Deep learning is known as a promising multifunctional tool for processing images and other big data. By assimilating large amounts of heterogeneous data, deep-learning technology provides reliable prediction results for complex and uncertain phenomena. Recently, it has been increasingly used by horticultural researchers to make sense of the large datasets produced during planting and postharvest processes. In this paper, we provided a brief introduction to deep-learning approaches and reviewed 71 recent research works in which deep-learning technologies were applied in the horticultural domain for variety recognition, yield estimation, quality detection, stress phenotyping detection, growth monitoring, and other tasks. We described in detail the application scenarios reported in the relevant literature, along with the applied models and frameworks, the used data, and the overall performance results. Finally, we discussed the current challenges and future trends of deep learning in horticultural research. The aim of this review is to assist researchers and provide guidance for them to fully understand the strengths and possible weaknesses when applying deep learning in horticultural sectors. We also hope that this review will encourage researchers to explore some significant examples of deep learning in horticultural science and will promote the advancement of intelligent horticulture.

No abstract

Light is essential for plant growth. Light intensity, photoperiod, and light quality all affect plant morphology and physiology. Compared to light intensity, photoperiod, little is known about the effects of different monochromatic lights on crop species. To investigate how different lighting conditions influence crops with heterogeneous colors in leaves, we examined photosynthetic characteristics and quality (regarding edibility and nutrition) of purple cabbage under different combinations of lights. Eight different treatments were applied including monochromic red (R), monochromic blue (B), monochromic yellow (Y), monochromic green (G), and the combination of red and blue (3/1, RB), red/blue/yellow (3/1/1, RBY), red/blue/green (3/1/1,RBG), and white light as the control. Our results indicate that RBY (3/1/1) treatment promotes the PSII activity of purple cabbage, resulting in improved light energy utilization. By contrast, both G and Y lights alone have inhibitory effect on the PSII activity of purple cabbage. In addition, RBY (3/1/1) significantly boosts the anthocyanin and flavonoids content compared with other treatments. Although we detected highest soluble protein and vitamin C content under B treatment (increased by 30.0 and 14.3% compared with the control, respectively), RBY (3/1/1) appeared to be the second-best lighting condition (with soluble protein and vitamin C content increased by 8.6 and 4.1%, respectively compared with the control). Thus we prove that the addition of yellow light to the traditional combination of red/blue lighting conditions is beneficial to synthesizing photosynthetic pigments and enables superior outcome of purple cabbage growth. Our results indicate that the growth and nutritional quality of purple cabbage are greatly enhanced under RBY (3/1/1) light, and suggest that strategical management of lighting conditions holds promise in maximizing the economic efficiency of plant production and food quality of vegetables grown in controlled environments.

The purpose of this study was to establish an extraction method for the kinsenoside compound from the whole plant Anoectochilus roxburghii. Ultrasound assisted extraction (UAE) and Ultra-high performance liquid chromatography (UPLC) method were used to extract and determine the content of kinsenoside, while response surface method (RSM) was used to optimize the extraction process. The best possible range for methanol concentration (0–100%), the liquid-solid ratio (5:1–30:1 mL/g), ultrasonic power (240–540 W), duration of ultrasound (10–50 min), ultrasonic temperature (10–60 °C), and the number of extractions (1–4) were obtained according to the single factor experiments. Then, using the Box-Behnken design (BBD) of response surface analysis, the optimum extraction conditions were obtained with 16.33% methanol concentration, the liquid-solid ratio of 10.83:1 mL/g and 35.00 °C ultrasonic temperature. Under these conditions, kinsenoside extraction yield reached 32.24% dry weight. The best conditions were applied to determine the kinsenoside content in seven different cultivation ages in Anoectochilus roxburghii.

Spectral imaging is a promising technique for detecting the quality of rice seeds. However, the high cost of the system has limited it to more practical applications. The study was aimed to develop a low-cost narrow band multispectral imaging system for detecting rice false smut (RFS) in rice seeds. Two different cultivars of rice seeds were artificially inoculated with RFS. Results have demonstrated that spectral features at 460, 520, 660, 740, 850, and 940 nm were well linked to the RFS. It achieved an overall accuracy of 98.7% with a false negative rate of 3.2% for Zheliang, and 91.4% with 6.7% for Xiushui, respectively, using the least squares-support vector machine. Moreover, the robustness of the model was validated through transferring the model of Zheliang to Xiushui with the overall accuracy of 90.3% and false negative rate of 7.8%. These results demonstrate the feasibility of the developed system for RFS identification with a low detecting cost.