Artificial Intelligence for Climate Action

Artificial Intelligence for Climate Action

Leveraging the power of artificial intelligence and mathematics to spur innovation and novel solutions to challenges at the intersection of climate change and national security

Our Contribution

APL engineers and scientists are building novel artificial intelligence (AI) capabilities to address the emerging national security challenges arising from climate change. With recent advances in generative AI and physics-constrained machine learning as well as increased remote sensing sources, there are new opportunities to continue to advance AI research toward addressing climate-related challenges for our nation and the world.

Visit APL’s Climate Security page to learn more about how the Lab is bringing all of its core competencies to bear on this critical challenge area.

Related Areas of Impact

Mission Area

Research and Exploratory Development

Related Programs

Human and Machine Intelligence

AI-Accelerated Earth System Models

APL researchers in the Intelligent Systems Center (ISC) are developing operational forecasts and tools for scientific exploration by accelerating Earth systems models. Existing physics models require extensive computational resources and can be time consuming to run, limiting the exploration of possible futures and characterization of uncertainty. Through collaboration with Earth systems researchers, and by leveraging state-of-the-art generative AI and other deep-learning approaches, we can overcome these limitations to accelerate understanding and prediction of Earth systems.

Physics-Constrained Machine Learning for Earth Systems Characterization

Incorporating physics constraints into machine learning approaches can ensure that algorithms do not violate physical laws, as well as learn with limited data. ISC researchers are building models of sea-ice drift with physics-inspired neural networks and modeling the impact of hurricanes on wave height using neural operators.

Machine Learning Super-Resolution of Climate Data

Traditional climate models often estimate climate variables at coarse spatial resolution for global coverage. We are applying machine learning super-resolution methods to enhance the spatial resolution of climate data, particularly focused on coastal regions prone to extreme temperatures. This will enhance the precision and usability of climate variables for localized climate impact studies.

Reinforcement Learning for Climate Decision-Making

As the climate changes faster than emissions can be mitigated, we are faced with the need for climate adaptation. The best way to adapt given resource constraints is a complex problem. ISC researchers are developing reinforcement learning methods to enable climate-informed decision-making. In particular, given potential solutions to address climate threats, our researchers optimize which solutions to deploy, and where, toward a comprehensive coastal defense-in-depth approach.

�Ӱ��Ƶ