Search

A lightweight strawberry detection and localization algorithm plays a crucial role in enabling the harvesting robot to effectively harvest strawberries. The YOLO model has often been used in strawberry fruit detection for its high accuracy, speed, and robustness. However, some challenges exist, such as the requirement for large model sizes, high computation operation, and undesirable detection. Therefore, the lightweight improved YOLOv5s-CGhostnet was proposed to enhance strawberry detection. In this study, YOLOv5s underwent comprehensive model compression with Ghost modules GCBS and GC3, replacing modules CBS and C3 in the backbone and neck. Furthermore, the default GIOU bounding box regressor loss function was replaced by SIOU for improved localization. Similarly, CBAM attention modules were added before SPPF and between the up-sampling and down-sampling feature fusion FPN–PAN network in the neck section. The improved model exhibited higher mAP@0.5 of 91.7% with a significant decrement in model size by 85.09% and a reduction in GFLOPS by 88.5% compared to the baseline model of YOLOv5. The model demonstrated an increment in mean average precision, a decrement in model size, and reduced computation overhead compared to the standard lightweight YOLO models.

Abstract Recent advances in solar‐driven interfacial evaporation (SDIE) have led to high evaporation rates that open promising avenues for practical utilization in freshwater production and industrial application for pollutant and nutrient concentration, and resource recovery. Breakthroughs in overcoming the theoretical limitation of 2D interfacial evaporation have allowed for developing systems with high evaporation rates. This study presents a comprehensive review of various evaporator designs that have achieved pure evaporation rates beyond 4 kg m−2 h−1, including structural and material designs allowing for rapid evaporation, passive 3D designs, and systems coupled with alternative energy sources of wind and joule heating. The operational mechanisms for each design are outlined together with discussion on the current benefits and areas for improvement. The overarching challenges encountered by SDIE concerning the feasibility of direct integration into contemporary practical settings are assessed, and issues relating to sustaining elevated evaporation rates under diverse environmental conditions are addressed.

Carbon dioxide (CO2) concentrations play an important role in plant production, as they have a direct impact on both plant growth and yield. Therefore, the objectives of this study were to predict CO2 concentrations in the greenhouse by applying time series models using five datasets. To estimate the CO2 concentrations, this study was conducted over a four-month period from 1 December 2023 to 31 March 2024, in a strawberry-cultivating greenhouse. Fifteen sensors (MCH-383SD, Lutron, Taiwan) were installed inside the greenhouse to measure CO2 concentration at 1-min intervals. Finally, the dataset was transformed into intervals of 1, 5, 10, 30, and 60 min. The time-series data were analyzed using the autoregressive integrated moving average (ARIMA) and the Prophet Forecasting Model (PFM), with performance assessed through root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The evaluation indicated that the best model performance was achieved with data collected at 1-min intervals, while model performance declined with longer intervals, with the lowest performance observed at 60-min intervals. Specifically, the ARIMA model outperformed across all data collection intervals while comparing with the PFM. The ARIMA model, with data collected at 1-min intervals, achieved an R2 of 0.928, RMSE of 7.359, and MAE of 2.832. However, both ARIMA and PFM exhibited poorer performances as the interval of data collection increased, with the lowest performance at 60-min intervals where ARIMA had an R2 of 0.762, RMSE of 19.469, and MAE of 11.48. This research underscores the importance of frequent data collection for precise environmental control in greenhouse agriculture, emphasizing the critical role of short-interval data collection for accurate predictive modeling.

The purpose of this study was to determine the optimal operating speeds for a modified linkage cum hopper type planting unit that was used in low-speed automated vegetable transplanters. The transplanter utilizes a biodegradable seedling plug-tray feeding mechanism. The movement of the planter unit was simulated at different operating conditions using kinematic simulation software, and the resulting trajectories were compared based on factors such as plant spacing, soil intrusion area, soil intrusion perimeter, and horizontal displacement of the hopper in soil and found optimal result at 200, 250 and 300 mm/s and 40, 50 and 60 rpm combinations. The optimal operating speeds were then tested in a soil bin facility and found to perform well when transplanting pepper seedlings, with measured plant spacing that was close to the theoretical spacing. The planting depth in each case was not significantly different and the planting angle in different speed combinations was found to be significantly different, but within permissible limits. The mulch film damage was low for the selected optimised speed combinations. This study resulted in the determination of the optimal speeds for the transplanter, which can be used as a basis for optimising the other mechanisms within the transplanter.

Removing seedlings from plug-trays to transplant in the field poses transplanting shocks to the seedlings and may reduce the survival rate. Therefore, this study designed biodegradable plug-tray cutting mechanism (SPCM) that separates seedlings with plug-cells from plug-trays and eliminates a complex clamping mechanism. SPCM consists of three sub-mechanisms that align the plug-cell at the seedling discharge point to cut and separate the plug-cell from the plug-tray, allowing the seedling to fall into the transplanting hopper. The SPCM separated around 82% of the plug-cell and delivered it to the planting unit. Furthermore, the SPCM-equipped transplanter achieved a transplanting performance of 74% with pepper and cabbage seedlings, with an average field efficiency of 68%, field capacity of 0.032-0.035 ha h-1 and required 73% less labour than manual seedling transplanting. The transplanting performance was satisfactory, with most pepper seedlings (85%) transplanted with a planting angle less than 10°, and 7% of cabbage seedlings were inclined and had sufficient planting depth of 48 mm for cabbage and 53 mm for pepper. In conclusion, the SPCM is a step towards sustainable and efficient vegetable seedling transplanting. Increasing efficiency, planting accuracy, and sustainability present exciting opportunities for further research and development in the field.

In order to produce marketable yield, scientific methodologies must be used to forecast the greenhouse microclimate, which is affected by the surrounding macroclimate and crop management techniques. The MATLAB tool NARX was used in this study to predict the strawberry yield, indoor air temperature, relative humidity, and vapor pressure deficit using input parameters such as indoor air temperature, relative humidity, solar radiation, indoor roof temperature, and indoor relative humidity. The data were normalized to improve the accuracy of the model, which was developed using the Levenberg–Marquardt backpropagation algorithm. The accuracy of the models was determined using various evaluation metrics, such as the coefficient of determination, mean square error, root mean square error, mean absolute deviation, and Nash–Sutcliffe efficiency coefficient. The results showed that the models had a high level of accuracy, with no significant difference between the experimental and predicted values. The VPD model was found to be the most important as it influences crop metabolic activities and its accuracy can be used as an indoor climate control parameter.

The optimal indoor environment is associated with comfortable temperatures along with favorable indoor air quality. One of the air pollutants, particulate matter (PM), is potentially harmful to animals and humans. Most farms have monitoring systems to identify other hazardous gases rather than PM due to the sensor cost. In recent decades, the application of environmental monitoring systems based on Internet of Things (IoT) devices that incorporate low-cost sensors has elevated extensively. The current study develops a low-cost air quality monitoring system for swine buildings based on Raspberry Pi single-board computers along with a sensor array. The system collects data using 11 types of environmental variables along with temperature, humidity, CO2, light, pressure, and different types of gases, namely PM1, PM2.5, and PM10. The system is designed with a central web server that provides real-time data visualization and data availability through the Internet. It was tested in actual pig barns to ensure stability and functionality. In addition, there was a collocation test conducted by placing the system in two different pig barns to validate the sensor data. The Wilcoxon rank sum test demonstrates that there are no significant differences between the two sensor datasets, as all variables have a p-value greater than 0.05. However, except for carbon monoxide (CO), none of the variables exhibit correlation exceeding 0.5 with PM concentrations. Overall, a scalable, portable, non-complex, low-cost air quality monitoring system was successfully developed within a cost of USD 94.

The ice plant (Mesembryanthemum crystallinum L.) has become a halophyte model to study the plant photosynthetic responses C3 photosynthesis to crassulacean acid metabolism (CAM), which is accelerated by salt stress. However, this adaptive mechanism improves water use efficiency, and water stress tolerance is still poorly known. This study examined the effect of individual and mixture of NaCl and CaCl2 concentrations on morphological parameters and bioactive component contents of ice plants in a plant factory system. Eight salt treatments individually and a combination of sodium chloride (NaCl) and calcium chloride (CaCl2), and Hoagland solutions were applied after the transplanting of ice plants. Morphological parameters like the number of leaves and lateral stems, leaf chlorophyll content (SPAD value), fresh weight, and dry weight of shoots and roots were measured at the adult stage. Concurrently, in the juvenile phase, the area of a canopy was evaluated using an image processing technique in HSV (hue, saturation, value) colour space. Correspondingly, ice plant secondary metabolites such as cations, anions, and radical scavenging activity were assayed in the adult phase correlated to the salt stress. The effects of salt stress on the growth of ice plants and secondary metabolite production were analysed using completely randomized block designs through the variance by one-way ANOVA with a significance level of p

TRNSYS is a common tool that has been recently used to model and simulate greenhouse energy demand and utilization using building energy simulation (BES). Previously, a single thermal point was used for validation, ignoring the distribution of greenhouse climate parameters, especially the temperature. Temperature variation often leads to thermal stratification, prompting researchers to propose volume discretization in dynamic greenhouse simulations. In this context, the effect of envelope characterization on the accuracy of discretized TRNSYS BES model was developed to determine the best BES model under a free-floating regime. The combination of the number of layers [double (D) and single (S)], geometry mode [3D and manual (M)], and layer type [massless (M) and no glazing window (W)], led to the development of five models: D_3D_M, D_3D_W, D_M_M, S_3D_W, and S_M_M. The simulation was performed in a standard radiation mode, and the output parameters were temperature and relative humidity (RH). R2 and the root square mean error (RSME) were used to check the fitness and degree of deviation, respectively, to validate the models. Analysis of variance (ANOVA) was employed to investigate the significant differences among the models, whereas contour plots were used to compare the distribution pattern between the significant models and experimental data. Validation of the models showed that the obtained R2 values ranged from 0.86 to 0.95, and the RSME values for the temperature were between 2.64 °C and 3.91 °C. These values were 0.91–0.93 and 19.72%–30.32% for RH. The ANOVA (p < 0.05) result exhibited significant differences between the S-scenario models and experimental central points in temperature and RH. The D- and S-layer scenarios with a 3D geometry and massless layer showed similar distribution with their corresponding experimental greenhouses. Hence, 3D_M was regarded as the best combination in the discretized BES model.

Thermally localized solar-driven water evaporation (SWE) in recent years has increasingly been developed due to the potential of cost-efficient freshwater production from small-scale portable devices. In particular, the multistage SWE has attracted much attention as the systems possess mostly a simple foundational structure and high solar-to-thermal conversion output rates, enough to produce freshwater from 1.5 L m−2h−1 (LMH) to 6 LMH. In this study, the currently designed multistage SWE devices were reviewed and examined based on their unique characteristics as well as their performances in freshwater production. The main distinguishing factors in these systems were the condenser staging design and the spectrally selective absorbers either in a form of high solar absorbing material, photovoltaic (PV) cells for water and electricity co-production, and coupling of absorber and solar concentrator. Other elements of the devices involved differences such as the direction of water flow, the number of layers constructed, and the materials used for each layer of the system. The key factors to consider for these systems include the heat and mass transport in the device, solar-to-vapor conversion efficiency, gain output ratio (representing how many times the latent heat has been reused), water production rate/number of stages, and kWh/number of stages. It was evident that most of the studied devices involved slightly different mechanisms and material compositions to draw out higher efficiency rates from the current limitations. The reviewed designs showed the ability to be adopted into small-scale solar desalination allowing for accessibility of sufficient freshwater in needing regions.

Fertilizer misapplications have induced widespread environmental deteriorations, climatic catastrophes, and economic losses; meanwhile, the Precision Agriculture (PA) endorsements have been influential in alleviating these issues. This study intended to tackle the fertilizer consumption inefficiencies by utilizing non-destructive remote sensing technologies, soil macronutrient distribution analysis, and a deep learning model. Specifically, an Unmanned Air Vehicle (UAV) was used in a cornfield to capture the plant's reflectance information for retrieving the Normalized Difference Vegetation Index (NDVI) during the vegetative and reproductive growth stages. Consequently, the field's soil samples were examined for their Nitrogen, Phosphorus, Potassium, and Carbon (NPKC) macronutrient constituencies. Finally, a Convolutional Neural Network-Regression model was developed to predict infield NPKC spatiotemporal variations in soil using the NDVI measurements. The deep learning model effectively determined the surpluses or shortages of the NPKC macronutrients within the cornfield throughout the growth stages. The model performed vigorously with R2 values of 0.93, 0.92, 0.98, and 0.83 in predicting N, P, K, and C levels in soil, respectively.

An experiment was conducted to evaluate modelling relationships between pig’s body surface temperature and ambient environment including inside and outside of pig barn. For this purpose, four different artificial neural network (ANN), including Feed Forward Back-propagation (FFB), Layer recurrent (LR), Elman (EL) and Cascade Forward Back-propagation (CFB) with different learning algorithms, transfer functions, hidden layers and neuron in each layer, and multi-linear regression (MLR) models have been performed to predict body temperature of pig. Six two-month-old pigs were studied over a period of 92 days during two years (2017–2018) to develop and evaluate the ANN and MLR models. The performance of the models in predicting pig’s body temperature was determined using statistical quality parameters, including coefficient of determination (R2), root mean square error (RMSE) and mean absolute percentage error (MAPE). The FFB model with the Levenberg-Marquardt training function, Gradient descent weight and bias learning function, Log-sigmoid transfer function and two hidden layers with 20 neurons was found as the best model. Sensitivity analysis indicated that the temperature-humidity index (THI) inside the room is the most influential factor in predicting pig’s body temperature in the MLR/ANN models.

Research on carbon management is fueled by the growing concern over rising carbon dioxide (CO2) levels in the atmospheric air and its possible impacts on the climate. In this study, we proposed a method of CO2 separation from atmospheric air. This study aimed to investigate the effects of CO2 enrichment on the air temperature inside a greenhouse using a hollow fiber (HF) membrane system. The experiment was conducted over a period of 30 days in two experimental conditions: 15 days without CO2 enrichment (WCS) and 15 days with CO2 enrichment (CS). Results showed that the mean CO2 concentration and air temperature were highest inside the greenhouse during the CS period, with values of 1120 ppm and 37.42 °C, respectively. Regression analysis revealed a positive correlation between CO2 concentration and temperature during the CS period (R2 = 0.628). The HF membrane system was found to be effective in increasing both the CO2 concentration and air temperature inside the greenhouse. However, the system also has limitations, including the cost, maintenance, and suitability for all types of crops. Further experiments are needed to address these limitations and determine the optimal CO2 concentration for different kinds of crops growing in greenhouses.

Light intensity, temperature, and humidity are key factors affecting photosynthesis, respiration, and transpiration. Among these factors, temperature is a crucial parameter to establish an optimal greenhouse climate. Temperature can be controlled by using an appropriate climate screen, which has a considerable impact on crop quantity and quality. The precise measurements of longwave radiative properties of screens are vital to the selection of the most suitable screen for greenhouses so that the desired temperature and a favorable environment can be provided to plants during nighttime. The energy-saving capability of screens can also be calculated by using these properties as inputs in a physical model. Two approaches have been reported so far in the literature for the measurement of these properties, i.e., spectrophotometry and wideband radiometry. In this study, we proposed some modified radiation balance methods for determining the total hemispherical longwave radiative properties of different screens by using wide-band radiometers. The proposed method is applicable to materials having zero porosity, partial opacity, and asymmetric screens with 100% solidity. These materials were not studied previously under natural conditions. The existing and proposed methods were applied and compared, and it was found that the radiometric values obtained from the developed methodology were similar to those previously reported in the literature, whereas the existing method gave unstable results with zero reflectance.

Timely monitoring of fruit weight is a paramount concern for the improvement of productivity and quality in strawberry cultivation. Therefore, the present study was conducted to introduce a simple non-destructive technique with machine learning models in measuring fruit weight of strawberries. Nine hundred samples from three strawberry cultivars, i.e., Seolhyang, Maehyang, and Santa (300 samples in each cultivar), in six different ripening stages were randomly collected for determining length, diameter, and weight of each fruit. Pixel numbers of each captured fruit’s image were calculated using image processing techniques. A simple linear-based regression (LR) and a nonlinear regression, i.e., support vector regression (SVR) models were developed by using pixel numbers as input parameter in modeling fruit weight. Findings of the study showed that the LR model performed slightly better than the SVR model in estimating fruit weight. The LR model could explain the relationship between the pixel numbers and fruit weight with a maximum of 96.3% and 89.6% in the training and the testing stages, respectively. This new method is promising non-destructive, time-saving, and cost-effective for regularly monitoring fruit weight. Hereafter, more strawberry samples from various cultivars might need to be examined for the improvement of model performance in estimating fruit weight.

The optimal production of strawberries requires the essential nutrients and favourable media for vegetative and reproductive growth. The present study sought to determine the effectiveness of growth parameters and fruit yield of strawberries in different media growing under a greenhouse. To analyze the significant effect for the growth and fruit yield among the growing media, four treatments such as control soil (CS), bio plus compost (T1), the combination of bio plus compost, and synthetic nutrient applied media/integrated media (T2) and synthetic nutrient applied soil media (T3) were assayed. Morphology parameters like plant height, canopy area, fresh weight, dry weight of roots were measured in each stage after eight weeks and sixteen weeks and yield attributing parameter as the number of fruits set per plant and number of fruits per plant were measured at the beginning and end of the reproductive stage eight and sixteen weeks respectively. The effects of growing media for the strawberry plant growth and productivity were analyzed using completely randomized block designs through analyzing the variance with a significance level of p < 0.05. The canopy area of the strawberry plants was calculated using the image processing technique applied in HSV colour space. Correspondingly, the vegetative stage and reproductive stage of T2 plants attained the maximum plant height of 16.93 ± 0.31 cm and 19.34 ± 0.21 cm, canopy area with 23.02 ± 1.94 cm2 and 28.78 ± 0.93 cm2, fresh weight of 18.00 ± 3.06 g, and 20.15 ± 3.49 g, dry weight of 5.15 ± 1.26 g and 6.66 ± 2.34 g and the number of fruits set per plant 18.83 ± 2.64 and number of fruits per plant 24.17 ± 2.14 followed by T1, T3, and CS respectively. A comparison of the relative growth and fruit yield at the vegetative and reproductive phases of plants T2 implied better performance. This study demonstrated that bio plus compost with synthetic nutrients act as a better source for the growth and production of strawberries under the greenhouse.

Non-destructive and destructive leaf area estimation are critical in plant physiological and ecological experiments. In modern agriculture, ubiquitous digital cameras and scanners are primarily replacing traditional leaf area measurements. Thus, measuring the leaflet’s dimension is integral in analysing plant photosynthesis and growth. Leaf dimension assessment with image processing is widely used nowadays. In this investigation employed an image segmentation algorithm to classify the ice plant (Mesembryanthemum crystallinum L.) canopy image with a threshold segmentation technique by grey colour model and calculating the degree of green colour in the HSV (hue, saturation, value) model. Notably, the segmentation technique is used to separate suitable surfaces from a defective noisy background. In this work, the canopy area was measured by pixel number statistics relevant to the known reference area. Furthermore, this paper proposed total leaf area estimation in a destructive method by a computer coordinating area curvimeter and lastly evaluated the overlapping percentage using the total leaf area and canopy area measurements. To assess the overlapping percentage using the proposed algorithm, the curvimeter method experiment was performed on 24 images of ice plants. The obtained results reveal that the overlapping percentage is less than 10%, as evidenced by a difference in the curvimeter and the proposed algorithm’s results with the canopy leaf area approach. Furthermore, the results show a strong correlation between the canopy and total leaf area (R2: 0.99) calculated by our proposed method. This overlapping leaf area finding offers a significant contribution to crop evolution by using computational techniques to make monitoring easier.

Determination of internal qualities such as total soluble solids (TSS) and pH is a paramount concern in strawberry cultivation. Therefore, the main objective of the current study was to develop a non-destructive approach with machine learning algorithms for predicting TSS and pH of strawberries. Six hundred samples (100 samples in each ripening stage) in six ripening stages were collected randomly for measuring the biometrical characteristics, i.e., length, diameters, weight and TSS and pH values. An image of each strawberry fruit was captured for colour feature extraction using an image processing technique. Channels of each colour space (RGB, HSV and HSL) were used as input variables for developing multiple linear regression (MLR) and support vector machine regression (SVM-R) models. The result of the study indicated that SVM-R model with HSV colour space performed slightly better than MLR model for TSS and pH prediction. The HSV based SVM-R model could explain a maximum of 84.1% and 79.2% for TSS and 78.8% and 72.6% for pH of the variations in measured and predicted data in training and testing stages, respectively. Further experiments need to be conducted with different strawberry cultivars for the prediction of more internal qualities along with the improvement of model performance.

There is much interest in alternative energy sources for greenhouse heating and cooling, due to the impact of severe climatic conditions and increasing fossil fuel prices. The main objective of this study was to experimentally evaluate the performance of an air-to-water heat pump (AWHP) system to fulfil the cooling and heating energy requirements of a three-spanned greenhouse under local weather conditions in Daegu, South Korea. For this purpose, a system comprising three air-to-water heat pumps, a water storage tank, and fan coil units (FCU)s was designed. Experiments were conducted extensively during the summer and winter seasons. The maximum heating and cooling energy supply to the greenhouse was 210 kcal∙h−1∙m−2 and 230 kcal∙h−1∙m−2, respectively. Based on the outcomes of this study, the AWHP system can provide heating during the winter season. During the summer season, the FCU capacity was insufficient to provide the desired cooling to achieve the setpoint air temperature inside the studied greenhouse. To achieve the desired microclimate during the summer season, the capacity of the FCU or number of FCUs must be increased. Moreover, one AWHP with a water storage tank, was sufficient to provide the required cooling and heating in both seasons. Two additional AWHPs can be used to provide energy to more greenhouse areas in the future. The results can be used as a case study to find a more resilient and reliable source for greenhouse heating and cooling. The average COP of the AWHP in heating mode was 2.2, while on cooling mode, it was 3.2.

The purpose of this study was to conduct a modeling-based energy performance assessment and validation of an air-to-water heat pump (AWHP) system, in the cooling mode, integrated with a multi-span greenhouse using TRNSYS software. We used the building energy simulation (BES) model to investigate the performance characteristics of the AWHP system for greenhouse cooling. We modelled the components of the AWHP system, including the fan coil unit (FCU), water storage tank, and water circulation pump integrated with the greenhouse model. The proposed model included all the components of the experimental system. We validated the proposed model by comparing the simulation results with those obtained from field experiments. We investigated the cooling energy supply to the multi-span greenhouse, greenhouse internal air temperature, heat pump (HP) output temperature, and coefficient of performance (COP). We evaluated the performance of our model by calculating the Nash–Sutcliffe efficiency (NSE) coefficient of all the validated components. Furthermore, we performed linear regression analyses (R2) to determine the relationship between the different parameters. NSE values of 0.87, 0.81, and 0.93, for the greenhouse internal air temperature, the energy supply to the greenhouse, and the HP output water temperature, respectively, validated the prediction accuracy of the model. Moreover, R2 values of 0.83 and 0.39 indicated that cooling loads are more dependent on ambient solar radiation than ambient air temperature. Furthermore, an R2 value of 0.91 showed a linear relationship between the HP’s energy consumption and ambient air temperature. The average daily COP of the HP system was 2.9. Overall, the simulation results showed acceptable correlation with the experimental results. The high NSE values validated the high predictive power of the model. The proposed validation model can be used to improve the performance of systems by optimizing the control strategies and capacities of the equipment (e.g., the HP, the FCU, and the area of the greenhouse). We have provided detailed information to enable engineers, researchers, and consultants to implement the model for their specific needs.

Strawberry cultivation is highly dependent on environmental parameters and energy during the winter. Two gothic greenhouses with different glazing material combinations, polyolefin–thermal screen (PoTS) and polyolefin–thermal screen–polyethylene (PoTSPe), were used for strawberry cultivation. The energy-saving capabilities of the two configurations and their impact on the microclimates of the greenhouses were investigated. The temperature, relative humidity, vapor pressure deficit, leaf temperature, carbon dioxide concentration and solar radiation over the experimental period in the PoTS greenhouse were 13.0 ± 2.3°C, 75.8 ± 6.5%, 0.4 ± 0.1 kPa, 13.6 ± 1.7 °C, and 168.8 ± 82.3W/m2, respectively, whereas those of the PoTSPe condition were 13.1 ± 2.3 °C, 80.0 ± 5.7%, 0.3 ± 0.1 kPa, 13.5 ± 1.6 °C, and 183.1 ± 90.5 W/m2. The mean fuel consumption by the PoTS and PoTSPe greenhouses were 5.5 and 3.5 L, respectively. The performance analysis shows that both greenhouses were able to maintain the environmental parameters and leaf temperature within the recommended ranges, although more energy was consumed in the PoTS. More yield was obtained in the PoTS greenhouse, however, not significantly different from PoTSPe yield.

Intensively grown strawberries in a greenhouse require frequent and precise soil physicochemical constituents for optimal production. Strawberry leaf color analyses are the most effective way to evaluate soil status and protect against excess environmental nutrients and financial setbacks. Meanwhile, precision agriculture (PA) endorsements have been utilized to mimic solutions to these problems. This research aimed to create machine learning models such as multiple linear regression (MLR) and gradient boost regression (GBR) for simulating strawberry leaf color changes related to soil physicochemical components and plant age using RGB (red, green, and blue) mean values. The soil physicochemical properties of the largest varied colored leaves of strawberry were precisely measured by a multifunctional soil sensor from the rooting zones. Simultaneously, 400 strawberry leaflets were detached in each vegetative and reproductive stage, and individual leaves were captured using a digital imaging system. The RGB mean values of colored images were extracted using the image segmentation algorithms of image processing technique. Consequently, MLR and GBR models were developed to predict leaf RGB mean values based on soil physicochemical measurements and plant age. The GBR model vigorously fitted with RGB mean values throughout the growth stage, with R2 and RMSE values of (R = 0.77, 7.16, G = 0.72, 7.37, and B = 0.70, 5.68), respectively. Furthermore, the MLR model performed moderately with R2 and RMSE values of (R = 0.67, 8.59, G = 0.57, 9.12, and B = 0.56, 6.81) when consecutively predicting RGB mean values in strawberry leaves. Eventually, the GBR model performed more effectively than the MLR model with high-performance metrics. In addition, the leaf color model uses visualization technology to measure growth progress, and it performs well in predicting dynamic changes in strawberry leaf color.

Abstract Purpose This study aimed to achieve successful composting and aeration rate and to optimize the carbon:nitrogen (C:N) ratio to provide favourable conditions for the process. In the current experiment, investigation were made on variations in physico–chemical properties, i.e., temperature, ammonia and carbon dioxide emissions, pH, electrical conductivity (EC), organic matter (OM) and seed germination index (GI%) of composting chicken manure mixed with sawdust and wood shavings under different aeration rates in a closed reactor system. Methods Three cylindrical reactors (total volume, 60 L) were used with three aeration rates of 0.25, 0.50 and 0.75 L min−1 kg−1 OM. The air was dispensed from the bottom of an air compressor. The ambient and compost temperature were monitored thrice daily over 30 days of composting. Results The highest temperatures were 56.9, 55.8 and 48.1 °C, with 0.25, 0.50 and 0.75 L min−1 kg−1 OM aeration rates, respectively. At the end of composting, lowest ammonia and carbon dioxide emissions were observed with 0.25 L min−1 kg−1 OM aeration, indicating that this compost was more stable than other composts. The lowest GI was recorded on day 30 with 0.75 L min−1 kg−1 OM aeration, indicating severe phytotoxicity in the substrate. Maximum OM degradation occurred with 0.25 L min−1 kg−1 OM aeration. Conclusion This study, therefore, suggested that 0.25 L min−1 kg−1 OM aeration in the composing of the chicken manure mixed with sawdust and wood shavings in closed a reactor system provided the most favourable conditions for maturation.

Abstract Background This study aims to measure the output torque and analyze the exhaust elements of a small diesel engine that use the diesel fuel mixed with waste cooking oil to validate the driving and environmental characteristics of this fuel. Methods The fuel used was diesel fuel mixed with 15% of waste cooking oil, a small quantity of additives and was produced with no complicated refining process (WCO15). Continuous driving experiments were conducted for 90 min with it and the results were compared with the data obtained with pure diesel fuel (WCO0). Results As for the engine driving characteristics, engine speed, output torque, and fuel consumption were measured. As for the exhaust, a statistical analysis was conducted on temperature, O2, CO2, NO, and NO2. Conclusions As a result, the torque of WCO15 was 65.6% in comparison with WCO0 at the engine speed of 3600 rpm. In either fuel, the O2 concentration and temperature of exhaust showed a negative correlation, while CO2 and NO concentration showed a positive correlation.

This study proposes a building energy simulation (BES) model of an air-to-water heat pump (AWHP) system integrated with a multi-span greenhouse using the TRNSYS-18 program. The proposed BES model was validated using an experimental AWHP and a multi-span greenhouse installed in Kyungpook National University, Daegu, South Korea (latitude 35.53° N, longitude 128.36° E, elevation 48 m). Three AWHPs and a water storage tank were used to fulfill the heat energy requirement of the three-span greenhouse with 391.6 m2 of floor area. The model was validated by comparing the following experimental and simulated results, namely, the internal greenhouse temperature, the heating load of the greenhouse, heat supply from the water storage tank to the greenhouse, heat pumps’ output water temperature, power used by the heat pumps, coefficient of performance (COP) of the heat pump, and water storage tank temperature. The BES model’s performance was evaluated by calculating the root mean square error (RMSE) and the Nash–Sutcliffe efficiency (NSE) coefficient of validation results. The overall results correlated well with the experimental and simulated results and encouraged adopting the BES model. The average calculated COP of the AWHP was 2.2 when the outside temperature was as low as −13 °C. The proposed model was designed simply, and detailed information of each step is provided to make it easy to use for engineers, researchers, and consultants.

Indoor air temperature (IAT) and indoor relative humidity (IRH) are the prominent microclimatic variables; still, potential contributors that influence the homeostasis of livestock animals reared in closed barns. Further, predicting IAT and IRH encourages farmers to think ahead actively and to prepare the optimum solutions. Therefore, the primary objective of the current literature is to build and investigate extensive performance analysis between popular ML models in practice used for IAT and IRH predictions. Meanwhile, multiple linear regression (MLR), multilayered perceptron (MLP), random forest regression (RFR), decision tree regression (DTR), and support vector regression (SVR) models were utilized for the prediction. This study used accessible factors such as external environmental data to simulate the models. In addition, three different input datasets named S1, S2, and S3 were used to assess the models. From the results, RFR models performed better results in both IAT (R2 = 0.9913; RMSE = 0.476; MAE = 0.3535) and IRH (R2 = 0.9594; RMSE = 2.429; MAE = 1.47) prediction among other models particularly with S3 input datasets. In addition, it has been proven that selecting the right features from the given input data builds supportive conditions under which the expected results are available. Overall, the current study demonstrates a better model among other models to predict IAT and IRH of a naturally ventilated swine building containing animals with fewer input attributes.

This study proposes a multi-span greenhouse Building Energy Simulation (BES) model using a Transient System Simulation (TRNSYS)-18 program. A detailed BES model was developed and validated to simulate the thermal environment in the greenhouse under different design parameters for the multi-span greenhouse. Validation of the model was carried out by comparing the results from computed and experimental greenhouse internal temperatures. The statistical analyses produced an R2 value of 0.84, a root mean square error (RMSE) value of 1.8 °C, and a relative (r)RMSE value of 6.7%, showing good agreement between computed and experimental results. The validated proposed BES model was used to evaluate the effect of multi-span greenhouse design parameters including thermal screens, number of screens, orientation, covering materials, double glazing, north-wall insulation, roof geometry, and natural ventilation, on the annual energy demand of the greenhouse, subjected to Taean Gun (latitude 36.88° N, longitude 126.24° E), Chungcheongnam-do, South Korea winter and summer season weather conditions. Additionally, the proposed BES model is capable of evaluating multi-span greenhouse design parameters with daily and seasonal dynamic control of thermal and shading screens, natural ventilation, as well as heating and cooling set-points. The TRNSYS 18 program proved to be highly flexible for carrying out simulations under local weather conditions and user-defined design and control of the greenhouse. The statistical analysis of validated results should encourage the adoption of the proposed model when the underlying aim is to evaluate the design parameters of multi-span greenhouses considering local weather conditions and specific needs.

In this study, we propose a building energy simulation model of a multi-span greenhouse using a transient system simulation program to simulate greenhouse microenvironments. The proposed model allows daily and seasonal control of screens, roof vents, and heating setpoints according to crop needs. The proposed model was used to investigate the effect of different thermal screens, natural ventilation, and heating setpoint controls on annual and maximum heating loads of a greenhouse. The experiments and winter season weather conditions of greenhouses in Taean Gun (latitude 36.88° N, longitude 126.24° E, elevation 45 m) Chungcheongnam-do, South Korea was used for validation of our model. Nash–Sutcliffe efficiency coefficients of 0.87 and 0.71 showed good correlation between the computed and experimental results; thus, the proposed model is appropriate for performing greenhouse thermal simulations. The results showed that the heating loads of the triple-layered screen were 70% and 40% lower than that of the single-screen and double-screen greenhouses, respectively. Moreover, the maximum heating loads without a screen and for single-, double-, and the triple-layered screens were 0.65, 0.46, 0.41, and 0.34 MJ m−2, respectively. The analysis of different screens showed that Ph-77 (shading screen) combined with Ph-super (thermal screen) had the least heating requirements. The heating setpoint analysis predicted that using the designed day- and nighttime heating control setpoints can result in 3%, 15%, 14%, 15%, and 40% less heating load than when using the fixed value temperature control for November, December, January, February, and March, respectively.

Linear partial least square and non-linear support vector machine regression analysis with various preprocessing techniques and their combinations were used to determine the soluble solids content of hardy kiwi fruits by a handheld, portable near-infrared spectroscopy. Fruits of four species, namely Autumn sense (A), Chungsan (C), Daesung (D), and Green ball (Gb) were collected from five different areas of Gwangyang (G), Muju (M), Suwon (S), Wonju (Q), and Yeongwol (Y) in South Korea. The dataset for calibration and prediction was prepared based on each area, species, and in combination. Half of the dataset of each area, species, and combined dataset was used as calibrated data and the rest was used for model validation. The best prediction correlation coefficient ranges between 0.67 and 0.75, 0.61 and 0.77, and 0.68 for the area, species, combined dataset, respectively using partial least square regression (PLSR) method with different preprocessing techniques. On the other hand, the best correlation coefficient of predictions using the support vector machine regression (SVM-R) algorithm was 0.68 and 0.80, 0.62 and 0.79, and 0.74 for the area, species, and combined dataset, respectively. In most cases, the SVM-R algorithm produced better results with Autoscale preprocessing except G area and species Gb, whereas the PLS algorithm shows a significant difference in calibration and prediction models for different preprocessing techniques. Therefore, the SVM-R method was superior to the PLSR method in predicting soluble solids content of hardy kiwi fruits and non-linear models may be a better alternative to monitor soluble solids content of fruits. The finding of this research can be used as a reference for the prediction of hardy kiwi fruits soluble solids content as well as harvesting time with better prediction models.

Solar renewable energy (SRE) applications are substantial in eradicating the rising global energy shortages and reversing the approaching environmental apocalypse. Hence, effective solar irradiance forecasting models are crucial in utilizing SRE efficiently. This paper introduces a partially amended hybrid model (PAHM) by the implementation of a new algorithm. The algorithm innovatively utilizes bi-directional gated unit (Bi-GRU), autoregressive integrated moving average (ARIMA) and naive decomposition models to predict solar irradiance in 5-min and 60-min intervals. Meanwhile, the models’ generalizability strengths would be tested under an 11-fold cross-validation and are further classified according to their computational costs. The dataset consists of 32 months’ solar irradiance and weather conditions records. A fundamental result of this study was that the single models (Bi-GRU and ARIMA) outperformed the hybrid models (PAHM, classical hybrid model) in the 5-min predictions, negating the assumptions that hybrid models oust single models in every time interval. PAHM provided the highest accuracy level in the 60-min predictions and improved the accuracy levels of the classical hybrid model by 5%, on average. The single models were rigorous under the 11-fold cross-validation, performing well with different datasets; although the computational efficiency of the Bi-GRU model was, by far, the best among the models.

In this study, Energy Recovery Ventilator (ERV) was applied in a pig house model where the internal temperature, relative humidity, and CO2 were analyzed. The experiment was performed in a pig house model where an ERV was installed and two pigs (8 months, ca. 20 kg) were bred. In the pig house model, the internal temperature, relative humidity, and CO2 were divided into three cases and were then measured. In Case (A), ventilating fan and ERV were not used. In Case (B), a ventilating fan was installed and operated. In Case (C), an ERV was installed and operated in the pig house model. In Case (A), the internal temperature between 12:00-17:00 hours was measured at about 23-24°C, which was lower than usual temperature for breeding. For Case (B), the internal temperature was 22-25°C and the relative humidity was about 70-80%. In Case (C), the internal temperature was 29-32°C. Tropical Agricultural Research Vol. 26 (3): 547 – 553 (2015)

In this work, we proposed a Building Energy Simulation (BES) dynamic climatic model of greenhouses by utilizing Transient System Simulation (TRNSYS 18) software to study the effect of use of different thermal screen materials and control strategies of thermal screens on heat energy requirement of greenhouses. Thermal properties of the most common greenhouse thermal screens were measured and used in the BES model. Nash-Sutcliffe efficiency coefficients of 0.84 and 0.78 showed good agreement between the computed and experimental results, thus the proposed model appears to be appropriate for performing greenhouse thermal simulations. The proposed model was used to evaluate the effects of different thermal screens including; Polyester, Luxous, Tempa, and Multi-layers, as well as to evaluate control strategies of greenhouse thermal screens, subjected to Daegu city, (latitude 35.53 °N, longitude 128.36 °E) South Korea winter season weather conditions. Obtained results show that the heating requirement of greenhouses with multi-layer night thermal screens was 20%, 5.4%, and 13.5%, less than the Polyester, Luxous, and Tempa screens respectively. Thus, our experiments confirm that the use of multi-layered thermal screen can reduce greenhouse heat energy requirement. Furthermore, screen-control with outside solar radiation at an optimum setpoint of 60 W·m−2 significantly influences the greenhouse’s energy conservation capacity, as it exhibited 699.5 MJ · m−2, the least energy demand of all strategies tested. Moreover, the proposed model allows dynamic simulation of greenhouse systems and enables researchers and farmers to evaluate different screens and screen control strategies that suit their investment capabilities and local weather conditions.

An experiment was conducted to determine the extent to which the distribution of CO2 depended on the thermal conditions within a greenhouse. The CO2 levels and the change in the horizontal temperature gradient were measured throughout the greenhouse. The appropriate level of CO2 and the concentrated mass of CO2 were analyzed at predetermined points to verify the relation between CO2 and temperature to establish whether a constant distribution existed throughout the facility. As a result, when using the membrane system, the CO2 concentrations external and internal to the greenhouse were measured to be 380~440 ppm and 1020 ppm, respectively. The efficiency of the membrane system was shown to be about 268%. The highest CO2 concentration was about 1000 ppm near the floor, where the temperature was the lowest. In contrast, at a height of 2.50 m, where the temperature was the highest, the CO2 concentration was the lowest at about 400~500 ppm. Tropical Agricultural Research Vol. 26 (4): 714 – 720 (2015)

In the current work, GPS system was used to follow the movements and location of Korean native cattle in open pasture land and to study their pregnancy. The results showed that there were distinct differences in active mass for a day between pregnancy, non-pregnancy, early pregnancy and late pregnancy of the cattle. Based on the experimental results, the pregnancy and non-pregnancy in cattle could be predicted by analysis of the active mass and pattern using GPS. Using such data in real time at stockbreeding farmhouses, the bio-symptoms of Korean native cattle could be judged and subsequent actions can be taken rapidly in urgent situations. Tropical Agricultural Research Vol. 26 (1): 202 – 209 (2014)

In this study, biogas generated from the anaerobic digestion of animal manure was purified and separated and the hollow fiber membrane was prepared by the phase separation of cellulose triacetate (CTA) method to separate the biogas. The product was used in the experiment because the separation of gas by using a gas permeation rate of the hollow fiber membrane was produced. A hollow fiber gas separation membrane module using the hollow fiber membrane in the test was produced and biogas generated in the anaerobic digester was purified using a gas separation membrane module. The separation and purification of the resulting biogas was generated from the livestock manure. The isolation and purification of the resulting biogas was CH4 94.2 %, CO2 92.0 % and recovery efficiency was CH4 102.1 %, CO2 83.5 %. Siloxane 0.1 PPM or less, H2S 3 PPM or less were fed, Dewpoint -20° C below by controlling the biogas supplied to the gas separation membrane module at this time and the operating pressure of the gas separation membrane module was 4~7Bar, in the range of temperature is 15~45 °C. Therefore, it was separated in a high concentration of CO2 92.0 % CH4 94.2 %, compared to the composition of the biogas (CH4 68 %, CO2 28 %, O2 0.6 %, H2S 1 PPM or less, Balance 2.7 %) before carrying out the separation and purification test of biogas produced in the study using the gas separation membrane module. In addition, the CH4 and CO2 transfer efficiency was maximized and saved in the stainless steel tank.Tropical Agricultural Research Vol. 26 (1): 210 – 216 (2014)