In this study, blackberry fruits were dried in a pilot-scale hot-air dryer to identify the drying characteristics of the fruits. The air velocity was set as 1 m·s ⁻¹ , and the temperature range was set as 54 to 75 °C. Fick’s law of diffusion was used to describe heat transfer during the decreasing rate period. Effective diffusivity values were calculated, and the Arrhenius constitutive model was used to describe the temperature dependence of these values. The Page, logarithmic, approximation of diffusion, two-term, and Midilli et al. models were used to fit the experimental data. A nonlinear regression analysis was used to calculate rate constants and model coefficients. The present findings revealed that among the tested models, the Midilli et al. model best described the experimental data; therefore, it was concluded that the model could be used to describe the drying characteristics of blackberry fruits.

Traditional agricultural methods, which are still adopted today, depend on many factors. Food production processes face serious risks, such as limited clean water resources and supplements such as phosphorus, in addition to weather conditions due to climate change, the distribution of pests and soil-borne diseases, and increasing demand due to population growth, which can lead to famine. In particular, there may be cases where the soil nutrient content is insufficient and the soil structure is not suitable for cultivation. Therefore, soilless farming techniques have become popular, where the producer is entirely in control of the process. Additionally, many factors affect conventional farming techniques, including restrictions on land suitable for agriculture, climate-increased transportation costs from production areas to central regions, and environmental sanctions. Therefore, soilless farming techniques and the use of technology have rapidly gained importance. The use of technology has two crucial parameters: hardware and software. Today, no device can simultaneously control the electrical conductivity, pH, dissolved oxygen, and temperature of the solution in systems cultivated with soilless farming techniques. The present study was conducted to find a solution to the needs in this area. An automatic control system was developed and tested, employing a microcontroller, various sensors, appropriate open-source codes, and original software. Electrical conductivity (EC), power of hydrogen (pH), dissolved oxygen (DO), and temperature (T) values were determined successfully by the developed control system. The area where the experiment was conducted is a fully controlled and closed area established within Ankara University. The ambient temperature was 22 °C and the humidity was 39%. The coordinates of the experimental area are 39.962013 and 32.867491. Three different artificial lighting intensities (165.6 µmol m⁻² s⁻¹, 248.4 µmol m⁻² s⁻¹, and 331.2 µmol m⁻² s⁻¹) and a desired photoperiod duration can be applied to the site.

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.

One important goal of precision horticulture (PH), as well as precision agriculture (PA), is to measure and manage spatial and temporal variation in orchards. In this study, temporal and spatial analysis of yields were carried out over 2 years for a 0.5-ha apple orchard (at the Haymana Research Station of Ankara University, Turkey, from 2017 to 2018) to determine the variability of yields over time and included seven apple varieties: ‘Royal Gala’, ‘Red Chief’, ‘Braeburn’, ‘Mondial Gala’, ‘Jonagold’, ‘Fuji’, and ‘Mitch Gala’. To achieve this, yield data for two different years were analyzed for mean yield, temporal variance, and cv in terms of spatial and temporal stability, and their yield maps were produced. The results showed that ‘Jonagold’, ‘Braeburn’, and ‘Red Chief’ varieties yielded less than the average yield, whereas the other varieties produced average yields when the yield from 2 years was taken into account. Calculation of the values for determining temporal stability over time resulted in all existing varieties being identified as stable over time. For example, the ‘Jonagold’ and ‘Red Chief’ varieties showed 100% stability in terms of temporal variance. Results also showed that the ‘Gala’ varieties were stable for 2 years and produced high yields, whereas the other varieties were specified as stable and low yielding when spatial and temporal variability was considered in combination.

Toprağın elektriksel iletkenliği, tekstür, tuzluluk, nem, derinlik gibi toprak parametrelerinin tespit edilmesinin yanında günümüzde hassas tarım uygulamalarında da kullanılmaya başlamıştır. Toprağın elektriksel iletkenliği ile ürün verimi ve protein içeriği ilişkilidir. Geleneksel yöntem ile toprağın elektriksel iletkenliğinin tespiti çok fazla zaman almakta ve yüksek maliyetlidir. Bu nedenlerden dolayı günümüzde toprağın elektriksel iletkenliğinin ölçümünde kullanılan çok çeşitli sensörler geliştirilmiştir. Bu sensörlerin amacı topraktan olabildiğince hızlı, kolay, güvenilir ve toprak yapısına zarar vermeden veri toplamaktır. Bu çalışmanın amacı toprağın elektriksel iletkenliğinden faydalanarak buğday bitkisinin verim ve protein içeriğinin değişimini saptamaktır. Bu çalışma ile elde edilen veriler ile ürün verimi ve protein içeriği arasında önemli ilişkiler tespit edilmiştir. Araştırma sonucu arazinin elektriksel iletkenlik değerleri ile verim değerleri arasındaki ilişkiler (R2) sırasıyla Bezostaja-1 çeşidi için 0,8152, Gün-91 çeşidi için 0,8115, Sagittario çeşidi için 0,7775, Altıntaş-95 çeşidi için 0,7380 ve Gönen-98 çeşidi için 0,8852 olarak bulunmuştur. Arazinin elektriksel iletkenlik değerleri ile protein içerikleri arasındaki ilişkiler (R2) ise sırasıyla Bezostaja-1 çeşidi için 0,8375, Gün-91 çeşidi için 0,8637, Sagittario çeşidi için 0,8561, Altıntaş-95 çeşidi için 0,8598 ve Gönen-98 çeşidi için 0,8852 olarak bulunmuştur.

Chlorophyll meters manage both the amount and duration of nitrogen fertilizer application based on the principle that the chlorophyll or nitrogen content of plants should be maintained throughout their development. For smallholders in developing countries, the use of a hand-held meter to manage nitrogen fertilizer in rice and wheat is the most popular method. The adoption of nitrogen management strategies based on close sensing using chlorophyll meters and optical sensors will largely depend on the inclusion of specific economic analysis in future research. The importance of using sensors and chlorophyll meters for nitrogen fertilizer management depends on how successful current practices have been. In this study, five different nitrogen rates (0, 80, 120, 160, 200 kg N ha-1) were applied to two different wheat varieties, and the effect of these different nitrogen rates on wheat protein content was investigated in a randomized block design. A quadratic polynomial model described the relationship between protein content and nitrogen rates.