Predicting like-for-like pole replacements with multimodal learning - BC-1040

Genre de projet: Recherche
Discipline(s) souhaitée(s): Génie - informatique / électrique, Génie, Informatique, Sciences mathématiques, Statistiques / études actuarielles
Entreprise: Anonymous
Durée du projet: 4 à 6 mois
Date souhaitée de début: 11/02/2026
Langue exigée: Anglais
Emplacement(s): Richmond / Vancouver, BC, Canada
Nombre de postes: 1
Niveau de scolarité désiré: MaîtriseDoctorat
Ouvert aux candidatures de personnes inscrites à un établissement à l’extérieur du Canada: No

Au sujet de l’entreprise: 

The partner organization (ANONYMOUS) is an established Canadian electrical utility consulting firm based in British Columbia, with a team of approximately 95 professionals. The company provides engineering services to major Canadian utilities across transmission, distribution, substation, and telecommunications infrastructure. A significant part of its practice is distribution pole replacement design: assessing end-of-life wood poles and producing the engineering design required to replace them safely and to standard. The company is investing in an applied AI/R&D program that uses computer vision and machine learning to automate the interpretation of field photographs of utility poles, so that engineering design information currently extracted manually can be pre-filled automatically with calibrated confidence scores and clear flags for designer review. Interns joining this program work with a real production dataset of field imagery and design records, alongside the company's internal ML, platform, and engineering teams, with a direct path from research results to deployment in a production design workflow.

Veuillez décrire le projet.: 

What is the project about / main goal: Some pole replacements can be completed "like for like" — replaced as-is with no design modification — while others require engineering redesign. Predicting which is which from field images and design records is a high-value triage capability with immediate business value, because it separates straightforward replacements from poles requiring engineering review. The critical risk posture is high recall on modification-required cases, so no pole needing redesign is waved through.
Main tasks to be performed by the candidate:
• Curate existing binary labels (like-for-like vs modification-required) and link field images with design records and pole-level metadata
• Evaluate image-only, design-record-only, and multimodal approaches
• Calibrate confidence scores and define a designer-review fallback for uncertain cases
• Perform error analysis focused on high-risk false positives
Methodology/techniques to be used: Multimodal classification with calibrated confidence; targets: recall ≥ 0.90 on modification-required cases, precision ≥ 0.85 on auto-accepted like-for-like cases.

Expertise ou compétences exigées: 

Multimodal ML; computer vision; risk-aware evaluation.
Optional: assets
Production dataset of utility-pole field imagery with linked engineering design records; internal labeling platform and labeling pipeline; existing trained baseline models to build on; cloud GPU compute; day-to-day co-supervision by the company's internal ML and platform team.