Dr Tomas Lagos
-
Ph.D. in Operations Research (2023) University of Pittsburgh, Swanson School of Engineering Thesis:
-
Master's in Operations Management (2017) University of Chile, Faculty of Physical and Mathematical Sciences Thesis:
-
Bachelor of Engineering in Industrial Engineering (2016) University of Chile
听
Dr Tomas Lagos is a Lecturer in the School of Information Systems and Technology Management (SISTM) at 91色情片 Sydney.
His research mission is to address pressing environmental and economic challenges, leveraging advanced computational methods to contribute to a more sustainable and resilient future. Tomas鈥檚 work bridges the gap between complex algorithmic development and real-world application, aiming to solve critical issues in resource management, climate adaptation, and modern supply chains.
听
- Publications
- Media
- Grants
- Awards
- Research Activities
- Engagement
- Teaching and Supervision
The First INFORMS TSL Data-Driven Research Challenge (2024-2025 TSL-Meituan)
Winning material:听Data-Driven Optimization for Meal Delivery: A Reinforcement Learning Approach for Order-Courier Assignment and Routing at Meituan
Call:听https://connect.informs.org/tsl/tslresources/datachallenge
Outcome: https://www.informs.org/Recognizing-Excellence/Community-Prizes/Transportation-Science-and-Logistics-Section/TSL-Data-Driven-Research-Challenge
Commitment to Impact
A core pillar of Tomas鈥檚 academic work is delivering measurable social, environmental, and economic impact. His research is designed to move beyond the theoretical and drive strategic policy changes.
Notable impacts include:
-
Electrical Network Resiliency: Conducted foundational research on enhancing the resilience of the electrical network in Chile. The strategic recommendations arising from these publications have been adopted and are currently being implemented.
-
Wildfire Mitigation Policies: Recently finalized advanced algorithms that provide data-driven recommendations on preventive landscape treatments to mitigate wildfire spread. These models were rigorously calibrated using real-world data from Texas and Australia. The next phase of this project involves applying these algorithms to real-life forestland data to help nations highly vulnerable to climate change craft strategic, effective landscape treatment policies.
Research Interests
Methodologies:
-
Artificial Intelligence & Machine Learning
-
Reinforcement Learning
-
Optimization (Bilevel, Robust, Combinatorial)
-
Online Scheduling
-
Network Theory
Applications:
-
Resources Policy Management
-
Sustainability and Climate Change Adaptation
-
Wildfires & Electrical Networks Resiliency
-
Supply Chain Logistics & Transportation
-
E-Commerce
听
听