Meet Jinfeng Lou, CBI fellow addressing urban challenges

Nov 22, 2024

Jinfeng Lou

My name is Jinfeng Lou, and I am thrilled to be a Carnegie Bosch Institute fellow at Carnegie Mellon University. I earned my Ph.D. from the University of Hong Kong, where my research centered on advancing resilience and sustainability within the building and civil infrastructure sector by developing various AI and secured information systems.

What are your long-term goals?

My long-term goals include advancing the development of intelligent and resilient infrastructure systems to address critical urban challenges. I hope to integrate advanced AI methodologies with civil engineering principles to create solutions that can dynamically predict, respond to, and mitigate flood impacts on urban infrastructure, enhancing the safety and resilience of densely populated urban environments. Through the CBI fellowship program, I plan to focus on creating robust, adaptable models that incorporate real-time data from sensors, environmental indicators, and even human behavior during emergencies.

How will the CBI fellowship help you achieve these goals?

The CBI fellowship program offers a unique blend of academic rigor and industry collaboration, both of which are crucial for achieving my goals. Through the mentorship of best faculty and access to Bosch's industry-grade resources, I will be positioned to refine my technical expertise in AI while applying my research in real-world contexts. The program’s support for conference travel and international collaboration will also allow me to expand my professional network and gain insights from diverse perspectives, which are essential for interdisciplinary work.

What is the biggest challenge you hope to tackle?

One of the biggest challenges I hope to tackle is developing AI systems that can adapt to complex, rapidly changing urban environments, specifically for subway flood resilience. Traditional subway flood management systems are often rigid and reactive, struggling to predict or adapt to the unpredictable nature of climate change. My research aims to introduce AI-powered, physics-informed models that dynamically adjust to real-time conditions and anticipate critical infrastructure needs. Addressing these issues could set a new standard for intelligent urban subways, capable of minimizing disaster impacts on public safety and economic stability.

What obstacles do you see in addressing these challenges? 

A significant obstacle in addressing these challenges is the inherent complexity of modeling real-time, interdependent systems. Subway infrastructure presents a unique set of hurdles, such as intricate connectivity, multiple operational dependencies, and varied human responses in emergencies. Capturing these dynamics in a way that allows AI to both predict and adapt remains a technical challenge. Additionally, securing access to diverse, high-quality data is essential but difficult, as real-time data from urban infrastructure is often fragmented or incomplete. Regulatory constraints and privacy considerations also complicate data collection efforts. Despite these challenges, I am committed to developing interdisciplinary methodologies and leveraging resources at CMU and Bosch to innovate resilient, adaptive AI systems for urban infrastructure.