Deep learning (DL) and computer vision applications in precision agriculture have great potential to identify and classify plant and vegetation species. This study presents the applicability of DL modeling with computer vision techniques to analyze the nutrient levels of hydroponically grown four lettuce cultivars (Lactuca sativa L.), namely Black Seed, Flandria, Rex, and Tacitus. Four different nutrient concentrations (0, 50, 200, 300 ppm nitrogen solutions) were prepared and utilized to grow these lettuce cultivars in the greenhouse. RGB images of lettuce leaves were captured. The results showed that the developed DL’s visual geometry group 16 (VGG16) and VGG19 architectures identified the nutrient levels of lettuces with 87.5 to 100% accuracy for four lettuce cultivars, respectively. Convolution neural network models were also implemented to identify the nutrient levels of the studied lettuces for comparison purposes. The developed modeling techniques can be applied not only to collect real-time nutrient data from other lettuce type cultivars grown in greenhouses but also in fields. Moreover, these modeling approaches can be applied for remote sensing purposes to various lettuce crops. To the best knowledge of the authors, this is a novel study applying the DL technique to determine the nutrient concentrations in lettuce cultivars.

Appropriate microclimate conditions in broiler housing are critical for optimizing poultry production and ensuring the health and welfare of the birds. In this study, spatial variabilities of the microclimate in summer and winter seasons in a mechanically ventilated broiler house were modeled using the computational fluid dynamics (CFD) technique. Field measurements of temperature, relative humidity, and airspeeds were conducted in the house to compare the simulated results. The study identified two problems of high temperature in summer, which could result in bird heat stress and stagnant zones in winter, and simulated possible alternative solutions. In summer, if an evaporative cooling pad system was used, a decrease in temperature of approximately 3 °C could be achieved when the mean air temperature rose above 25 °C in the house. In winter, adding four 500-mm circulation fans of 20-m spacing inside the house could eliminate the accumulation of hot and humid air in the stagnant zones in the house. This study demonstrated that CFD is a valuable tool for adequate heating, ventilation, and air conditioning system design in poultry buildings.

In recent years, computational fluid dynamics (CFD) has become increasingly important and has proven to be an effective method for assessing environmental conditions in poultry houses. CFD offers simplicity, efficiency, and rapidity in assessing and optimizing poultry house environments, thereby fueling greater interest in its application. This article aims to facilitate researchers in their search for relevant CFD studies in poultry housing environmental conditions by providing an in-depth review of the latest advancements in this field. It has been found that CFD has been widely employed to study and analyze various aspects of poultry house ventilation and air quality under the following five main headings: inlet and fan configuration, ventilation system design, air temperature–humidity distribution, airflow distribution, and particle matter and gas emission. The most commonly used turbulence models in poultry buildings are the standard k-ε, renormalization group (RNG) k-ε, and realizable k-ε models. Additionally, this article presents key solutions with a summary and visualization of fundamental approaches employed in addressing path planning problems within the CFD process. Furthermore, potential challenges, such as data acquisition, validation, computational resource requirements, meshing, and the selection of a proper turbulence model, are discussed, and avenues for future research (the integration of machine learning, building information modeling, and feedback control systems with CFD) are explored.

This study predicted the daily evapotranspiration of eggplant (Solanum melongena L.) under full and deficit irrigation in the Bafra district of Samsun province, Turkey, using machine learning methods. Artificial neural networks (ANNs), deep neural networks (DNN), M5 model tree (M5Tree), random forest (RF), support vector machine (SVM), k-nearest neighbor (kNN), and adaptive boosting were investigated as machine learning approaches. Determination of evapotranspiration in this study consists of three methods: (i) The reference evapotranspiration (ET_o) was obtained from the Food and Agriculture Organization-56 Penman–Monteith equation, (ii) the values of evapotranspiration (ET_c) calculated by multiplying the reference evapotranspiration by the crop coefficient (K_c), and (iii) the values of evapotranspiration (ET_a) measured using soil water balance between successive soil water measurements as the outputs. The model’s performance in ET_o estimation was higher when minimum and maximum temperature (T_max and T_min), wind speed (u₂), average relative humidity (RH_avg), solar radiation (R_s), and days of the year were used as inputs. The best performance was obtained in the ANN model with a coefficient of determination (R²) value of 0.984, a mean absolute error (MAE) of 0.098 mm d⁻¹, a root-mean-square error (RMSE) of 0.153 mm d⁻¹, and Nash–Sutcliffe efficiency of 0.983. The model’s performance in ET_c estimation was significantly improved with the addition of leaf area index (LAI) and crop height (h_c) to the climate parameters (MAE and RMSE values decreased by 22.6 and 23.2%, respectively). The accuracy of ET_c estimation for some plant traits (h_c and LAI) and average temperature (T_avg) was sufficient. The best statistical performance in estimating ET_a was obtained by the RF model (T_avg, u₂, RH_avg, and R_s) using climate parameters. DNN proved to be the least successful model compared to the other six models in predicting ET_o, ET_c, and ET_a.