Publication: Machine and Statistical Learning for Sustainable Infrastructure and Mobility Systems
dc.contributor.advisor | Jimi Oke | |
dc.contributor.author | Apostolov, Atanas | |
dc.contributor.department | University of Massachusetts Amherst | |
dc.contributor.department | Civil Engineering | |
dc.date | 2024-03-28T19:39:27.000 | |
dc.date.accessioned | 2024-04-26T18:14:24Z | |
dc.date.available | 2024-08-01T00:00:00Z | |
dc.date.issued | 2024-02-01 | |
dc.date.submitted | February | |
dc.date.submitted | 2024 | |
dc.description.abstract | This thesis presents machine and statistical learning approaches for sustainable planning in infrastructure and mobility systems. First, I have developed a convolutional neural network (CNN) to predict tree failure likelihood. Such assessments have traditionally been performed manually. I conduct a visual analysis of the predictions, indicating an approach for incorporating interpretability into model selection. Benchmarking the results against those produced by state-of-the-art CNNs, I show that a relatively simple model produces better results in a computational time that is three times faster. Via this novel framework, I demonstrate the potential of machine learning to automate and consequently reduce the costs of tree failure likelihood assessments in proximity to power lines, thereby promoting sustainable infrastructure. Secondly, I examine the effects of COVID-19 on mobility, segmented by transportation type, as well as social activity such as workplaces and residential, and their interdependencies. Using time series data across five continents, I estimate a Bayesian global vector autoregression model which explains patterns in activity and mobility trends and analyze their relationship with COVID-19 spread. I expect that the model framework and outcomes will guide policymakers to adopt appropriate measures to mitigate and safely recover from future disease outbreaks. | |
dc.description.degree | Master of Science in Civil Engineering (M.S.C.E.) | |
dc.description.embargo | 2024-08-01 | |
dc.identifier.doi | https://doi.org/10.7275/36519325 | |
dc.identifier.orcid | https://orcid.org/0000-0002-7321-6051 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14394/33091 | |
dc.relation.url | https://scholarworks.umass.edu/cgi/viewcontent.cgi?article=2482&context=masters_theses_2&unstamped=1 | |
dc.rights.uri | http://creativecommons.org/licenses/by-sa/4.0/ | |
dc.source.status | published | |
dc.subject | AI | |
dc.subject | CNN | |
dc.subject | infrastructure management | |
dc.subject | sustainability | |
dc.subject | BGVAR | |
dc.subject | global mobility | |
dc.subject | Civil Engineering | |
dc.title | Machine and Statistical Learning for Sustainable Infrastructure and Mobility Systems | |
dc.type | campusone | |
dc.type | article | |
dc.type | thesis | |
digcom.contributor.author | isAuthorOfPublication|email:naskoap@gmail.com|institution:University of Massachusetts Amherst|Apostolov, Atanas | |
digcom.date.embargo | 2024-08-01T00:00:00-07:00 | |
digcom.identifier | masters_theses_2/1395 | |
digcom.identifier.contextkey | 36519325 | |
digcom.identifier.submissionpath | masters_theses_2/1395 | |
dspace.entity.type | Publication |