Synergizing Crop Growth Models and Digital Phenotyping: A Cost-Effective IoT-Based Sensing Network Design

Sensing devices (eg multispectral) coupled with advanced analysis methods (eg AI) autonomously collect and process in-situ phenotype data (ie observable plant traits resulting from the performance of a genotype in a specific environment). However, this approach faces limitations, namely the low integration of phenotype data in decision support systems for leveraging agricultural practices and predicting plant behaviour amid complex genotype, environment and management interactions (GEM). To enhance the role of digital phenotyping in supporting Precision Agriculture, this paper proposes a sensing network based on IoT. The developed system comprises three modules: data collection–stationary and robotics-assisted sensors to gather phenotype data; communication–physical data connections between devices and virtual connections over the internet transferring the data to a centralised database–designed to receive, store, and process data. In the database, several processes occur simultaneously, namely data visualisation to confirm the correct sensors and data stream functioning. Also, phenotype data will be merged with a crop growth model (CGM), decreasing the simulation uncertainty and obtaining, in advance, insights about plant behaviour considering GEM conditions. To assess the performance of the proposed network, a greenhouse was equipped with several sensors that collect plant, environment and soil data (eg leaves number, air temperature, soil moisture). Lettuce plants were induced to nitrogen stress to characterise physiologic plant shifts and evaluate the reliability of CGM predictions. The proposed network can provide real-time-causal support toward advanced agricultural practices, evolving from a data-driven approach to an integrative framework where context (GEM) drives advanced decision-making.