Abstract
The reduced Tomgro model is one of the popular biophysical models, which can reflect the actual growth process and model the yields of tomato-based on environmental parameters in a greenhouse. It is commonly integrated with the greenhouse environmental control system for optimally controlling environmental parameters to maximize the tomato growth/yields under acceptable energy consumption. In this work, we compare three mainstream evolutionary algorithms (genetic algorithm (GA), particle swarm optimization (PSO), and differential evolutionary (DE)) for calibrating the reduced Tomgro model, to model the tomato mature fruit dry matter (DM) weights. Different evolutionary algorithms have been applied to calibrate 14 key parameters of the reduced Tomgro model. And the performance of the calibrated Tomgro models based on different evolutionary algorithms has been evaluated based on three datasets obtained from a real tomato grower, with each dataset containing greenhouse environmental parameters (e.g., carbon dioxide concentration, temperature, photosynthetically active radiation (PAR)) and tomato yield information at a particular greenhouse for one year. Multiple metrics (root mean square errors (RMSEs), relative root mean square errors (r-RSMEs), and mean average errors (MAEs)) between actual DM weights and model-simulated ones for all three datasets, are used to validate the performance of calibrated reduced Tomgro model.
Highlights
Nowadays, greenhouses are preferred by many tomato growers
The reduced state-variable tomato model [9] is used for the simulation of tomato growth on the basis of three inputs that are measured inside a greenhouse environment: the photosynthetically active radiation in [mmol/m2/s] or photosynthetically active radiation (PAR) (W ∕m2), air temperature [◦C] and CO2 concentration [ppm]
The evaluations of different evolutionary algorithms for calibrating the reduced Tomgro model are presented
Summary
Greenhouses are preferred by many tomato growers. Compared with the field growing, growing tomatoes in a greenhouse can extent the tomato growing season, protect tomatoes against temperature and weather changes as well as provide tomatoes with a safe growing environment [15]. With the development of modern techniques, the environmental parameters (e.g., carbon dioxide concentration, temperature, photosynthetically active radiation (PAR)) in a greenhouse nowadays can be controlled to guarantee tomatoes to grow at the most appropriate environmental conditions [18,23]. A variety of models have been developed for crop yield modelling, which is divided into two categories: data-driven model and explanatory biophysical model as in [14]. While the explanatory model describes the relationship between greenhouse environmental factors (e.g., CO2, temperature, etc.) and crop morphological development based on ordinary differential equations (ODEs), for modelling the crop yield. Compared with the data-driven model, a biophysical model is more practical to reflect the actual growth process of crops, which is commonly integrated in the greenhouse environmental control system for optimizing the tomato yields [24]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
