On precisely relating the growth of Phalaenopsis leaves to greenhouse environmental factors by using an IoT-based monitoring system

Abstract

Traditional methods for monitoring the environmental factors of a greenhouse and the growth of Phalaenopsis orchids often suffer from low spatiotemporal resolution, high labor-intensity, requiring much time, and a lack of automation and synchronization. To solve these problems, this study develops an Internet of Things (IoT)-based system to monitor the environmental factors of an orchid greenhouse and the growth status of Phalaenopsis at the same time. The whole system consists of an IoT-based environmental monitoring system and an IoT-based wireless imaging platform. An image processing algorithm based on the Canny edge detection method, the seeded region growing (SRG) method, and the mathematical morphology is also developed to estimate the leaf area of Phalaenopsis. The long-term experiments with respect to four different environmental conditions for cultivating Phalaenopsis are conducted. The statistical analysis methods, including the one-way ANOVA, two-way ANOVA, and Games-Howell test, are performed to examine the relation between the growth of Phalaenopsis leaves and the environmental factors in the greenhouse. The optimal cultivation conditions for Phalaenopsis can be easily identified. The experimental results indicate that the daily average growth rate of the leaf area of Phalaenopsis is approximately 79.41mm2/day when the temperature and relative humidity in the greenhouse are controlled at 28.83±2.58 (°C) and 71.81±8.88 (%RH), respectively. The proposed system shows a great potential to provide quantitative information with high spatiotemporal resolution to floral farmers. It is promisingly expected that the proposed system will effectively contribute to updating farming strategies for Phalaenopsis in the future.