainty from their decarbonisation plans.
Thanks to research by University College Cork (UCC) scientists, countries across the world will eventually be able to estimate future transport demands more accurately.
As transport-related emissions account for a significant portion of the global greenhouse gas emissions, finding ways to measure and predict demand will help governments as they work to refine climate policies.
The UCC academics worked in collaboration with scientists from Columbia University on research that led to the creation of a machine learning platform called TrebuNet.
The tool works more efficiently and accurately than the current methods countries are using to measure future transport demand.
Until now, projecting transport use was done either by simulating demands or by using regression-based analysis.
UCC academics believe that the machine learning architecture will be applicable to the wider energy modelling sector.
Siddarth Joshi led the research as part of his PhD in Energy Engineering at UCC. “This study provides insights into development of a novel machine learning architecture that increases the accuracy in the estimation of transport energy service demands,” he said.
“The innovative machine learning architecture and its benefits are measurable for the energy modelling community and is transferable to different disciplines.”
Brian Ó Gallachóir, UCC professor of energy engineering, agreed that the new system of projecting transport demands would act “as backbone for understanding the future direction of global energy markets” as well as climate policy.
Joshi and his colleagues’ research was published in the journal Scientific Reports. Dr James Glynn, senior research fellow with Columbia University explained that the new method the researchers devised demonstrated innovation in energy systems modelling and data analytics to solve weakness in understanding the outlook within energy system models.
“This helps us remove uncertainty in decarbonisation pathways,” he added. “Decarbonising transport in line with global net-zero 2050 targets requires urgent climate action. Collaboration between Columbia SIPA and UCC is leading to new approaches in energy systems modelling and data science to provide the tools and evidence-based research for decision makers designing climate policy.”
UCC carries out a lot of Ireland’s research related to energy modelling. In February, two UCC academics were given a funding award of €3.5m by the Government to look at how energy modelling could benefit Ireland.
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.
