The Energy Seminar: "Multimodal Machine Learning and Climate Change Adaptation," Cynthia Zeng, PhD Candidate, MIT

Talk title: Multimodal Machine Learning and Climate Change Adaptation

Abstract: Climate change is escalating the frequency and severity of natural disasters worldwide, necessitating urgent societal adaptation. In this talk, I present a multimodal machine learning (ML) framework designed to predict natural disasters. Traditionally, weather forecasting has depended on dynamical equations for over a century. However, recent advancements in artificial intelligence are revolutionizing this domain. The innovative multimodal ML framework leverages processing techniques from computer vision, natural language processing, time series signal processing techniques to integrate various data types, such as satellite imagery, textual information, and tabular data, to generate both short-term and long-term forecasts. Our first case study demonstrates that, for 24-hour hurricane forecasting, our ML models achieve results that are competitive with those produced by established national weather forecasting agencies. In our second case study, we explore the potential to create global models with a multi-year scope for assessing flood risks. Artificial intelligence will fundamentally change the way our interaction with weather, and these ML-driven risk assessments will have profound impacts on urban planning, infrastructure investment, renewable energy planning, and insurance policy.

Bio: Cynthia Zeng is a fifth year PhD candidate at the Operations Research Center at MIT, advised by Professor Dimitris Bertsimas. Her research focuses on developing machine learning and optimization methods to address issues around climate change and sustainability. Her notable contributions include a multimodal machine learning framework for predicting natural disasters, such as hurricanes and floods. In addition, her collaboration work with OCP Group, world’s largest phosphate producer, has been implemented and reduces 50% air pollution from industrial activities. With a vision to harness technology for a sustainable future, Cynthia brings valuable insights from her past roles as a quantitative analyst at BlackRock (London) and an investment analyst at SoftBank Vision Fund (China). She received her Bachelor’s degree in mathematics from Imperial College London.

More about the Energy Seminar:

The Energy Seminar has been a mainstay of energy engagement at Stanford for nearly 20 years and is one of the flagship programs of the Precourt Institute for Energy. We aim to bring a wide variety of perspectives to the Stanford community – academics, entrepreneurs, utilities, big businesses, and more. We're proud to have hosted some of the biggest names in the energy world as well as those just starting out. 

Seminars take place most Mondays during the academic year and typically have an audience of 100+ attendees. Anyone with an interest in energy is welcome to join one seminar or all of them! You can enjoy seminars in the following ways:

• Attend live. The auditorium may change quarter by quarter, so check each seminar event to confirm location. Explore the current quarter's schedule.
• Watch live in a browser livestream. Check each seminar event for its unique livestream URL.
• Watch recordings of past seminars 
  • Available on the Past Energy Seminars page and the Energy Seminars playlist of the Stanford Energy YouTube channel
• (For students) Take the seminar as a 1-unit class (CEE 301/ENERGY 301/MS&E 494)

If you'd like to join the Energy Seminar mailing list to hear about upcoming talks, sign up here and select the Energy Seminar checkbox.