Addressing and mitigating the effects of climate change requires a collective effort, bringing together our strengths in industry, government, academia and civil society. As we continue to explore the role of technology to advance the art of the possible, we’re launching the Microsoft Climate Research Initiative (MCRI). This community of multidisciplinary researchers is working together to accelerate cutting-edge research and transformative innovation in climate science and technology.
MCRI enables us to bring Microsoft’s research and computing capabilities to a deep and ongoing collaboration with experts in the field. To launch this initiative, we are focusing on three critical areas in climate research where computational advances can drive major scientific transformations: Overcoming constraints to decarbonization, reducing uncertainties in carbon accounting, and assessing climate risks in greater detail .
Through these collaborative research projects, we hope to develop and support a highly engaged research ecosystem that includes a diversity of perspectives. Researchers will provide transdisciplinary and diverse expertise, particularly in areas beyond traditional computer science, such as environmental science, chemistry, and a variety of engineering disciplines. All results of this initiative are expected to be made public and freely available to drive even wider research and progress on these important climate issues.
“As researchers, we are excited to work together on projects chosen specifically for their potential impact on global climate challenges. With the computing capabilities of Microsoft and the domain expertise of our collaborators, our complementary strengths can accelerate progress in extraordinary ways.”
– Karin Strauss, Microsoft
Microsoft researchers will work with collaborators globally to co-investigate priority climate-related topics and bring innovative, world-class research to influential journals and countries.
First stage collaborations
Real-time monitoring of CO carbon control progress2 and Air Pollutant Observations with a Physically Informed Transformer-Based Neural Network
Jia Xing, Tsinghua University; Siwei Li, Wuhan University; Shuxin Zheng, Chang Liu, Shun Zheng, and Wei Cao, Microsoft
Understanding the change in CO2 emissions from CO measurement2 concentrations such as that made by satellites is very useful in tracking the real-time progress of carbon reduction actions. Current CO2 observations are relatively limited: methods based on numerical models have very low computational efficiency. The proposed study aims to develop a new method that combines numerical atmospheric modeling and machine learning to infer CO2 emissions from satellite observations and ground monitor sensor data.
AI-Based Real-Time Global Carbon Budget (ANGCB)
Zhu Liu, Tsinghua University; Biqing Zhu and Philippe Ciais, LSCE; Steven J. Davis, UC Irvine; Wei Cao and Jiang Bian, Microsoft
Climate change mitigation will depend on a carbon emission trajectory that successfully achieves carbon neutrality by 2050. To this end, an assessment of the global carbon budget is essential. The near-real-time AI-based Global Carbon Budget (ANGCB) project aims to provide the world’s first global carbon budget estimate based on Artificial Intelligence (AI) and other data science technologies.
Carbon reduction and removal
Computational discovery of novel metal-organic frameworks for carbon capture
Jeffrey Long, UC Berkeley; Xiang Fu, Jake Smith, Bichlien Nguyen, Karin Strauss, Tian Xie, Daniel Zuegner, and Chi Chen, Microsoft
CO removal2 from the environment is expected to be an integral component of keeping the temperature increase below 1.5°C. However, today this is an inefficient and expensive undertaking. This project will apply generative machine learning to the design of novel metal-organic frameworks (MOFs) to optimize low-cost CO removal2 from air and other dilute gas streams.
An evaluation of liquid metal-catalyzed CO2 Reducing
Michael D. Dickey, North Carolina State; Kourosh Kalantar-Zadeh, University of New South Wales; Kali Frost, Bichlien Nguyen, Karin Strauss, and Jake Smith, Microsoft
Co.2 the reduction process can be used to convert captured carbon into a storable form, as well as produce sustainable fuels and materials with lower environmental impacts. This project will evaluate liquid metal-based reduction processes, identifying advantages, bottlenecks and opportunities for improvement needed to achieve industry-relevant scales. It will lay the foundation for improving catalysts and address barriers to scaling.
Computational design and characterization of organic electrolytes for flow battery and carbon capture applications
David Kwabi, Anne McNeil, and Bryan Goldsmith, University of Michigan; Bichlien Nguyen, Karin Strauss, Jake Smith, Ziheng Lu, Yingce Xia, and Kali Frost, Microsoft
Energy storage is essential to enable 100% zero carbon electricity generation. This work will use generative machine learning models and quantum mechanical modeling to drive the discovery and optimization of a new class of organic molecules for energy-efficient electrochemical energy storage and carbon capture.
Prediction of properties of recyclable polymers
Aniruddh Vashisth, University of Washington; Bichlien Nguyen, Karin Strauss, Jake Smith, Kali Frost, Shuxin Zheng, and Ziheng Lu, Microsoft
Despite encouraging progress in recycling, many plastic polymers often end up being single-use materials. The plastics that make up printed circuit boards (PCBs), ubiquitous in every modern device, are among the most difficult to recycle. Vitrimers, a new class of polymers that can be recycled several times without significant changes in material properties, represent a promising alternative. This project will leverage advances in machine learning to select vitrimeric formulations that meet the demands imposed by their use in PCBs.
Accelerated discovery of green cement materials
Eleftheria Roumeli, University of Washington; Kristen Severson, Yuan-Jyue Chen, Bichlien Nguyen, and Jake Smith, Microsoft
The concrete industry is a major contributor to greenhouse gas emissions, most of which can be attributed to cement. The discovery of alternative cement is a promising way to reduce the environmental impacts of the industry. This project will use machine learning methods to accelerate the optimization of the mechanical properties of “green” cements that meet application quality constraints while minimizing the carbon footprint.
Causal inference for understanding the impact of humanitarian interventions on food security in Africa
Gustau Camps-Valls, University of Valencia; Ted Shepherd, University of Reading; Alberto Arribas Herranz, Emre Kiciman and Lester Mackey, Microsoft
The Causal4Africa project will investigate the problem of food security in Africa from a new perspective of causal inference. The project will illustrate the utility of causal discovery and effect assessment from observational data through intervention analysis. Ambitiously, it will improve the utility of causal PP approaches to climate risk assessment by enabling the interpretation and assessment of the likelihood and potential consequences of specific interventions.
Improving subseasonal forecasting with machine learning
Judah Cohen, Verisk; Dara Entekhabi and Sonja Totz, MIT; Lester Mackey, Alberto Arribas Herranz, and Bora Ozaltun, Microsoft
Water and fire managers rely on subseasonal forecasts two to six weeks in advance to allocate water, manage fires, and prepare for droughts and other weather extremes. However, capable predictions of the subseasonal regime are lacking due to a complex dependence on local weather, global climate variables, and the chaotic nature of weather. To address this need, this project will use machine learning to adaptively correct biases in traditional physics-based forecasts and to adaptively combine the forecasts of different models.
Get progress updates and new resources for accelerating sustainability scientific research >