A small-scale shared experimental smart farm simulation platform
Our goal is to build a small-scale, campus-shared, and cloud-mode Experimental Smart Farm Simulation (ESFSim) platform. This platform, informed by real-world data collected from the UC Merced Experimental Smart Farm (ESF), will allow researchers to more quickly run experiments and gather data. Because many experiments can be run in parallel within a simulation, researchers can pursue ideas that may not be feasible to test on a real farm due to cost or scale. Of course, bespoke digital simulations have drawbacks of their own. They are initially costly and difficult to build. By creating a common foundation, more researchers will be able to make use of compute resources by lowering the effort required to deploy simulator-based experiments. They can instead focus their efforts on customizing the platform to suit their specific needs and performing directly productive research activities. Such efforts can be reused by other researchers to further lessen the effort required to use the system.
ESFSim will enable the study of short- and long-term feedback loops affecting both farming and sustainability practices. Key to this approach is the ability to generate and access heterogeneous data at different spatio-temporal scales. Real-world data from the smart farm will be accessible via edge devices.
The land at UC Merced's smart farm is prepared for planting.
UC Merced is building a 45-acre Experimental Smart Farm (ESF) from scratch to enable collaborative, inter-disciplinary research between academics and stakeholders interested in automation, environmental sustainability, data processing, and worker health and safety in farming for specialty crops (e.g., vegetables, fruits, tree nuts). The ESF will support a broad range of Cyber-Physical Systems (CPS) and CPS-enabled convergent research at the intersection of agricultural technology, environmental sustainability, and the future of work. However, performing research activities on a real farm is expensive, time-consuming, personnel-intensive, and often requires waiting long periods of time for results. A physical farm is also a limited resource that must be shared between users.
Good datasets are at the core of ESFSim efforts. Widely used Ag datasets will be available through ESFSim, as well as multiple cutting-edge datasets
Modern AI and machine learning techniques have many potential benefits for Ag. ESFSim aims to support such tasks by making it easy for researchers to access to HPC infrastructure.
The ESFSim system will provide researchers with the tools they need to create and store datasets, perform AI training, and run smart farm simulations.
All tools will be available through a web portal. User guides and training will be available so that ESFSim can be quickly adopted and used.
We are too! Contact xiaoyi (dot) lu (at) ucmerced.edu, or click the button below to get more information about the project and how you can get involved.
This work is funded by the F3 Farms Food Future program at the University of California, Merced