About

Fengqi You is the Roxanne E. and Michael J. Zak Professor in Energy Systems Engineering at Cornell University. He holds affiliations with multiple Graduate Fields at Cornell, including Chemical Engineering, Computer Science, Electrical and Computer Engineering, Operations Research and Information Engineering, Systems Engineering, Mechanical Engineering, Civil and Environmental Engineering, and Applied Mathematics. Within Cornell, he serves as the Chair of Ph.D. Studies in Systems Engineering, Co-Director of the Cornell University AI for Science Institute (CUAISci), Co-Director of the Cornell Institute for Digital Agriculture (CIDA), and Director of the Cornell AI for Sustainability Initiative (CAISI). His research focuses on fundamental theories and methods of systems engineering, with applications in materials informatics, smart manufacturing, digital agriculture, energy systems, and sustainability. Fengqi has authored over 300 refereed articles in prominent journals and his work has been highlighted in major scientific outlets and covered by leading media outlets worldwide. He has received over 25 major national and international awards from professional organizations such as AIChE, ACS, RSC, ASEE, and AACC, including prestigious recognitions like the NSF CAREER Award, AIChE Environmental Division Early Career Award, and the Lawrence K. Cecil Award in Environmental Chemical Engineering.

Research topics

• Computer Science
• Artificial Intelligence
• Engineering
• Mathematical optimization
• Mathematics
• Ecology
• Operations management
• Process engineering
• Systems engineering
• Meteorology
• Data science
• Environmental science
• Geography
• Management science

Selected publications

• High-Fidelity Full-Sky Video Prediction for Photovoltaic Ramp Event Forecasting

  ArXiv.org · 2026-05-04

  articleOpen accessSenior author

  Accurate ultra-short-term forecasting of photovoltaic (PV) ramp events is essential for maintaining grid stability in solar-integrated power systems, particularly under rapidly changing cloud conditions. This paper presents a generative forecasting framework that integrates a future sky video prediction model (PhyDiffNet) with a ramp aware PV output forecasting model (RaPVFormer). Based on the relatively slow yet chaotic dynamics of cloud motion, the system forecasts ramp events up to 16 minutes in advance at a 1-minute resolution by capturing fine-grained spatiotemporal cloud patterns and generating high-fidelity full-sky video frames. Interpretability is enhanced through attention visualization, highlighting cloud occlusion regions that significantly influence irradiance variability. Supported by extensive quantitative evaluation, the proposed framework demonstrates state-of-the-art performance in both full-sky video prediction and PV output forecasting. It delivers consistent improvements in structural, perceptual, and temporal video quality, along with a 10% increase in Critical Success Index (CSI) for PV ramp detection. These results demonstrate the capability of AI driven multimodal sensing for ultra short term solar forecasting, supporting more reliable renewable integration and potentially reducing dependence on reserve capacity.

  PublisherOA PDF

• The synergy of geometric tolerance factor and machine learning in discovering stable materials

  Journal of Materials Informatics · 2026-01-12

  articleOpen accessSenior author

  Assessing stability remains a fundamental prerequisite for deploying materials across a wide range of applications, including batteries, catalysts, and photovoltaics. However, first-principles stability checks such as phonon dispersion and energy above hull calculations typically require days to weeks of computing time per composition, creating a critical bottleneck for truly high-throughput discovery. In this Perspective, we highlight the underutilized potential of geometric tolerance factors (T<sub>f</sub>) as lightweight yet informative indicators for rapid stability assessment. First, we review the T<sub>f</sub> developed for representative materials systems, including perovskites, spinels, and garnets, and analyze recent cases where such indicators have been integrated into AI-driven materials discovery. Then, we identify key open challenges in designing T<sub>f</sub> that are both accurate and generalizable, as well as in effectively incorporating them into AI frameworks. The potential solutions, including active learning for multi-composition structure, electron density profile-based learning for ionic radii estimation, and diffusion model for thermodynamic and kinetic stability, are proposed to address these challenges. The synergy between T<sub>f</sub>-based heuristics and advanced AI models has the potential to triage vast compositional spaces before committing to expensive first-principles stability validation, thereby enabling broader innovations in materials design and deployment.

  PublisherDOI

• Biochar from Livestock Waste: A Pathway to Sustainable Agriculture and Climate Change Mitigation

  Environmental Science & Technology · 2026-01-13 · 1 citations

  articleSenior authorCorresponding

  Livestock manure is not only a major global source of greenhouse gases from agriculture but also an important source of nutrients for crop production. Judicious management of livestock manure should deliver an effective way to both promote crop growth and mitigate greenhouse gas emissions. Here, we show using the global change analysis model (GCAM) integrated assessment model augmented with a pyrolysis module (GCAM-pyrolysis) that biochar production from global livestock manure may intensify agricultural systems through a 10% (median, 3–27% CE) increase in crop yields. GCAM-pyrolysis estimates that in 2050 widespread pyrolysis of livestock manures will cause an expansion of 415,000 km2 of cropland for food production (median, 376,000–473,000 km2 CE) compared to the reference scenario, at the expense of forests, pastures, and crops purposely grown to produce bioenergy (corn, sugar, palm fruit, oil crops), to produce an additional 5.1 Pcal (median, 3.2–6.7 Pcal CE) of food. Biochar presents significant opportunities in allowing productive land use change and increased crop production while increasing carbon dioxide removal and reducing greenhouse gas emissions. However, widespread adoption of pyrolysis may require food equity and land conservation regulations to mitigate its undesirable effects, such as an estimated increase in staple food prices in certain regions.

  PublisherDOI

• Mitigating lead toxicity towards safer commercialization of perovskite solar cells

  Nature Energy · 2026-04-24

  article
  PublisherDOI

• High-Fidelity Full-Sky Video Prediction for Photovoltaic Ramp Event Forecasting

  arXiv (Cornell University) · 2026-05-04

  preprintOpen accessSenior author

  Accurate ultra-short-term forecasting of photovoltaic (PV) ramp events is essential for maintaining grid stability in solar-integrated power systems, particularly under rapidly changing cloud conditions. This paper presents a generative forecasting framework that integrates a future sky video prediction model (PhyDiffNet) with a ramp aware PV output forecasting model (RaPVFormer). Based on the relatively slow yet chaotic dynamics of cloud motion, the system forecasts ramp events up to 16 minutes in advance at a 1-minute resolution by capturing fine-grained spatiotemporal cloud patterns and generating high-fidelity full-sky video frames. Interpretability is enhanced through attention visualization, highlighting cloud occlusion regions that significantly influence irradiance variability. Supported by extensive quantitative evaluation, the proposed framework demonstrates state-of-the-art performance in both full-sky video prediction and PV output forecasting. It delivers consistent improvements in structural, perceptual, and temporal video quality, along with a 10% increase in Critical Success Index (CSI) for PV ramp detection. These results demonstrate the capability of AI driven multimodal sensing for ultra short term solar forecasting, supporting more reliable renewable integration and potentially reducing dependence on reserve capacity.

  PublisherDOI

• Ultrahigh‐Efficiency and Long‐Calendar‐Life Aqueous Cadmium Metal Batteries Under Extremely Harsh Conditions

  Angewandte Chemie · 2026-05-11

  article

  ABSTRACT Aqueous multivalent metal batteries (AMMBs) hold great promise for non‐flammable, cost‐effective, and scalable energy storage. However, the parasitic hydrogen evolution reaction (HER) has severely plagued the metal plating efficiency and calendar life, particularly under realistic stress conditions, including low current densities, extended storage periods, and harsh temperatures. Herein, we leverage the inherent HER resistance of cadmium metal and the water‐confining solvation structures of concentrated electrolytes to synergistically tackle the HER challenge, and we successfully demonstrated ultrahigh‐efficiency and long‐calendar‐life cadmium metal batteries under strict conditions (0.1 mA cm −2 , 99.75% efficiency, 21.4 months’ life). Even under extreme conditions, such as ultralow current (0.01 mA cm −2 ), long rest periods (up to 60 days), and wide temperature ranges (−50°C to +80°C), Cd maintains a high efficiency of 90%–99.9%. In stark contrast, zinc suffers from drastic performance degradation and loses 27%–73% efficiency. The superior performance is correlated with the distinct solvation structure in the concentrated electrolyte, which transforms the hydration form of Cd 2+ cations and strengthens water molecules via a strong cation‐coordination effect. Our work establishes a new benchmark for AMMBs and highlights the decisive role of electrode selection and electrolyte design in advancing AMMB performance.

  PublisherDOI

• Ultrahigh‐Efficiency and Long‐Calendar‐Life Aqueous Cadmium Metal Batteries Under Extremely Harsh Conditions

  Angewandte Chemie International Edition · 2026-05-11

  articleCorresponding

  ABSTRACT Aqueous multivalent metal batteries (AMMBs) hold great promise for non‐flammable, cost‐effective, and scalable energy storage. However, the parasitic hydrogen evolution reaction (HER) has severely plagued the metal plating efficiency and calendar life, particularly under realistic stress conditions, including low current densities, extended storage periods, and harsh temperatures. Herein, we leverage the inherent HER resistance of cadmium metal and the water‐confining solvation structures of concentrated electrolytes to synergistically tackle the HER challenge, and we successfully demonstrated ultrahigh‐efficiency and long‐calendar‐life cadmium metal batteries under strict conditions (0.1 mA cm −2 , 99.75% efficiency, 21.4 months’ life). Even under extreme conditions, such as ultralow current (0.01 mA cm −2 ), long rest periods (up to 60 days), and wide temperature ranges (−50°C to +80°C), Cd maintains a high efficiency of 90%–99.9%. In stark contrast, zinc suffers from drastic performance degradation and loses 27%–73% efficiency. The superior performance is correlated with the distinct solvation structure in the concentrated electrolyte, which transforms the hydration form of Cd 2+ cations and strengthens water molecules via a strong cation‐coordination effect. Our work establishes a new benchmark for AMMBs and highlights the decisive role of electrode selection and electrolyte design in advancing AMMB performance.

  PublisherDOI

• A dynamic routing-guided interpretable framework for salt–solvent chemistry

  Nature Computational Science · 2026-02-19 · 1 citations

  articleSenior authorCorresponding
  PublisherDOI

• Comparative life cycle carbon footprints of buy online pick up in-store retail

  Transportation Research Part D Transport and Environment · 2026-02-24

  articleSenior authorCorresponding
  PublisherDOI

• Author response for "Machine Learning Pipelines for the Design of Solid-State Electrolytes"

  2025-11-09

  peer-reviewSenior author
  PublisherDOI

Recent grants

• CAREER: A Computational Framework for Multiscale Optimization of Sustainability for Process Supply Chains

  NSF · $512k · 2016–2022

• CAREER: A Computational Framework for Multiscale Optimization of Sustainability for Process Supply Chains

  NSF · $512k · 2016–2016

Frequent coauthors

• Chao Ning

  Shanghai Jiao Tong University

  34 shared

• Yunfei Chu

  34 shared

• Jian Gong

  33 shared

• Dajun Yue

  Northwestern University

  32 shared

• Akshay Ajagekar

  30 shared

• Jiyao Gao

  Cornell University

  29 shared

• Abdulelah S. Alshehri

  Cornell University

  27 shared

• Xueyu Tian

  Cornell University

  26 shared

Awards & honors

• NSF CAREER Award (2016)
• AIChE Environmental Division Early Career Award (2017)
• AIChE Research Excellence in Sustainable Engineering Award (…
• Computing and Systems Technology (CAST) Outstanding Young Re…
• Cornell Engineering Research Excellence Award (2018)