Publications & Research

This paper describes a novel machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple ML techniques and utilizing diverse data sources. Our multimodal framework, called Hurricast, efficiently combines spatial–temporal data with statistical data by extr...

Artificial intelligence (AI) systems hold great promise to improve healthcare over the next decades. Specifically, AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of ap...

The COVID-19 pandemic has created unprecedented challenges worldwide. Strained healthcare providers make difficult decisions on patient triage, treatment and care management on a daily basis. Policy makers have imposed social distancing measures to slow the disease, at a steep economic price. We des...

There are benefits to be gained from combining the strengths of modeling frameworks that capture social, environmental and design-based considerations. Many of the important challenges of the next decade lie at the intersection of the natural environment, human decision making and the design of spac...

The escalating frequency and severity of natural disasters, exacerbated by climate change, underscore the critical role of insurance in facilitating recovery and promoting investments in risk reduction. This work introduces a novel Robust Optimization (RO) framework tailored for the calculation of c...

The escalating frequency and severity of natural disasters, exacerbated by climate change, underscore the critical role of insurance in facilitating recovery and promoting investments in risk reduction. This work introduces a novel Robust Optimization (RO) framework tailored for the calculation of c...

Tabular data is essential for applying machine learning tasks across various industries. However, traditional data processing methods do not fully utilize all the information available in the tables, ignoring important contextual information such as column header descriptions. In addition, pre-proce...

Flooding is one of the most destructive and costly natural disasters, and climate changes would further increase risks globally. This work presents a novel mul- timodal machine learning approach for multi-year global flood risk prediction, combining geographical information and historical natural di...

Flooding is one of the most destructive and costly natural disasters, and climate changes would further increase risks globally. This work presents a novel mul- timodal machine learning approach for multi-year global flood risk prediction, combining geographical information and historical natural di...

AI will fundamentally change our relationship with the weather. As climate change leads us into a new world where weather will be more extreme, we will need to incorporate AI into decision making.

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 e...

Climate change is intensifying the frequency and severity of natural disasters across the globe, making societal adaptation an urgent priority. This talk delves into two key avenues where Machine Learning (ML) can play a transformative role in addressing climate adaptation challenges. The first part...

Climate change leads to more frequent and costly natural disasters worldwide. In light of this, insurance can play a pivotal role in supporting recovery and incentivizing investments in hazard mitigation. In this talk, I will present our work on an Adaptive Robust Optimization (ARO) framework for ca...

The work presents a data-driven approach to mitigate air pollution impact from industrial plants on nearby cities by linking operational decisions with weather conditions. Our method combines predictive machine learning models to forecast short-term wind conditions and prescriptive production level ...

This work describes a novel machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple ML techniques and utilizing diverse data sources. Our multimodal framework, called Hurricast, efficiently combines spatial-temporal data with statistical data by extra...