RCEI Groundwork Grants to Address AI, Climate and Energy

RCEI awarded Groundwork Grants to faculty affiliates Kay Bidle, Benedict Borer, Xiaomeng Jin, Robert Mieth, Roger Wang, Lucas Marxen, and Efthymios Nikolopoulos to support development of research proposals that leverage the power of Artificial Intelligence (AI) to address climate and energy challenges. Below are descriptions of each of the winning proposals. 

Elucidating Emergent Rules Governing Marine Snow Properties and Carbon Sequestration using Artificial Intelligence and Machine Learning.

• Principal Investigator: Kay Bidle, Marine and Coastal Sciences, School of Environmental and Biological Sciences 
• Co-Principal Investigator: Benedict Borer, Marine and Coastal Sciences, School of Environmental and Biological Sciences.  

With support from their Groundwork Grant, Bidle and Borer will lead a workshop connecting researchers from computer science, oceanography, and geosciences to better understand how “marine snow” — tiny organic particles that sink through the ocean — can sequester carbon in the deep sea. This process, called the biological carbon pump, plays a key role in regulating Earth’s climate by removing carbon dioxide from the atmosphere. We are currently unable to predict this process due to the multifaceted and varied nature of these particles. Novel technologies can now collect detailed data on the sinking behavior and composition of thousands of individual particles, shifting the bottleneck for new discoveries from data acquisition to its analysis. The aim of this workshop is to explore how artificial intelligence and machine learning can aid in interpreting these data, foster collaboration across disciplines within Rutgers and beyond, and lay the groundwork for external grant applications. Aside from accelerating innovation in ocean carbon export research, a further aim of the planned workshop is to engage students and early career professionals to work at the exciting crossroads of AI/ML and Earth sciences. This will equip the next generation of interdisciplinary climate scientists with cutting-edge tools to tackle complex environmental challenges critical to society.  

Remote Sensing of Air Pollution Powered by Artificial Intelligence.

• Principal Investigator: Xiaomeng Jin, Environmental Sciences, School of Environmental and Biological Sciences.  

This Groundwork Grant will support a project that advances the use of artificial intelligence (AI) techniques to improve estimates of air pollution extremes caused by wildfires. There is growing interest in using machine learning models to translate satellite measurements to air pollution exposure, but current tools struggle to capture the extreme values caused by episodic events such as wildfires. Jin proposes to tackle this challenge by developing a physics-informed machine learning model that integrates a process-based chemical transport model with smart data balancing techniques that correct for imbalances in the training data. This work has the potential to enhance public health preparedness and air quality management by providing more accurate assessments of wildfire impacts, while strengthening partnerships with local agencies to support data-driven decision-making that protects vulnerable communities.  

An Open-Source Power Grid Model of NJ and Beyond as Energy for AI for Energy Groundwork.

• Principal Investigator: Robert Mieth, Industrial and Systems Engineering, School of Engineering.  

This project builds an open-source, high-resolution model of the New Jersey power grid and its surrounding regional grid to serve as critical groundwork for research at the intersection of AI, energy systems, and climate resilience. By integrating publicly available infrastructure, energy demand, weather, and demographic data, the model addresses two urgent and complementary challenges: “Energy for AI” and “AI for Energy”. On the one hand, AI and data centers are driving surging electricity demand which requires detailed grid planning models. On the other hand, AI offers powerful tools for forecasting, planning, and decision making if provided with realistic, structured data. The proposed model will enable solutions in both directions. A key project milestone is a workshop at Rutgers that will gather input from the power systems research community in our region and seed future collaborative proposals. This effort lays the foundation for future work on grid modernization, climate resilience, and AI-enabled energy systems at Rutgers. The quantitative insights enabled by this research are expected to directly benefit the public by informing pathways to more affordable and more reliable electricity supply. 

AI Assistant for NJFloodMapper.  

• Principal Investigator: Roger Wang, Civil and Environmental Engineering, School of Engineering 
• Co-Principal Investigator: Lucas Marxen, NJ Climate Change Resource Center, Bloustein School of Planning and Public Policy 
• Co-Principal Investigator: Efthymios Nikolopoulos, Civil and Environmental Engineering, School of Engineering. 

This project aims to develop an AI assistant to transform how geographic, disaster, and climate data are accessed and understood. This AI assistant will serve as a general-purpose tool capable of interpreting complex environmental datasets, enabling users to interact in a natural, conversational language. As a testing ground for this technology, the team will integrate the assistant into NJFloodMapper, a highly informative and widely used platform that provides flood risk and resilience data for New Jersey and the broader Mid-Atlantic region. By doing so, the project aims to enhance NJFloodMapper’s utility for the regional community, allowing residents, planners, and policymakers to make more informed decisions in the face of rising sea levels and intensifying storms driven by climate change. This project enhances public engagement with climate science by empowering New Jersey’s residents, planners, and policymakers with an accessible AI tool, fostering informed decision-making to bolster community resilience and economic competitiveness in the face of climate change across municipal, county, and state levels.