Feng Tao 陶鳳
Assistant Professor in Climate AI at the Pennsylvania State University
Bio
I am an Assistant Professor in Climate AI at College of Information Science and Technology and Institute of Energy and the Environment (co-hire) at the Pennsylvania State University. I work at the interface of soil carbon science, mechanistic modelling, and AI to understand the global soil carbon cycle and its response to climate change. Before joining Penn State, I was a Schmidt AI for Science Postdoctoral Fellow at Cornell University, working with Dean Ben Houlton on enhanced rock weathering. I obtained my Ph.D. in Ecology from Tsinghua University in 2023, working with Prof Yiqi Luo (Cornell), and Prof Xiaomeng Huang (Tsinghua) on soil organic carbon and AI, and B.S. in Environmental Science from Sun Yat-sen University in 2018.
I am actively seeking one postdoc, PhD students (starting from 2026 Spring or Fall), master/undergraduate interns, and visiting scholars to join my lab. Potential projects are listed in Opportunities. If you are interested in, please feel free to contact me via Email with your CV.
Research Vision
(To know more about my current research, check out this recorded video at Climate Change AI Seminar)
The world must create new, science-backed solutions to reduce carbon dioxide emissions and scalable carbon dioxide removal (CDR) approaches, which are essential to averting the most perilous climate impacts this century. The global soil system, with its potential to sequester billions of tons of carbon as organic or inorganic forms over durable timescales, represents a promising nature-based climate solution.
However, key scientific questions regarding the soil carbon cycle—such as the mechanisms of formation, persistence, and the response of soil organic and inorganic carbon to environmental changes and land management—remain unresolved. This gap in mechanistic and quantitative understanding has impeded transferring knowledge from academia to policymaking and industry to develop and implement verifiable methods for soil carbon sequestration. The need for science-backed, data-verified solutions to promote soil carbon storage is more pressing than ever.
My research, grounded in a proven track record of success and innovation in mechanistic modeling, big data analytics, and AI, seeks to fundamentally advance soil carbon sciences and management toward climate mitigation solutions. By concentrating on the two giants in the global soil system—soil organic carbon and soil inorganic carbon—my work explores viable giga-ton CDR solutions that can bend the warming curve. I have developed and continue to create novel process-guided AI tools (Example I) for scientific discoveries in the soil carbon cycle and supporting verifiable decarbonization methods such as enhanced rock weathering. The scientific outcomes of my research have the potential to revolutionize approaches in promoting soil carbon storage (Example II), providing a viable and verifiable pathway towards immense, high-quality, and tractable soil carbon sequestration.
Selected Publications
Tao, F., B. Z. Houlton, Y. Huang, Y.-P. Wang, S. Manzoni, B. Ahrens, U. Mishra, L. Jiang, X. Huang, and Y. Luo. 2024. Convergence in simulating global soil organic carbon by structurally different models after data assimilation, Global Change Biology, 30(5), e17297.
Huang, Y., X. Song, Y.-P. Wang, J. G. Canadell, Y. Luo, P. Ciais, A. Chen, S. Hong, Y. Wang, F. Tao, W. Li, Y. Xu, R. Mirzaeitalarposhti, H. Elbasiouny, I. Savin, D. Shchepashchenko, R. A. V. Rossel, D. S. Goll, J. Chang, B. Z. Houlton, H. Wu, F. Yang, X. Feng, Y. Chen, Y. Liu, S. Niu, and G.-L. Zhang. 2024. Size, distribution, and vulnerability of the global soil inorganic carbon. Science 384:233-239.
Tao, F., Y. Huang, B. A. Hungate, S. Manzoni, S. D. Frey, M. W. I. Schmidt, M. Reichstein, N. Carvalhais, P. Ciais, L. Jiang, J. Lehmann, Y.-P. Wang, B. Z. Houlton, B. Ahrens, U. Mishra, G. Hugelius, T. D. Hocking, X. Lu, Z. Shi, K. Viatkin, R. Vargas, Y. Yigini, C. Omuto, A. A. Malik, G. Peralta, R. Cuevas-Corona, L. E. Di Paolo, I. Luotto, C. Liao, Y.-S. Liang, V. S. Saynes, X. Huang, and Y. Luo. 2023. Microbial carbon use efficiency promotes global soil carbon storage. Nature 618, 981-985 (2023).
Tao, F., and Y. Luo. PROcess-guided deep learning and DAta-driven modelling (PRODA). In Y. Luo & B. Smith (Eds.), Land Carbon Cycle Modeling: Matrix Approach, Data Assimilation, and Ecological Forecasting. Taylor and Francis.