Using the computing capacity of plants to understand their physiology and stress response (INTELLIPLANTS)

The use of nonlinear dynamical systems (such as compliant robot morphologies) as physical computing systems is widely spread in the domain of machine learning and robotics. Often, physical reservoir computing is used as a theoretical framework. In this project we have applied the physical reservoir computing for the first time to plants. This allows us to better understand the dynamic responses of plants to their variable environment and ultimately develop a system where the plant itself tells us when growing conditions are less than optimal.

The INTELLIPLANTS project is now finished.  Using image analysis techniques and a wide range of contact sensors, we were able to capture the response of plants to varying environmental conditions. This dynamic information on plant responses will then be employed to characterize the nonlinear dynamical properties of the plant. Using these, we have conceived a general framework, based on the physical reservoir computing concept, that makes it possible to analyze the computational processing capacity of plants. 

The framework offers a means to validate the information processing capabilities or "intelligence" of plants. Furthermore, this improves our knowledge of the complex plant responses to variable environmental factors like temperature, light and water. Ultimately, this should offer a means to improve management of crop growth e.g., climate monitoring, pathogen detection, greenhouse climate control and irrigation scheduling.