Search

Abstract CO2 enrichment is an essential environmental control technology due to its significantly enhancing effect on crop production capacity. Despite being a key energy consumer in protected agriculture (i.e. greenhouse systems), CO2 enrichment remains at a low energy use efficiency level, highlighting the need for developing more energy-efficiency strategies for CO2 enrichment. Therefore, this study employed the computational fluid dynamics (CFD) simulation method to replicate the CO2 diffusion process resulting from CO2 enrichment in three commercial strawberry greenhouses with varying geometric characteristics. Based on the CFD-simulated CO2 concentration distributions, the leaf photosynthetic rate was calculated using a mathematical model group. The CO2 enrichment efficiency was then analysed by calculating the ratio of increased photosynthesis across the cultivation area to the amount of energy (in CO2 equivalent) used. The efficiency peaked when the average CO2 concentration was approximately 500 μmol mol−1, thereby providing guidance for determining the target concentration of CO2 enrichment in production. Although this study is limited as the CFD simulation only considered a typical short-period CO2 enrichment event, future research will provide a broader analysis by considering changes throughout the day.

This paper proposes a new approach to visualizing spatial variation of plant status in a tomato greenhouse based on farm work information operated by laborers. Farm work information consists of a farm laborer’s position and action. A farm laborer’s position is estimated based on radio wave strength measured by using a smartphone carried by the farm laborer and Bluetooth beacons placed in the greenhouse. A farm laborer’s action is recognized based on motion data measured by using smartwatches worn on both wrists of the farm laborer. As experiment, harvesting information operated by one farm laborer in a part of a tomato greenhouse is obtained, and the spatial distribution of yields in the experimental field, called a harvesting map, is visualized. The mean absolute error of the number of harvested tomatoes in each small section of the experimental field is 0.35. An interview with the farm manager shows that the harvesting map is useful for intuitively grasping the states of the greenhouse.

As robotic systems become increasingly integrated into plant phenotyping processes, the quality of images captured plays an increasingly crucial role in accurate data collection and analysis. Here we address the challenge of assessing and enhancing image quality in the context of plant phenotyping robot using a pan-tilt-zoom camera. We present a data-driven approach using machine learning, specifically the Random Forest classifier, to classify both blurred and sharp images. Our method involves feature extraction, data preprocessing, hyperparameter tuning, and cross-validation. The resulting model demonstrates promising performance as indicated by its accuracy, precision, recall, area under the curve (AUC), and feature importance analysis. Notably, our results support a highly accurate classifier, achieving a correct classification rate of 95% for sharp images and 92% for blurred ones, a receiver operating characteristic curve with an AUC of 0.93, and a precision-recall curve with an average precision of 0.91. Shapley Additive Explanations analysis identifies "edge density" and "mean gradient magnitude" as influential to the classifier, offering valuable insights for future feature engineering and model refinement. The classifier has a short inference time (2.8 s) on a Raspberry Pi 4B computer, both improving the quality of captured images and automatically eliminating blurred images. By enhancing image quality assessment, this research improves data reliability and the overall effectiveness of plant phenotyping robots. We discuss the implications of these findings and their practical relevance and suggest directions for future research. [ABSTRACT FROM AUTHOR]

Supplemental lighting techniques in greenhouses can increase plant growth and yield but require substantial amounts of energy. We proposed the use of energy-saving supplemental lighting, which was applied during rapid fruit development when the transport of photosynthetic products into the fruit was active. We measured the physiological responses (photosynthesis, growth, yield) of the strawberry plants with single fruit truss, wherein the following 3 treatments were made: plants were cultivated with no supplemental lighting (control), supplemental lighting throughout the experimental period (normal-light), and supplemental lighting during rapid fruit development (short-light). The period of rapid fruit development corresponded to 33% of the experimental period, and the cumulative light intensity for the short-light treatment was half of that for the normal-light treatment, and twice that of the control treatment. Consequently, the leaf area and dry weight of the plant body were significantly increased following normal-light and short-light treatments compared with the control treatment. The yield for the short-light treatment was also increased and nearly equal to that of the normal-light treatment but no significance to the control treatment. However, the energy use efficiency of the short-light was improved 1.5-fold compared to the normal-light treatment. Thus, shortening the period of supplemental lighting in accordance with the characteristics of fruit development is potentially effective. [ABSTRACT FROM AUTHOR]