Peculiarities of quality formation of apples(Malus domestica Borkh.) of ‘Dmiana’ variety

L. Shevchuk¹²*, Y. Vintskovska², R. Grynyk², S. Babenko², B. Mazur¹ and V. Tonkha²

¹National University of Life and Environmental Sciences of Ukraine, Henerala Rodimtseva Str. 19, UA03041 Kyiv, Ukraine
²Institute of Horticulture of the National Academy of Agrarian Sciences of Ukraine, Sadova Str. 23, UA03027 Kyiv, Ukraine
*Correspondce: l.shevchuk_2021@ukr.net

Abstract:

The appearance, size and taste of fruit are among the main indicators of quality and marketability. These characteristics are determined by the content and ratio of biochemical components, which are influenced by the biotic and abiotic factors involved in cultivation. Studies have shown that the dry matter content of Dmina fruits is independent of rootstocks and planting schemes. However, the sugar content was significantly higher in fruits grown on M.26 rootstock with a planting scheme of 4.0×1.0 m and significantly lower in fruits grown on M.9 rootstock with the same planting scheme: 11.3% and 9.8%, respectively. Titratable acids were found in fruits grown on rootstock M.9 with a planting scheme of 4.0×0.5 m. In addition to the influence of planting scheme and rootstock, weather conditions also affected the biochemical content of Dmina fruits. Cool nights during the initial growth and development period contributed to dry matter accumulation, but negatively affected sugar synthesis. The correlation coefficients for all rootstock variants were higher than 0.703 and 0.911, respectively. The content of titratable acids depended significantly on the average daily and night-time air temperatures in the month before harvesting; this dependence was indirect and the correlation coefficients were high in all variants with rootstocks.

Key words:

dray matter, Malus, sugars, titrated acids

Apple scab detection using CNN and Transfer Learning

S. Kodors¹*, G. Lacis², O. Sokolova2,V. Zhukovs¹, I. Apeinans¹ and T. Bartulsons²

¹Rezekne Academy of Technologies, Faculty of Engineering, Institute of Engineering, Atbrivoshanas Str. 115, LV-4601 Rezekne, Latvia
²Institute of Horticulture, Graudu Str. 1, LV-3701 Ceriņi, Krimūnu pagasts, Dobeles novads, Latvia
*Correspondence: sergejs.kodors@rta.lv

Abstract:

The goal of smart and precise horticulture is to increase yield and product quality by simultaneous reduction of pesticide application, thereby promoting the improvement of food security. The scope of this research is apple scab detection in the early stage of development using mobile phones and artificial intelligence based on convolutional neural network (CNN) applications. The research considers data acquisition and CNN training. Two datasets were collected – with images of scab infected fruits and leaves of an apple tree. However, data acquisition is a time-consuming process and scab appearance has a probability factor. Therefore, transfer learning is an appropriate training methodology. The goal of this research was to select the most suitable dataset for transfer learning for the apple scab detection domain and to evaluate the transfer learning impact comparing it with learning from scratch. The statistical analysis confirmed the positive effect of transfer learning on CNN performance with significance level 0.05.

Key words: