Introducing the Microsoft Climate Research Initiative
Addressing and mitigating the effects of climate change requires a collective effort, leveraging our strengths in industry, government, academia and civil society. As we continue to explore the role of technology in advancing the art of the possible, we are launching the Microsoft Climate Research Initiative (MCRI). This community of multidisciplinary researchers works together to accelerate cutting-edge research and transformative innovation in climate science and technology.
MCRI enables us to bring Microsoft’s research skills and computational capabilities to deep and ongoing collaboration with domain experts. For the launch of this initiative, we are focusing on three critical areas of climate research where advances in computing can drive key science transformations: overcoming constraints to decarbonization, reducing uncertainties in carbon accounting, and assessing risks. climate in more detail.
Through these collaborative research projects, we hope to develop and maintain a highly engaged research ecosystem comprising a diversity of perspectives. Researchers will offer cross-disciplinary and diverse expertise, particularly in areas beyond traditional computing, such as environmental science, chemistry, and various engineering disciplines. All results of this initiative should be made public and freely accessible to spur even broader research and progress on these important climate issues.
“As researchers, we are excited to work together on projects specifically selected for their potential impact on global climate challenges. With the compute capabilities of Microsoft and the domain expertise of our people, our complementary strengths can accelerate progress in incredible ways.
– Karin Strauss, Microsoft
Microsoft researchers will work with collaborators around the world to co-investigate priority climate-related topics and bring innovative, world-class research to influential journals and venues.
First phase collaborations
Real-time monitoring of carbon control progress from CO2 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 evolution of CO2 emissions from CO measurement2 concentrations such as those produced by satellites is very useful for monitoring the progress of carbon reduction actions in real time. Current CO2 observations are relatively limited: methods based on numerical models have very low computational efficiency. The proposed study aims to develop a novel method that combines atmospheric numerical modeling and machine learning to infer CO2 emitted by satellite observations and data from ground surveillance sensors.
AI-powered Near 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
Mitigation of climate change will depend on a carbon emissions trajectory that successfully achieves carbon neutrality by 2050. To this end, an assessment of the global carbon budget is essential. The AI-based, near real-time ANGCB (Global Carbon Budget) project aims to provide the world’s first carbon budget assessment based on artificial intelligence (AI) and other data science technologies.
Carbon Reduction and Removal
Computational discovery of new metal-organic frameworks for carbon capture
Jeffrey Long, University of Berkeley; Xiang Fu, Jake Smith, Bichlien Nguyen, Karin Strauss, Tian Xie, Daniel Zuegner and Chi Chen, Microsoft
Eliminate CO2 environment should be an integral part of keeping the temperature increase below 1.5°C. However, today it is an inefficient and expensive business. This project will apply generative machine learning to the design of novel metal-organic frameworks (MOFs) to optimize low-cost CO removal.2 air and other dilute gas streams.
An assessment of liquid metal catalyzed CO2 Reduction
Michael D. Dickey, State of North Carolina; Kourosh Kalantar-Zadeh, University of New South Wales; Kali Frost, Bichlien Nguyen, Karin Strauss, and Jake Smith, Microsoft
CO2 The reduction process can be used to convert captured carbon into a storable form as well as to manufacture sustainable fuels and materials with lower environmental impacts. This project will evaluate liquid metal-based reduction processes, identifying benefits, pinch points and opportunities for improvement needed to achieve industry-relevant scales. It will lay the groundwork for improving catalysts and addressing scaling bottlenecks.
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 the 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 all modern devices, are among the most difficult to recycle. Vitrimers, a new class of polymers that can be recycled multiple times without significant change in material properties, present a promising alternative. This project will take advantage of advances in machine learning to select vitrimer formulations that withstand 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, the majority of which can be attributed to cement. The discovery of alternative cements is a promising way to reduce the environmental impacts of 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 to understand 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 study 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 estimation from observational data through intervention analysis. Ambitiously, it will enhance the usefulness of causal ML approaches for climate risk assessment by enabling the interpretation and assessment of the likelihood and potential consequences of specific interventions.
Improving sub-seasonal forecasts 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 wildfires, and prepare for droughts and other extreme weather events. However, skillful predictions for the sub-seasonal pattern are lacking due to a complex reliance on local weather patterns, global climate variables, and the chaotic nature of weather patterns. To address this need, this project will use machine learning to adaptively correct biases in traditional physics-based forecasts and adaptively combine forecasts from disparate models.
Get progress updates and new resources to accelerate sustainability science research >