How Grace Algeo is Building Smarter Systems for Modern Farming

By Quinn Kennerly

Imagine a greenhouse where artificial intelligence helps guide daily decisions, from climate control to crop care. Growers use environmental sensors, data-driven analytics and precision modeling to create an environment that keeps plants thriving.

This is what Grace Algeo envisions for the future of controlled environment agriculture, or CEA. CEA encapsulates using technology to grow crops indoors, be it greenhouses, vertical farms, warehouses or any space that allows for year-round growth.

As a master’s student in biological systems engineering at the University of California, Davis, Algeo conducts research focused on forecasting greenhouse behavior using Long Short-Term Memory, or LSTM, models, a type of machine learning model designed to spot patterns and make predictions over time.

In the Controlled Environment Engineering Lab, led by Assistant Professor of Biological and Agricultural Engineering Shamim Ahamed, Algeo trains LSTM models on multivariate climate and crop data. She then uses them to create predictive tools that can anticipate plant water demand, climate patterns and yield forecasts in highly dynamic greenhouse systems.