The popularity and demand for high-quality date palm fruits (Phoenix dactylifera L.) have been growing, and their quality largely depends on the type of handling, storage, and processing methods. The current methods of geometric evaluation and classification of date palm fruits are characterised by high labour intensity and are usually performed mechanically, which may cause additional damage and reduce the quality and value of the product. Therefore, non-contact methods are being sought based on image analysis, with digital solutions controlling the evaluation and classification processes. The main objective of this paper is to develop an automatic classification model for varieties of date palm fruits using a convolutional neural network (CNN) based on two fundamental criteria, i.e., colour difference and evaluation of geometric parameters of dates. A CNN with a fixed architecture was built, marked as DateNET, consisting of a system of five alternating Conv2D, MaxPooling2D, and Dropout classes. The validation accuracy of the model presented in this study depended on the selection of classification criteria. It was 85.24% for fruit colour-based classification and 87.62% for the geometric parameters only; however, it increased considerably to 93.41% when both the colour and geometry of dates were considered.

The research was conducted during the years 2007–2013, on the base of a long-term study established in 1958, at the Experimental Station Brody (52°26′ N; 16°18′ E), belonging to the Poznań University of Life Sciences. Varieties of potatoes resistant to cyst nematodes were grown in a seven-course crop rotation (potato—spring barley—alfalfa—alfalfa—spring oilseed rape—winter wheat—winter rye) and in continuous monoculture. The presented study from the years 2007–2013 covers the next 8th rotation of the 7-field crop rotation (since 1958). With regard to continuous cultivation, this is the period between the 50th and 56th year of the potato monoculture. The experiment included 11 fertilization variants, of which the following 7 were included in the study: 1—control object without fertilization, 2—manure, 3—manure + NPK, 4—NPKCa, 5—NPK, 6—NP, 7—NK and 8—PK. Every year, mineral and organic fertilization was applied in the following doses per 1 ha: N—90 kg, P—26 kg, K—100 kg, manure—30 t and Ca—0.7 t. Potato cultivation in monoculture resulted in a significant reduction in tuber yield compared to crop rotation and a reduction in the number of tubers per plant and the average weight of one tuber. Manure fertilization, especially in combination with NPK mineral fertilizer, had a more favorable effect on the level of potato yielding and the content of N, P, K and Mg in tubers compared to only mineral fertilization, but decreased the content of dry matter, starch and Ca. The results of long-term experiment indicate that the most effective in potato cultivation is the combined application of both manure and full mineral fertilization (NPK) with the proper sequence of plants (crop rotation).

This paper describes the research aimed at developing an effective quality assessment method for potato tubers using neural image analysis techniques. Nowadays, the methods used to identify damage and diseases are time-consuming, require specialized knowledge, and often rely on subjective judgment. This study showed the use of the developed neural model as a tool supporting the evaluation of potato tubers during the sorting process in the storage room.

The main objective of this study is to develop an automatic classification model for winter rapeseed varieties, to assess seed maturity and damage based on seed colour using a convolutional neural network (CNN). A CNN with a fixed architecture was built, consisting of an alternating arrangement of five classes Conv2D, MaxPooling2D and Dropout, for which a computational algorithm was developed in the Python 3.9 programming language, creating six models depending on the type of input data. Seeds of three winter rapeseed varieties were used for the research. Each imaged sample was 20.000 g. For each variety, 125 weight groups of 20 samples were prepared, with the weight of damaged or immature seeds increasing by 0.161 g. Each of the 20 samples in each weight group was marked by a different seed distribution. The accuracy of the models’ validation ranged from 80.20 to 85.60%, with an average of 82.50%. Higher accuracy was obtained when classifying mature seed varieties (average of 84.24%) than when classifying the degree of maturity (average of 80.76%). It can be stated that classifying such fine seeds as rapeseed seeds is a complex process, creating major problems and constraints, as there is a distinct distribution of seeds belonging to the same weight groups, which causes the CNN model to treat them as different.

An important factor along with the availability of food is its quality. It depends, among other things, on the type of plant protection products used and the method of their application. This manuscript presents research on the possibility of using a shielded band sprayer in field onion cultivation. The shielded band spraying technology presented in this article is the subject of a patent application (application number P.428494-The prototype of the machine was produced in Poland in cooperation with the University of Life Sciences in Poznań). The research consisted in comparing the quantity and quality of the obtained crop, based on various methods of reducing the weed population. The research results indicate that the proposed shielded band spraying technology may affect the food quality (the active substance is not sprayed on onion plants) and profitability of farms (less use of plant protection products).

The purpose of the field experiments was to show possible differences in the quality and size of onion yield and the amount of working liquid used in the technology of the precise application of herbicides. The research material was an onion plantation during three growing seasons in 2015/2016, 2016/2017, and 2017/2018. Cultivation conditions were the same for all plots covered by the experiment. Onions were grown in the row-strip method with a spacing of 150 cm. The experimental factor was the method of weed control on the plots: A—without weeding (control); B—manual weeding; C—conventional herbicide application; D—precise herbicide application. Herbicides were used: Agil 100EC, Pendigan 330EC, Roundup 360SL, Galigan 240EC, Goal 480SC, Lontrel 300SL, Emblem 20WP, Fusilade Forte 150EC, Szogun 10EC, and Lentagran 45WP. The total onion yield did not differ statistically within the accepted confidence interval, regardless of the weeding method in the growing seasons studied. The developed technology allows a reduction in herbicide consumption in onion cultivation by 26% compared to conventional technology, which is of great importance in the aspect of introducing chemical substances into the environment and their accumulation in crops.