High oil content microalgae are a source for biofuel production. They can be produced in open ponds or closed photobioreactors. To efficiently grow such microalgae, illumination for photosynthesis, CO2 consumption, and the pH and nutrient content of the growth medium must be monitored and precisely controlled. In a closed photobioreactor, illumination is the most critical parameter because it is the most expensive factor of algae production and must be operated 24 h per day. In this research, Chlorella kessleri (UTEX 398) microalgae were grown in photobioreactors. All parameters were identical, except the source and intensity of the illumination. The light sources included red light-emitting diodes (LED), blue LED, and fluorescent lights. Growth of the microalgae was observed for seven days and the effects of the three illumination sources on cell count, cell weight, and cell size were determined. In the first experiment, in which the current of all three light sources was the same, red LED produced the highest number of cells with the highest weight while blue LED light produced the largest cells. In the second experiment, in which the light intensity was the same for all three light sources, the highest weight was again achieved with the red LED. Thus, we suggest that most advantageous production system may be to use a red light initially to produce the desired cell concentration, then switch to a blue light to increase cell size.

Tomato is one of the most important vegetables in the world. Presence of diseases and pests in the growing area significantly affect the choice of variety in tomato. Early-stage diagnosis plays an important role in determining whether the tomato is subject to effective and economical chemical, mechanical and biological controls, and internal and external quarantine. In this study, deep learning was used to diagnose some diseases in tomatoes. For this purpose, a novel deep CNN-based approach and some Keras models including DenseNet201, InceptionResNetV2, MobileNet, VGG16 architectures were used. Early, middle, and late stages of 18.456 images of Bacterial Spot, Early Blight, Leaf Mold, Septoria Leaf Spot, Target Spot, Mosaic Virus, Yellow Leaf Curl Virus and healthy leaves were examined. The experimental results showed that the custom CNN model produced 99.82% training accuracy. We recommend this model in terms of monitoring and diagnosing of tomato diseases. The results obtained with this study can be used in robotic spraying and harvesting operations.

The purpose of this study was to investigate the possibility of solar-powered thermoelectric elements (Peltier) to harvest water from the atmosphere. An Arduino-controlled model capable of harvesting water from air was designed and used in laboratory experiments. The developed prototype system was analyzed by using a package program using computational fluid dynamics. During the experiments, temperature and humidity data were recorded on a computer. We found that the Peltier used in the system developed temperature and relative humidity differences between the inlet air and outlet air from the system. These differences in temperature and humidity created an environment for harvesting water by condensing the humidity in air.

Classification of hazelnuts is one of the values adding processes that increase the marketability and profitability of its production. While traditional classification methods are used commonly, machine learning and deep learning can be implemented to enhance the hazelnut classification processes. This paper presents the results of a comparative study of machine learning frameworks to classify hazelnut (Corylus avellana L.) cultivars (‘Sivri’, ‘Kara’, ‘Tombul’) using DL4J and ensemble learning algorithms. For each cultivar, 50 samples were used for evaluations. Maximum length, width, compression strength, and weight of hazelnuts were measured using a caliper and a force transducer. Gradient boosting machine (Boosting), random forest (Bagging), and DL4J feedforward (Deep Learning) algorithms were applied in traditional machine learning algorithms. The data set was partitioned into a 10-fold-cross validation method. The classifier performance criteria of accuracy (%), error percentage (%), F-Measure, Cohen’s Kappa, recall, precision, true positive (TP), false positive (FP), true negative (TN), false negative (FN) values are provided in the results section. The results showed classification accuracies of 94% for Gradient Boosting, 100% for Random Forest, and 94% for DL4J Feedforward algorithms.