To feed the world?s growing population, food production must increase by an estimated 70% by 2050. Achieving food security by minimizing supply fluctuations and adjusting to the growth in food demand presents many challenges that will require major adjustments in current agricultural practices, most importantly in controlled-environment agriculture (CEA). Current CEA facilities consume substantial energy, hence making this technology energy-hungry and preventing their wider adoption. This interdisciplinary CPS project intends to build a networked CPS together with advanced data analytics and integrated renewable energy and energy storage aiming at reducing the dependence on utility grid and hence energy cost, while optimizing crop production efficiency. This project led by Clemson University brings together a team from agricultural sciences, control systems and computing/data science to create a networked system for CEA, with the goal of improving crop growth and yield while minimizing the energy cost; it enables self-adaptation and autonomy of CEA and advances the frontier of core CPS research. The research results will be integrated into the undergraduate and graduate curriculum development at the institutions involved with students trained on interdisciplinary research and education. The PIs? partnership with K-12 schools and CEA growers will be leveraged to educate students, mostly from underrepresented groups, and practicing engineers on the development and deployment of CPS technologies in CEAs.<br/><br/>This project builds a novel system for multi-scale, cooperative and autonomous sensing, control and renewable energy management to address several fundamental challenges of complex CEA systems, a key step towards fully autonomous and net-zero-energy CEA. The hierarchical structure of this project exploits inter-dependencies of crop physiology, energy systems and environment to advance research in CEA systems aiming at enhancing their resilience. This project outcomes enable a paradigm shift in a number of areas including: (1) integration of photosynthesis models with real-time biophysical measurements for optimizing environmental parameters; (2) automatic monitoring of the crop growth and environmental conditions using advanced AI-guided image and sensor data analytics; (3) automated robot-assisted data collection using novel control approaches for optimal distribution of mobile manipulators over large CEAs with safety guarantees; (4) devising novel stochastic control tools to manipulate environmental parameters to facilitate photosynthesis for each crop species and growth stage. The tight interaction of controllable physical systems with autonomous biological systems and the environment provides an intriguing problem space that can be also useful for a broad range of other cyber-physical systems.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.