Grant: Alliance Grants
University of Toronto
$74,257.00
AI-Based Prediction of Construction-Induced Ground Vibrations for Reduced Environmental Impact and Community Well-Being
FY 2024-25
Summary
Construction-induced ground vibrations pose significant challenges to structural integrity, environmental quality, and project management in civil engineering. Current vibration monitoring relies heavily on extensive sensor networks, which are costly, prone to data loss, and inefficient for large-scale deployment. This research aims to address these limitations by developing advanced artificial intelligence (AI) and deep learning (DL) models capable of predicting ground vibrations with reduced sensor dependency, reconstructing lost data, and extending predictions to unsampled locations.
Integrating principles of geotechnical engineering, wave propagation, signal processing, and DL, the project will create hybrid models combining data-driven approaches with finite element simulations. By leveraging real-world datasets, the models will handle spatiotemporal prediction of vibrations and recovery of lost sensor data, addressing both random and continuous data gaps. Finite element simulations will inform transfer learning techniques, enhancing prediction accuracy for diverse ground vibration conditions.
This research is founded on closely collaborating with industry to develop an advanced practical AI-based tool for ground vibration monitoring and assessment. The models will be developed using extensive datasets and advanced sensors provided by the industry organization. The research outcomes include reduced monitoring costs, robust predictive capabilities, and improved vibration management practices, promoting sustainable and efficient construction processes. Additionally, the project will deliver training opportunities for highly qualified personnel (HQPs), equipping them with interdisciplinary expertise in geotechnics, artificial intelligence, and practical applications.
This research advances Canada's capacity in AI-driven engineering and offers economic, environmental, and societal benefits, including reduced construction costs, minimized environmental impact, and enhanced urban quality of life.
Program
Alliance Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
602265-2024
Name nom
Esmaeili, Kamran K
Department département
Civil & Mineral Engineering, Dept of
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
74257
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
1401
Research subject group en
Mining and mineral processing
Research subject group fr
Génie minier et minéral
Research subject en
Mining engineering
Research subject fr
Génie minier
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
AI-Based Prediction of Construction-Induced Ground Vibrations for Reduced Environmental Impact and Community Well-Being
Keywords
construction; environmental impact; ground vibration; machine learning; monitoring; numerical modeling; predictive models
Application summary
Construction-induced ground vibrations pose significant challenges to structural integrity, environmental quality, and project management in civil engineering. Current vibration monitoring relies heavily on extensive sensor networks, which are costly, prone to data loss, and inefficient for large-scale deployment. This research aims to address these limitations by developing advanced artificial intelligence (AI) and deep learning (DL) models capable of predicting ground vibrations with reduced sensor dependency, reconstructing lost data, and extending predictions to unsampled locations.
Integrating principles of geotechnical engineering, wave propagation, signal processing, and DL, the project will create hybrid models combining data-driven approaches with finite element simulations. By leveraging real-world datasets, the models will handle spatiotemporal prediction of vibrations and recovery of lost sensor data, addressing both random and continuous data gaps. Finite element simulations will inform transfer learning techniques, enhancing prediction accuracy for diverse ground vibration conditions.
This research is founded on closely collaborating with industry to develop an advanced practical AI-based tool for ground vibration monitoring and assessment. The models will be developed using extensive datasets and advanced sensors provided by the industry organization. The research outcomes include reduced monitoring costs, robust predictive capabilities, and improved vibration management practices, promoting sustainable and efficient construction processes. Additionally, the project will deliver training opportunities for highly qualified personnel (HQPs), equipping them with interdisciplinary expertise in geotechnics, artificial intelligence, and practical applications.
This research advances Canada's capacity in AI-driven engineering and offers economic, environmental, and societal benefits, including reduced construction costs, minimized environmental impact, and enhanced urban quality of life.