Search

Greenhouse cultivation is one of the current strategies to address the challenges of food production, sustainability, and food quality. Similarly, the use of technological tools to automate greenhouse environments through a set of sensors and actuators allows for the control and improvement of processes within this environment. This document presents data collected from the sensors and actuators of two identical greenhouse environments, one with the cultivation of stringless blue lake beans and the other without cultivation. The aim is that this dataset will provide a broader characterization of the behavior of climatic variables inside greenhouse environments and how they are impacted by control actions, subsequently contributing to the development of new research on implementations of or improvements to control, supervision, management, and automation actions in greenhouse environments. [ABSTRACT FROM AUTHOR]

This study investigated the interoperability of a tomato fruit detection model trained using nighttime images from two greenhouses. The goal was to evaluate the performance of the models in different environmets, including different facilities, cultivation methods, and imaging times. An innovative imaging approach is introduced to eliminate the background, highlight the target plants, and test the adaptability of the model under diverse conditions. The results demonstrate that the tomato fruit detection accuracy improves when the domain of the training dataset contains the test environment. The quantitative results showed high interoperability, achieving an average accuracy (AP50) of 0.973 in the same greenhouse and a stable performance of 0.962 in another greenhouse. The imaging approach controlled the lighting conditions, effectively eliminating the domain-shift problem. However, training on a dataset with low diversity or inferring plant appearance images but not on the training dataset decreased the average accuracy to approximately 0.80, revealing the need for new approaches to overcome fruit occlusion. Importantly, these findings have practical implications for the application of automated tomato fruit set monitoring systems in greenhouses to enhance agricultural efficiency and productivity.

This study investigated the interoperability of a tomato fruit detection model trained using nighttime images from two greenhouses. The goal was to evaluate the performance of the models in different environmets, including different facilities, cultivation methods, and imaging times. An innovative imaging approach is introduced to eliminate the background, highlight the target plants, and test the adaptability of the model under diverse conditions. The results demonstrate that the tomato fruit detection accuracy improves when the domain of the training dataset contains the test environment. The quantitative results showed high interoperability, achieving an average accuracy (AP50) of 0.973 in the same greenhouse and a stable performance of 0.962 in another greenhouse. The imaging approach controlled the lighting conditions, effectively eliminating the domain-shift problem. However, training on a dataset with low diversity or inferring plant appearance images but not on the training dataset decreased the average accuracy to approximately 0.80, revealing the need for new approaches to overcome fruit occlusion. Importantly, these findings have practical implications for the application of automated tomato fruit set monitoring systems in greenhouses to enhance agricultural efficiency and productivity. [ABSTRACT FROM AUTHOR]

Accurate detection of muskmelon fruit ripeness is crucial to ensure fruit quality, optimize picking time, and enhance economic benefits. This study proposes an improved lightweight YOLO-RFEW model based on YOLOv8n, aiming to address the challenges of low efficiency in muskmelon fruit ripeness detection and the complexity of deploying a target detection model to a muskmelon picking robot. Firstly, the RFAConv replaces the Conv in the backbone part of YOLOv8n, allowing the network to focus more on regions with significant contributions in feature extraction. Secondly, the feature extraction and fusion capability are enhanced by improving the C2f module into a C2f-FE module based on FasterNet and an Efficient Multi-Scale attention (EMA) mechanism within the lightweight model. Finally, Weighted Intersection over Union (WIoU) is optimized as the loss function to improve target frame prediction capability and enhance target detection accuracy. The experimental results demonstrate that the YOLO-RFEW model achieves high accuracy, with precision, recall, F1 score, and mean Average Precision (mAP) values of 93.16%, 83.22%, 87.91%, and 90.82%, respectively. Moreover, it maintains a lightweight design and high efficiency with a model size of 4.75 MB and an inference time of 1.5 ms. Additionally, in the two types of maturity tests (M-u and M-r), APs of 87.70% and 93.94% are obtained, respectively, by the YOLO-RFEW model. Compared to YOLOv8n, significant improvements in detection accuracy have been achieved while reducing both model size and computational complexity using the proposed approach for muskmelon picking robots' real-time detection requirements. Furthermore, when compared to lightweight models such as YOLOv3-Tiny, YOLOv4-Tiny, YOLOv5s, YOLOv7-Tiny, YOLOv8s, and YOLOv8n, the YOLO-RFEW model demonstrates superior performance with only 28.55%, 22.42%, 24.50%, 40.56%, 22.12%, and 79.83% of their respective model sizes, respectively, while achieving the highest F1 score and mAP values among these seven models. The feasibility and effectiveness of our improved scheme are verified through comparisons between thermograms generated by YOLOv8n and YOLO-RFEW as well as detection images. In summary, the YOLO-RFEW model not only improves the accuracy rate of muskmelon ripeness detection but also successfully realizes the lightweight and efficient performance, which has important theoretical support and application value in the field of muskmelon picking robot development. [ABSTRACT FROM AUTHOR]

In order to solve the problem of low prediction accuracy of the existing greenhouse tomato growth model, a non-linear model of greenhouse tomato growth and development was established based on the basic characteristics of tomato physiology, and the environmental pa- rameters in the greenhouse were used as model variables. This model described the influence of environmental factors, such as temperature, humidity, soil temperature and soil moisture in the greenhouse on the growth rate of tomato. The model had good explanatory ability and high precision. First of all, various sensors were used to collect various environmental data of tomato growth in the greenhouse of Jilin City, Jilin Province. Then, the actual data of the tomato greenhouse was preliminarily processed, and then the KNN algorithm was used to supplement missing and abnormal data, and correlation analysis was carried out. Finally, based on the processed tomato crop growth data, we considered the real-time feedback of tomato crops to the greenhouse environment. Combining with the correlation, we used the SVM optimization algorithm to analyze the greenhouse tomato data of Jilin Economic Development Zone from 2020 to 2021. After simulation, the accuracy rates of SVM, LDA and LR were 0.904, 0.885 and 0.865, respectively. The results showed that SVM could better predict the growth changes of tomato. The establishment of the greenhouse tomato crop-environment interaction model laid a good foundation for the greenhouse environment prediction control. [ABSTRACT FROM AUTHOR]

This work aims to avoid the complex control process caused by complex coupling and serious interference of control variables in traditional greenhouse environmental control and achieve the adaptive control of agricultural greenhouse. This work studies smart agricultural greenhouses' adaptive control and supply chain management based on the intelligent fuzzy auxiliary cognitive system (IFACS). This work firstly expresses the intelligent fuzzy control theory and analyses data according to the fuzzy control set. Secondly, the adaptive control and supply chain management of the intelligent agricultural greenhouse are studied by using an intelligent fuzzy aided cognitive system. Finally, the light intensity and carbon dioxide content of the intelligent agricultural greenhouse are analysed; the temperature and humidity content of the intelligent agricultural greenhouse of the traditional control method and adaptive control are compared; the impact of carbon dioxide emissions on the environment under supply chain management is analysed. The research results indicate that the adaptive control of the intelligent agricultural greenhouse based on the IFACS can keep the greenhouse temperature within a specific range and reduce the impact of temperature on the development of agricultural greenhouses. The IFACS is effectively managed in the adaptive control of the intelligent agricultural greenhouse. From 2015 to 2020, the smart agricultural greenhouse supply chain management gradually reduced the content of greenhouse gas (GHG) emitted by the production and suppliers through the IFACS. The content of greenhouse gases emitted by product transporters did not change significantly, and the greenhouse gases emitted by non‐manufacturing suppliers gradually decreased. In 2020, supply chain GHG emission intensity decreased by 20% compared with 2015, and GHG emissions from product transportation also decreased by 6% compared with the previous year. This research has reference significance for the adaptive control of intelligent agricultural greenhouse by IFACS and the environmental control of agricultural greenhouse by supply chain management. [ABSTRACT FROM AUTHOR]

The precise control of a greenhouse environment is vital in production. Currently, environmental control in traditional greenhouse production relies on experience, making it challenging to accurately control it, leading to environmental stress, resource waste, and pollution. Hence, this paper proposes a decision-making greenhouse environment control strategy that employs an existing monitoring system and intelligent algorithms to enhance greenhouse productivity and reduce costs. Specifically, a model library is created based on machine learning algorithms, and an intelligent optimization algorithm is designed based on the Non-Dominated Sorting Genetic Algorithm III (NSGA-3) and an expert experience knowledge base. Then, optimal environmental decision-making solutions under different greenhouse environments are obtained by adjusting the greenhouse environmental parameters. Our method's effectiveness is verified through a simulated fertilization plan that was simulated for a real greenhouse tomato environment. The proposed optimization solution can reduce labor and time costs, enable accurate decision-making in the greenhouse environment, and enhance agricultural production efficiency. [ABSTRACT FROM AUTHOR]

In the temperate climate of South Korea, specific corn varieties are cultivated using plug trays. The cultivation process is initiated from February to March within greenhouse facilities, maintaining a temperature below 10 degrees Celsius. Following this, in April, seedlings are transplanted to enable an exceptionally early harvest for increased profitability. However, the subsequent elevation in indoor temperatures leads to seedling overgrowth. This study explores the effectiveness of three plant growth regulators—paclobutrazol, prohexadione-calcium, and diniconazole–on super sweet corn seedlings. Significantly, the application of prohexadione-calcium at 2 ppm during the first leaf stage substantially reduces seedling height and impedes the growth of both the first and second internodes. This impact extends to leaf-related traits, manifesting reductions in the area, length, and width of the third leaf. Furthermore, prohexadione-calcium induces a significant decrease in both fresh and dried shoot weight, while simultaneously augmenting root weight. This alteration results in a noteworthy shift in the root–shoot ratio, particularly at 2 ppm. Subsequent experiments have identified the optimal concentration of prohexadione-calcium at 15 ppm, effectively mitigating overgrowth in both hybrid and inbred corn varieties. These findings provide essential insights for practitioners seeking to efficiently manage corn seedling overgrowth. The study contributes to understanding the retardant effect of prohexadione-calcium on various morphological traits, offering practical applications for optimizing plant growth regulator concentrations in corn cultivation strategies. [ABSTRACT FROM AUTHOR]

In greenhouse management, maintaining optimal humidity is essential for promoting plant growth, including photosynthesis, and preventing diseases and pests. Addressing spatial variability requires sensor-based monitoring for informed decisions on humidification systems, particularly for small, and suspension-type dehumidifiers. This study aims to assess the impact of various layouts of small-sized suspension-type dehumidifiers on vertical, spatial, and temporal humidity variability, along with energy consumption in a greenhouse. During experiments in a 648 m³ (18 m × 6 m × 6 m) plastic greenhouse, dehumidifiers were placed at four different layouts: one at the center (Layout 1), one on each side (Layout 2), two units at the center facing opposite directions (Layout 3), and two units on one side facing the center (Layout 4). Temperature and humidity (TH) sensors were connected to a microcontroller, facilitating wireless data acquisition, storage, and remote monitoring. The actuator was controlled through a relay module, and current sensors monitored power consumption. Spatial interpolation and mapping were employed using mapping software. These layouts reduced humidity from 89.30% to 51.10%, with Layout 2 displaying the most consistent humidity distribution. Water removal efficiency varied among layouts, with Layout 2 exhibiting the highest (61.15 L) and overall performance of 50%, while Layouts 1, 3, and 4 exhibited lower efficiencies of 40%, 44%, and 49%, respectively. Power consumption ranged from 0.506 to 0.528 kW for the dehumidifier and 0.242 to 0.264 kW for the fan. The findings highlighted that positioning the dehumidifier on both sides, facing towards the center (Layout 2), resulted in the most uniform humidity control within the greenhouse. The optimal layout of small suspension-type dehumidifiers in greenhouses would significantly improve humidity control, promoting plant growth. [ABSTRACT FROM AUTHOR]

Maintaining suitable temperature level around tomato in the greenhouse is essential for the high-quality production. However, in summer, the temperature level around the tomato is usually unclear except using a high-precision temperature imager. To solve this problem, thermal performance of 3D (three-dimensional) tomato model built based on SolidWorks was investigated by the computational fluid dynamics (CFD) simulations. To assess the effect of temperature distribution around the tomato, a simplified 3D tomato numerical model was firstly validated by a set of field measurement data. The light intensity and indoor ventilation were regarded as the mainly environment factors in the Venlo greenhouse, thermal stratification around tomatoes at different time of day was further studied. The numerical results illustrated the different temperature distribution around tomato body under different radiation intensity. It was found that ventilation could obviously adjust the temperature gradient around the tomato, and alleviate high temperature effect particularly in summer. Suitable ventilation could create a suitable thermal environment for the tomato growth. This study clearly demonstrated 3D temperature distribution around tomatoes, which is beneficial to provide the reference for accurate detection of 3D tomato temperature and appropriate thermal environment design.

Greenhouse cultivation is one of the current strategies to address the challenges of food production, sustainability, and food quality. Similarly, the use of technological tools to automate greenhouse environments through a set of sensors and actuators allows for the control and improvement of processes within this environment. This document presents data collected from the sensors and actuators of two identical greenhouse environments, one with the cultivation of stringless blue lake beans and the other without cultivation. The aim is that this dataset will provide a broader characterization of the behavior of climatic variables inside greenhouse environments and how they are impacted by control actions, subsequently contributing to the development of new research on implementations of or improvements to control, supervision, management, and automation actions in greenhouse environments.

Accurate detection of muskmelon fruit ripeness is crucial to ensure fruit quality, optimize picking time, and enhance economic benefits. This study proposes an improved lightweight YOLO-RFEW model based on YOLOv8n, aiming to address the challenges of low efficiency in muskmelon fruit ripeness detection and the complexity of deploying a target detection model to a muskmelon picking robot. Firstly, the RFAConv replaces the Conv in the backbone part of YOLOv8n, allowing the network to focus more on regions with significant contributions in feature extraction. Secondly, the feature extraction and fusion capability are enhanced by improving the C2f module into a C2f-FE module based on FasterNet and an Efficient Multi-Scale attention (EMA) mechanism within the lightweight model. Finally, Weighted Intersection over Union (WIoU) is optimized as the loss function to improve target frame prediction capability and enhance target detection accuracy. The experimental results demonstrate that the YOLO-RFEW model achieves high accuracy, with precision, recall, F1 score, and mean Average Precision (mAP) values of 93.16%, 83.22%, 87.91%, and 90.82%, respectively. Moreover, it maintains a lightweight design and high efficiency with a model size of 4.75 MB and an inference time of 1.5 ms. Additionally, in the two types of maturity tests (M-u and M-r), APs of 87.70% and 93.94% are obtained, respectively, by the YOLO-RFEW model. Compared to YOLOv8n, significant improvements in detection accuracy have been achieved while reducing both model size and computational complexity using the proposed approach for muskmelon picking robots’ real-time detection requirements. Furthermore, when compared to lightweight models such as YOLOv3-Tiny, YOLOv4-Tiny, YOLOv5s, YOLOv7-Tiny, YOLOv8s, and YOLOv8n, the YOLO-RFEW model demonstrates superior performance with only 28.55%, 22.42%, 24.50%, 40.56%, 22.12%, and 79.83% of their respective model sizes, respectively, while achieving the highest F1 score and mAP values among these seven models. The feasibility and effectiveness of our improved scheme are verified through comparisons between thermograms generated by YOLOv8n and YOLO-RFEW as well as detection images. In summary, the YOLO-RFEW model not only improves the accuracy rate of muskmelon ripeness detection but also successfully realizes the lightweight and efficient performance, which has important theoretical support and application value in the field of muskmelon picking robot development.

AbstractFertigation by drip irrigation enhances the supply of water and nutrients directly to the root zone of plants. This results in maximal crop water and nutrient uptake and reduces leaching of nutrients and chemicals from the root zone. Two tomato varieties were cultivated in soilless medium in two greenhouse conditions to assess fertilizer rate, and irrigation regime on yield, water and nutrient utilization under a factorial experimental layout in a split-split plot design. The treatments were: three levels of fertilizer rate (F1: 100%, F2: 80%, F3: 60%) as recommended for soilless grown greenhouse tomato production, three levels of irrigation regime (I1: 100%, I2: 80%, I3: 60%) with respect to the crop water requirement and two tomato genotypes (V1: Jalila F1, V2: Yetty F1). A 20% to 40% decrease in fertilizer rate and irrigation regime decreased cluster (0.9–6.6%), flower (0.9–13.1%) and fruit (0.3–15%) formation under greenhouse condition. Marketable yield as affected by the combination of fertilizer rate by irrigation regime by genotype increased with increase in crop water productivity and nutrient use efficiency under greenhouse condition. Nutrient use efficiency increased with increase in crop water productivity. Evidently, marketable yield, crop water productivity and nutrient use efficiency vary significantly with plant nutrition, irrigation, genotype and its interactions. These are critical in curbing water scarcity, managing the economic crisis and to further the quest for zero hunger.

In the temperate climate of South Korea, specific corn varieties are cultivated using plug trays. The cultivation process is initiated from February to March within greenhouse facilities, maintaining a temperature below 10 degrees Celsius. Following this, in April, seedlings are transplanted to enable an exceptionally early harvest for increased profitability. However, the subsequent elevation in indoor temperatures leads to seedling overgrowth. This study explores the effectiveness of three plant growth regulators—paclobutrazol, prohexadione-calcium, and diniconazole–on super sweet corn seedlings. Significantly, the application of prohexadione-calcium at 2 ppm during the first leaf stage substantially reduces seedling height and impedes the growth of both the first and second internodes. This impact extends to leaf-related traits, manifesting reductions in the area, length, and width of the third leaf. Furthermore, prohexadione-calcium induces a significant decrease in both fresh and dried shoot weight, while simultaneously augmenting root weight. This alteration results in a noteworthy shift in the root–shoot ratio, particularly at 2 ppm. Subsequent experiments have identified the optimal concentration of prohexadione-calcium at 15 ppm, effectively mitigating overgrowth in both hybrid and inbred corn varieties. These findings provide essential insights for practitioners seeking to efficiently manage corn seedling overgrowth. The study contributes to understanding the retardant effect of prohexadione-calcium on various morphological traits, offering practical applications for optimizing plant growth regulator concentrations in corn cultivation strategies.

In greenhouse management, maintaining optimal humidity is essential for promoting plant growth, including photosynthesis, and preventing diseases and pests. Addressing spatial variability requires sensor-based monitoring for informed decisions on humidification systems, particularly for small, and suspension-type dehumidifiers. This study aims to assess the impact of various layouts of small-sized suspension-type dehumidifiers on vertical, spatial, and temporal humidity variability, along with energy consumption in a greenhouse. During experiments in a 648 m³ (18 m × 6 m × 6 m) plastic greenhouse, dehumidifiers were placed at four different layouts: one at the center (Layout 1), one on each side (Layout 2), two units at the center facing opposite directions (Layout 3), and two units on one side facing the center (Layout 4). Temperature and humidity (TH) sensors were connected to a microcontroller, facilitating wireless data acquisition, storage, and remote monitoring. The actuator was controlled through a relay module, and current sensors monitored power consumption. Spatial interpolation and mapping were employed using mapping software. These layouts reduced humidity from 89.30% to 51.10%, with Layout 2 displaying the most consistent humidity distribution. Water removal efficiency varied among layouts, with Layout 2 exhibiting the highest (61.15 L) and overall performance of 50%, while Layouts 1, 3, and 4 exhibited lower efficiencies of 40%, 44%, and 49%, respectively. Power consumption ranged from 0.506 to 0.528 kW for the dehumidifier and 0.242 to 0.264 kW for the fan. The findings highlighted that positioning the dehumidifier on both sides, facing towards the center (Layout 2), resulted in the most uniform humidity control within the greenhouse. The optimal layout of small suspension-type dehumidifiers in greenhouses would significantly improve humidity control, promoting plant growth.

In the process of off-season vegetable greenhouse cultivation, the use of a large number of pesticides will lead to drug residues in vegetables and soil, thereby threatening food safety and causing environmental pollution. However, there is little research on the environmental problems in the process of vegetable greenhouse cultivation. Therefore, this study analyzed the residue of sulfonamides antibiotics in greenhouse cultivation technology and organic fertilizer cultivation of vegetables. Furthermore, the diffusion of sulfonamides in soil was analyzed by numerical simulation. Finally, the effective mechanisms to slow down or avoid the residues of sulfa antibiotics in greenhouse vegetables were recommended. It was found that the residue of sulfamethoxazole in soil was the highest among the three drugs, while the residue of sulfadiazine in soil was the lowest. The final concentration of sulfamethoxazole in the soil filtrate is still as high as 14.15 mg/L, while the residual concentration of sulfadiazine in the soil is only 4.92 mg/L. At the same time, the concentration residues of three drugs in the xylem of green pepper were different from those in the soil. Sulfadiazine with less residue in soil was absorbed more in the xylem of green pepper, and the final concentration reached 694 ug/L. In addition, soil pH also affected the accumulation of sulfonamides in greenhouse vegetables. For sulfamethoxine and sulfamethoxazole, their residual concentrations in the xylem of green pepper will increase slightly as the soil changes from acidic to alkaline, while sulfadiazine shows opposite environmental protection performance. This study can provide a reference for the research on drug residues in green vegetables, and ultimately reduce the environmental pollution of vegetable planting. [ABSTRACT FROM AUTHOR]

This work develops a distributed environmental monitoring system for the combination of hydroponics and aquaculture based on the internet of things technology, which mainly includes the information perception layer, the information transmission layer and the system architecture. The system has employed multiple sensors terminal to real-time acquisition, including air and water temperatures, dissolved oxygen etc. LoRa protocol is suitable for sending small data and the 4G was employed to collect data and send to the cloud platform. Java is used to develop background applications, to access cloud platforms and local data processing. Based on the collection and processing of environmental data and cloud service platform, the mobile application program client and remote login desktop have been developed. It has been implemented and tested in Tongzhou, Beijing for 3 months in 2020. The results showed the proposed monitoring system stability for overall operation and accuracy data transmission, which can support the actual hydroponics and aquaculture production management. After analysis of monitoring data collected from the developed monitoring system, indoor air and water temperature have the obvious correlation with atmospheric pressure (0.7 and 0.9) and outdoor temperature (1.0 and 0.9), respectively.

The light intensity is low in haze weather, and the facility is in a weak light environment for a long time. As a functional film, light conversion film (LCF) can improve the light conversion performance and is conducive to regulating the environment in the facility to promote crop growth. It can be seen from the test that the light transmittance of LCF under visible light conditions (400–780 nm) is 8.67% higher than that of ordinary film (OF), with stronger light transmittance. In the red–orange light band (600–700 nm), the LCF is 1.3% higher than that of the OF. Through the detection of irradiance, it was found that the irradiance was outdoor environment > LCF > OF in any weather. A two-year greenhouse experiment was conducted to study the effect of LCF on the whole growth process of facility agriculture (environment-soil-crop) under weak light. It is found that LCF reduces the air humidity by 0.47~2.83%; it has an obvious warming effect on the surface soil of greenhouse, and it is linearly correlated with temperature. In terms of crop growth, LCF significantly (p < 0.05) increased the photosynthetic rate at heading stage, and finally increased the yield, total soluble sugar and reduction-type Vitamin C by 8.97–39.53%, 9.22–30.14%, and 1.41–21.09%, respectively. In addition, considering the frequent haze weather in North China, the use of LCF can improve air temperature, CO2 concentration, photosynthetically active radiation (PAR), and soil temperature, and it can effectively deal with the challenge of weak light. In conclusion, LCF can improve the facility environment and improve crop yield and quality, indicating that the implementation of LCF has potential benefits in solving crop yield reduction and quality decline in haze weather. In addition, as the main component of LCF, rare earth materials are a new type of clean energy, which can effectively promote the sustainable development of the agricultural ecosystem. [ABSTRACT FROM AUTHOR]

The greenhouse environment control system is a type of non-linear system since the temperature and humidity of the system are highly coupled. Besides, the time lag of the temperature and humidity control process is large, so it’s quite difficult to linearize and decouple the temperature and humidity of the system. To cope with this issue, this paper proposed a novel control strategy for greenhouse environment control system based on Back Propagation Neural Network (BPNN) and inverse model, the proposed method can perform inverse identification on the temperature and humidity control system to attain higher accuracy. Then, the inverse model and the original system were connected in series to form a pseudo linear system to realize the decoupled control of temperature and humidity. After that, aiming at the impact of some non-linear factors on the greenhouse environment system, this paper adopted the adaptive fuzzy Proportion Integration Differentiation (PID) controller to enhance the adaptability of the system, thereby reducing control error and the interference caused by non-linear factors of the temperature and humidity control system. At last, the experimental results showed that, the temperature error of the system could be controlled within 1.2℃ and the error of relative humidity was less than 2.5%. The proposed method can improve the control effect of the greenhouse environment to a certain extent, and it provides a novel approach of greenhouse control. [ABSTRACT FROM AUTHOR]

Aerated irrigation (AI) has the potential to be an effective management strategy to further increase yield and nitrogen-use efficiency. To determine the correlation between aerated irrigation and nitrogen application, we conducted a greenhouse experiment in Zhengzhou, Henan, China. A two-factor, three- level experiment was set up in which three aeration rates of dissolved oxygen in irrigation water (A1 = 5 mg/L, A2 = 15 mg/L, and A3 = 40 mg/L) and three nitrogen application rates (N1 = 120 kg/hm², N2 = 180 kg/hm², and N3 = 240 kg/ hm²) were set by using randomized block testing. CK is normal subsurface irrigation without fertilization and aeration, seemed as a control treatment. The analysis of variance, correlation analysis, and structural equation model (SEM) clarify how each factor affects the yield and nitrogen absorption and the utilization of greenhouse tomatoes. (Results) The results show that aerated irrigation significantly improves the nitrogen uptake efficiency and tomato yield (p < 0.05). Compared with the non-aerated treatment, the tomato yield after aerated irrigation increased by 13.35%-29.73%, and the highest tomato yield was 250.42t/hm² under treatment A2N3. Compared with treatments A1N3 and A3N3, the yield of treatment A2N3 increased by 29.73% and 11.53%, respectively, and the tomato nitrogen absorption efficiency increased by 53.06% and 18.33%, respectively (p < 0.05). Under the action of a single factor, applying nitrogen under aerated conditions can increase tomato yield and nitrogen absorption. According to SEM analysis, aeration and nitrogen application are positively correlated to a significant extent with tomato nitrogen absorption and indirectly correlated positively with tomato yield; the path coefficients are 0.969 and 0.927, respectively. Therefore, the combination of aeration and nitrogen application can further increase yield and nitrogen absorption efficiency, and the aeration amount A2 (15 mg/L) and the nitrogen application rate N3 (240 kg/hm²) are the best combination to increase the nitrogen uptake and yield of tomatoes. The results of this research provide technical support for optimizing gas-nitrogen coupled drip-irrigation and should help to popularize the use of gas-nitrogen coupled irrigation. [ABSTRACT FROM AUTHOR]

The maturity level of tomato is a key factor of tomato picking, which directly determines the transportation distance, storage time, and market freshness of postharvest tomato. In view of the lack of studies on tomato maturity classification under nature greenhouse environment, this paper proposes a SE-YOLOv3-MobileNetV1 network to classify four kinds of tomato maturity. The proposed maturity classification model is improved in terms of speed and accuracy: (1) Speed: Depthwise separable convolution is used. (2) Accuracy: Mosaic data augmentation, K-means clustering algorithm, and the Squeeze-and-Excitation attention mechanism module are used. To verify the detection performance, the proposed model is compared with the current mainstream models, such as YOLOv3, YOLOv3-MobileNetV1, and YOLOv5 in terms of accuracy and speed. The SE-YOLOv3-MobileNetV1 model is able to distinguish tomatoes in four kinds of maturity, the mean average precision value of tomato reaches 97.5%. The detection speed of the proposed model is 278.6 and 236.8 ms faster than the YOLOv3 and YOLOv5 model. In addition, the proposed model is considerably lighter than YOLOv3 and YOLOv5, which meets the need of embedded development, and provides a reference for tomato maturity classification of tomato harvesting robot. [ABSTRACT FROM AUTHOR]

Improving crop light environment can not only increase crop biomass accumulation, but also affect crop yield and quality. Therefore, exploring the light environment requirements of different crops has always been a research hotspot in the field of facility horticulture. In this paper, taking a region with short light time in western China as an example, the effect of leaf back light supplementation on the quality of greenhouse tomatoes was systematically studied. The results of the study show that according to the light intensity in the western region and the growth habit of tomatoes, it is necessary to properly supplement the light of greenhouse tomatoes. The net photosynthetic rate (Pn) of tomato leaves under supplemental light treatment was significantly higher than that of the control. During the test time, the change trend of Pn-PPFD is the same as that of Pn. Under the El treatment, the maximum Pn of the leaves under the saturated light intensity was the highest, which increased by 63.4% compared with the control; followed by E2 and E3, with an increase of close to 42.8%. Foliar spraying of exogenous calcium can increase crop yield and improve quality. Calcium not only promotes the growth and development of crops, but also improves the quality of crops by improving the absorption of mineral nutrients by plants. There is an interaction effect between different light supplement modes and calcium, and the effect of low-concentration calcium fertilizer on fruit morphology and quality is better than that of high-concentration calcium fertilizer. Under different photoperiod conditions, exogenous Fe fertilizer has a promoting effect on the photosynthetic characteristics and fruit quality of tomato leaves, and the effect of spraying 145 µmol/L Fe fertilizer on leaves under 16h/8h photoperiod is the best. This research can provide technical support for the high-yield and high-quality production of vegetables in areas with short sunlight hours in western China. [ABSTRACT FROM AUTHOR]

Modern greenhouses need a certain equipment to achieve the expected environmental temperature in a short time while saving energy. To achieve greenhouse temperature management and energy savings through intelligent control, a greenhouse mechanism model is first built to study the controller design for a greenhouse located in Yiyang city in this paper. Then, the model accuracy is verified by experimental data. Based on the verified model, two intelligent control technologies are proposed, namely, active disturbance rejection control and fuzzy active disturbance rejection control. Methods are adopted to adjust skylight opening and thermal air conditioning for greenhouse temperature control and energy savings. In 60 hours of continuous working time, fuzzy active disturbance rejection control takes 10 hours less than active disturbance rejection control to make the greenhouse temperature reach the ideal steady state, and the temperature overshoot is reduced by 60%. Through analysis, the proposed fuzzy active disturbance rejection control method for greenhouse temperature management can achieve 15% energy savings. The proposed intelligent control technology can also be applied to temperature management for real greenhouses.

To effectively and practically solve the dynamic economic optimal control problem of greenhouse environment with mixed integer variables, an improved genetic algorithm (IGA） with engineering constraint rules was proposed. Based on piecewise constant method for discretizing the control variables, the optimal control problem was transformed into nonlinear programming (NLP） problem with finite-dimension parameters, and the standard genetic algorithm (SGA） was used to solve the NLP problem. A precise penalty function was used to deal with the state variable path constraints. The engineering constraint rules and some improvement measures of elite retention, multi-population parallel evolution and integer variable setting were used to improve the algorithm performance. The simulation results show that compared with SGA, IGA obtains better performance indexes and control quality, which proves the effectiveness and practicability of the proposed method. [ABSTRACT FROM AUTHOR]

The light intensity is low in haze weather, and the facility is in a weak light environment for a long time. As a functional film, light conversion film (LCF) can improve the light conversion performance and is conducive to regulating the environment in the facility to promote crop growth. It can be seen from the test that the light transmittance of LCF under visible light conditions (400–780 nm) is 8.67% higher than that of ordinary film (OF), with stronger light transmittance. In the red–orange light band (600–700 nm), the LCF is 1.3% higher than that of the OF. Through the detection of irradiance, it was found that the irradiance was outdoor environment > LCF > OF in any weather. A two-year greenhouse experiment was conducted to study the effect of LCF on the whole growth process of facility agriculture (environment-soil-crop) under weak light. It is found that LCF reduces the air humidity by 0.47~2.83%; it has an obvious warming effect on the surface soil of greenhouse, and it is linearly correlated with temperature. In terms of crop growth, LCF significantly (p < 0.05) increased the photosynthetic rate at heading stage, and finally increased the yield, total soluble sugar and reduction-type Vitamin C by 8.97–39.53%, 9.22–30.14%, and 1.41–21.09%, respectively. In addition, considering the frequent haze weather in North China, the use of LCF can improve air temperature, CO2 concentration, photosynthetically active radiation (PAR), and soil temperature, and it can effectively deal with the challenge of weak light. In conclusion, LCF can improve the facility environment and improve crop yield and quality, indicating that the implementation of LCF has potential benefits in solving crop yield reduction and quality decline in haze weather. In addition, as the main component of LCF, rare earth materials are a new type of clean energy, which can effectively promote the sustainable development of the agricultural ecosystem.

The maturity level of tomato is a key factor of tomato picking, which directly determines the transportation distance, storage time, and market freshness of postharvest tomato. In view of the lack of studies on tomato maturity classification under nature greenhouse environment, this paper proposes a SE-YOLOv3-MobileNetV1 network to classify four kinds of tomato maturity. The proposed maturity classification model is improved in terms of speed and accuracy: (1) Speed: Depthwise separable convolution is used. (2) Accuracy: Mosaic data augmentation, K-means clustering algorithm, and the Squeeze-and-Excitation attention mechanism module are used. To verify the detection performance, the proposed model is compared with the current mainstream models, such as YOLOv3, YOLOv3-MobileNetV1, and YOLOv5 in terms of accuracy and speed. The SE-YOLOv3-MobileNetV1 model is able to distinguish tomatoes in four kinds of maturity, the mean average precision value of tomato reaches 97.5%. The detection speed of the proposed model is 278.6 and 236.8 ms faster than the YOLOv3 and YOLOv5 model. In addition, the proposed model is considerably lighter than YOLOv3 and YOLOv5, which meets the need of embedded development, and provides a reference for tomato maturity classification of tomato harvesting robot.

Copyright of Journal of Shenyang Agricultural University is the property of Journal of Shenyang Agricultural University Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the smart agricultural environment such as greenhouse or vertical farm, the automation process is performed using the environment sensors to maintain the growth of the crops. Currently, the system rely on the defined rule to perform automation, but the situation can turn catastrophic. With the interruption in the communication, data forging, or eavesdropping, the crops will be rotten and destroyed. Therefore, to maintain the automation without failure, the connection needs to be secure and tampering has to be avoided. In this paper, we discuss the security solution for the wireless sensor networks in the automated agricultural environment without any human intervention. The sink node that collects the sensor values organizes the data and transfer the data to the server, along with the XML encryption and private key mechanism for the communication. The secure protocol is used to make connection using the private key, XML ecryption prevents the system from eavesdropping, and forging. Some of the events discussed in the papers are EVNData, SENSOR E r r o r, DDoS A t t a c k, and Conn T h r e a t. With the help of the event and the tag information, the data security and confidentiality is increased, for the better automation and crop growth. [ABSTRACT FROM AUTHOR]

Leaf area measurements are commonly obtained by destructive and laborious practice. This study shows how stereo and time‐of‐flight (ToF) images can be combined for non‐destructive automatic leaf area measurements. The authors focus on some challenging plant images captured in a greenhouse environment, and show that even the state‐of‐the‐art stereo methods produce unsatisfactory results. By transforming depth information in a ToF image to a localised search range for dense stereo, a global optimisation strategy is adopted for producing smooth results that preserve discontinuity. They also use edges of colour and disparity images for automatic leaf detection and develop a smoothing method necessary for accurately estimating surface area. In addition to show that combining stereo and ToF images gives superior qualitative and quantitative results, 149 automatic measurements on leaf area using the authors system in a validation trial have a correlation of 0.97 with true values and the root‐mean‐square error is 10.97 cm2, which is 9.3% of the average leaf area. Their approach could potentially be applied for combining other modalities of images with large difference in image resolutions and camera positions.

Based on the problems in the current greenhouse environmental monitoring system such as difficult connection layout, low flexibility and high costs, this paper builds the greenhouse environmental monitoring system based on wireless sensor network, and designs the sensor nodes and gateway nodes. The sensor nodes of this system are responsible for collecting environmental parameters and sending the data to gateway nodes via wireless sensor network. And the gateway nodes transmit the data to the remote monitoring platform. The microprocessor module of node hardware uses MSP430F149 microprocessor for data processing and control; wireless communication module consists of nRF905 RF chip and peripheral circuit, responsible for transmitting and receiving data; sensor module uses AM2301 sensor for data measurement ; the power supply module uses the circuit consisting of LT1129 - 3. 3 , LT1129 -5 and Max660 to provide 3. 3 and ± 5V power. The C language development is employed for wireless routing protocol of node and time synchronization algorithm, to achieve node data acquisition and processing, rule fOlWarding and remote transmission. Remote monitoring software uses NET. ASP, HTML and C# development to provide visual WEB mode remote data management platform for users. The system goes through networking testing in greenhouse in Xining City, and test results show that the system operation is stable and reliable, and the average network packet loss rate is 2.4% , effectively solving the problems in greenhouse environmental monitoring system and meeting the application requirements of greenhouse cultivation environmental monitoring. [ABSTRACT FROM AUTHOR]

A greenhouse provides a stable and suitable environment for the growth of plants. Temperature and humidity are closely related to plant growth. These factors directly affect the water content of plants and the quality of fruits. To solve the problems in the current monitoring system of greenhouse cultivation, such as complicated wiring, large node power consumption, and so on, this study proposes a wireless sensor network greenhouse-monitoring system based on third-generation network communication for the real-time monitoring of the temperature, humidity, light, and CO2 concentration in a greenhouse. GS1011M is regarded as the core in developing wireless terminal nodes. PC software is used to build a real-time observation platform. Sensor data are received in real time through a wireless communication network to complete the monitoring of the target area. A simulation research is also conducted. Results show that the power dissipation of the greenhouse environmental monitoring system is low, its data accuracy is high, and its operation is stable. [ABSTRACT FROM AUTHOR]

• High atmospheric p CO 2 levels, constrained by the paired C-isotopic compositions of carbonate and organic carbon from ∼1.6 Ga Gaoyuzhuang Formation, could have played an important role in compensating for the low solar luminosity and maintaining the temperature of the Mesoproterozoic Earth's surface. It is hypothesized that the Mesoproterozoic was characterized by a prevailing warm climate and a high atmospheric p CO 2 level. However, quantitative constraints on Mesoproterozoic atmospheric p CO 2 are scarce. Here, we report high-resolution organic and inorganic carbon isotope records from sediment samples aged ∼1.6 Ga, collected from Hebei Province in North China. The δ13C org values of these Mesoproterozoic samples vary from −28.4‰ to −34.3‰, and the δ13C carbonate values range from −2.1‰ to 0.4‰. The paired carbonate and organic carbon isotope records can be used as a proxy to quantify the atmospheric CO 2 concentration during the Mesoproterozoic. According to the calibration between the photosynthetic isotopic effect and atmospheric CO 2 , atmospheric CO 2 concentrations are estimated to be within the range of 910–18,800 ppmv, ∼2–50 times greater than the present atmospheric level. The results support the previous hypothesis which suggests that high levels of atmospheric CO 2 prevailed in the Early Mesoproterozoic. High atmospheric pCO 2 levels could have played an important role in compensating for the possible lower solar luminosity and maintaining the temperature of the Mesoproterozoic Earth's surface. [ABSTRACT FROM AUTHOR]

The design of a multi-agent system for integrated management of greenhouse production is described. The model supports the integrated greenhouse production, with targets set to quality and quantity of produce with the minimum possible cost in resources and environmental consequences. In this paper, we propose a real time and robust system for monitoring and control of the greenhouse condition which can automatically control of greenhouse temperature, lights, humidity, CO2 concentration, sunshine, pH, salinity, water available, soil temperature and soil nutrient for efficient production. We will propose a multi-agent methodology for integrated management systems in greenhouses. In this regards wireless sensor networks play a vital role to monitor greenhouse and environment parameters. Each control process of the greenhouse environment is modeled as an autonomous agent with its own inputs, outputs and its own interactions with the other agents. Each agent acts autonomously, as it knows a priori the desired environmental setpoints. Many researchers have been making attempts to develop the greenhouse environment management system. The existing environment management systems are bulky, very costly and difficult to maintain. In the last years, Multi Agent Systems and Wireless Sensor Networks are becoming important solutions to this problem. This paper describes the implementation and configuration of the wireless sensor network to monitor and control various parameter of greenhouse. The developed system is simple, cost effective, and easily installable. [ABSTRACT FROM AUTHOR]

• To effectively and practically solve the dynamic economic optimal control problem in greenhouse environments, an improved genetic algorithm with engineering constraint rules is proposed. • Engineering constraint rules greatly improve the algorithm optimization performance, and the practicability for the optimal control confines. • The setting of Nc is investigated, not only from the algorithm performance, but also from the practicality of control profiles. To effectively and practically solve the dynamic economic optimal control problem in greenhouse environments, an improved genetic algorithm with engineering constraint rules (R-GA) is proposed. Based on a dynamic greenhouse-crop model and control vector parameterization (CVP) method to discretize the control variables, the economic optimal control problem is transformed into a nonlinear programming (NLP) problem with finite-dimension parameters, and then R-GA is used to effectively solve the NLP problem. Three components were investigated, such as a smooth penalty function to deal with state variable path constraints, engineering constraint rules to improve the optimization performance and the algorithm feasibility, and the number of collocation points ( Nc ) to meet the actual control laws. The simulation results demonstrate that the proposed approach greatly improves the effectiveness and feasibility to solve the dynamic optimal control problem in greenhouse environments. [ABSTRACT FROM AUTHOR]

• The light intensity over 507 W ∙ m-2 did not have a significant effect on the transpiration rate increase. • The relationship between VPD and transpiration rate was expressed by Gauss peak fitting method. • Tomato transpiration model considering the specific environment in the greenhouse was developed. Since transpiration model of tomato is a main index for precise irrigation control in greenhouse soilless culture, more precise transpiration model needs to be developed for tomato cultivation. Although various models have been developed, they are limited under low VPD condition due to high light intensity in greenhouse, especially during the daytime at summer season of Korea. Therefore, the objective of this study was to develop an improved model considering the above unusual environment in greenhouse. Experiments were conducted between 2017 and 2018. The actual transpiration rate was measured by a load cell, weight measuring device, and used as data for model development. In 2018 experiment, an environment suitable for the growth of crops was established through shading film and humidification. The model equation was developed by calibrating parameters within the VPD range suitable for crop growth with compensated radiation under high light conditions. Experimental results showed that the transpiration rate had exponential increase to the maximum with respect to radiation and transpiration rate to VPD was fitted to gaussian peak shape. The developed model equation was verified by comparing with measured transpiration rate. Verification result showed that the developed model had a higher correlation coefficient than the existing one. In summary, a tomato transpiration model considering the specific environment in the greenhouse was developed in this study. It could be used to precision irrigation and environment control in greenhouse tomato cultivation. [ABSTRACT FROM AUTHOR]

The Internet of Things has a high impact on upgrade and transformation of the traditional greenhouse agricultural techniques. It is necessary to control the environmental factors for obtaining the optimum growth conditions for the crop and extend the production season to get the optimum yield. These aspects are fundamental for Agriculture 4.0, that uses technology not simply for the sake of innovation but to improve and address the real needs of consumers. In this paper, a prototype of a low-cost electronic platform for real time greenhouse environment monitoring has been designed, developed and built. The prototype has been developed with the purpose of firmware and software prototyping, in order to make the most of device performances. The electronic board is composed by a Main Board, a Green House Core, a Wi-Fi Module, a RS485 Module, an Analog-to-Digital Converter Module and a USB Module. The system permits to collect data by external sensors, elaborate and send them to external devices as laptop, smartphone and internet gateway, using both wired and wireless connection. These data concern to main greenhouse environmental parameters, such as air temperature, humidity, solar radiation, air velocity and CO2 concentration. A Web application has been implemented to allow users a consultation of greenhouse environmental state in a simple and fast way. [ABSTRACT FROM AUTHOR]