The main objective of this study is to demonstrate the use of artificial neural network (AN) modelling tool to predict the risk of phosphorus (P) loss from the fields to nearest water body. The attention is drawn to AN as an alternative approach to the P index calculation for prediction of the P losses. The specific tasks of this study were to determine risk classes of P loss by linking together source and transport factors that accelerate P losses and to evaluate AN model performance for predicting risk classes via nutrient transport. AN was trained with a Levenberg-Marquardt algorithm, and Scaled Conjugate Gradient algorithm was used to estimate the possible risk of P losses from agricultural land. Two small agricultural watersheds in Auce and Bauska were chosen to determine field parameters, and expert's evaluation was used for description of the risk classes' of P loss. Finally these values were used as inputs for the neural network model. The model was trained and validated by assessing its predictive performance on a testing set of data excluded from the training set. The research results highlight the capabilities of AN to predict risk for a particular field and suggest that future research on application of other algorithms is required.

The changes of areas of eight tree species in Lithuania during the past century were analysed. Aiming to apply the different approaches in forest studies, the Exponential smoothing method for forecasting the changes of the tree areas for the 25 years was used. The data dating from 1922 was analyzed as a time series. The descending trend was identified for Scots pine (Pinus sylvestris L.) and European ash (Fraxinus excelsior L.) and increasing trend – for Norway spruce (Picea abies (L.) H. Karst.), common oak (Quercus robur L.), birch species (Betula pubescens Ehrh. and Betula pendula Roth), black alder (Alnus glutinosa (L.) Gaertn.), European aspen (Populus tremula L.) and grey alder (Alnus incana (L.) Moench). The Exponential Trend with Multiplicative Seasonality (ET-MS) model was fitted for almost all investigated tree species with exception of European ash. For the latter species, the Damped Trend with Multiplicative Seasonality (DT-MS) model was chosen. Mean absolute percentage error of the model in all cases did not exceed 2%.

The development of rural territories in the European Union (EU) plays an essential role, and agricultural development can largely contribute to this process. To project agricultural trends, a number of models have been developed in the EU, while in Latvia the LASAM model was developed in 2016 to generate projections for agricultural sector development in Latvia until 2050. In 2017, LASAM was extended by a module for socio-economic assessment that allows projecting productivity for various types of farming. The research aim is to develop a model for productivity simulation for various specialisation types of farms in order to project their development in Latvia. To achieve the aim, two specific research tasks were set: 1) to develop a model for productivity simulation for various specialisation types of farms in Latvia; 2) to identify the key results of the simulation of productivity for various specialisation types of farms in Latvia. The research found that in the period 2005 – 2016 the value added of agriculture tended to slightly increase in Latvia, whereas an opposite trend was observed for the number of persons employed in agriculture, which tended to decrease in the period of analysis. Both trends determine the agricultural productivity trend as well. A projection of productivity measured as value added per AWU for various farming types in Latvia by means of the LASAM model has revealed that it is different, and the highest level of productivity in 2030 and 2050 is projected for granivores as well as field crop farms.

The aim of the article was to develop formulas, which can be used to model forecasts of production and economic effects of irrigated faba bean (Vicia faba var. minor), depending on drought severity level in a growing season. For the analysis we used data of ten-year (2005 – 2014) production effects of irrigated faba bean and indices calculated on the basis of meteorological data from the measuring point set in the vicinity of the experimental site in region of Bydgoszcz city, central Poland. Based on them, the most relevant relationships between irrigation productivity and chosen drought indices, calculated for a period of high water needs of the plant, were searched. Presented results have demonstrated that the non-irrigated faba bean yields depended significantly on drought severity level and showed very high variability in time. Irrigation contributed to a significant 49% increase in yields and their stability in the years. Due to this treatment, the coefficient of variation of the yield decreased from 55.1 to 19.6%. The production effects of irrigation depended significantly on moisture conditions over the period of high water needs of faba bean. In wet seasons, the increases in yields due to irrigation were insignificant and about three-fold lower, while in the dry periods – more than a half higher (57%) than the average increases. The results presented in the work are of great importance because they can be used to model forecasts of production, as well as to plan the development of irrigation systems in the given area.

One of the promising areas of creating a competitive market environment is the development of organic production. Under martial law, organic producers faced not only problems related to the export of organic products, but also other challenges caused by the military actions of the aggressor. The purpose of the study is to assess the impact of the war on the export of organic products by domestic agricultural enterprises. The article reveals the general state and changes in the dynamics of export of organic agricultural products by domestic organic producers; the challenges faced by producers of organic products in the conditions of martial law are presented; the impact of the war on the export of organic agricultural products by producers of organic products is determined; the forecast of the value of agricultural products exported by Ukraine for the period until 2025 was made (with the help of retrospective and statistical research methods); directions for supporting exporters of organic products for their development in the future are given. As a result of the authorsʼ research, it should be noted that export operations of organic products will increase, which will allow to ensure the strategic goals of Ukraine regarding development in the market environment.

Weather conditions in Latvia are very favourable for the development of potato late blight caused by Phytophthora infestans (Mont) de Bary. The control of potato late blight can be performed using different approaches: standardised technology, prognoses of the first infection and prognoses of the progress of disease development. The negative prognosis model Negfry is based on the last two mentioned above. For the control of potato late blight in Latvia mainly has been used - standardised technology. The first field treatment was made during the row closing or according to prognoses. Regular treatments were made each 8-14 days. The use of NegFry model started in Latvia in 1998. Local varieties and weather data have been used for the trial. For the control of potato late blight in field trials standartised fungicide application was compared with the NegFry model and the untreated variant. The major task of the use of the model is possibility to reduce the number of fungicide treatments. The NegFry model helps to realise an integrated plant protection system, which decreases fungicide application and increases economical efficiency.

The epidemiology of barley yellow dwarf disease is highly complex, involving numerous interactions between the abiotic environment and the crop, virus and vector - components of the disease. Barley yellow dwarf is the most economically damaging virus disease of grass and cereal crops worldwide. The disease identified as BYD has been reported in all countries in Europe causing losses on barley and oats, wheat and maize; losses on grasses are recognized but more difficult to quantify. There are five different strains of viruses causing BYD disease and all of them induce similar symptoms of chlorosis and stunting in graminaceous hosts. This report represents an overview of system components and their interactions in the epidemiology of barley yellow dwarf disease. As the main components considered here are aphids - (the only vectors of these viruses), host plants and viruses causing BYD disease. Some aspects of interactions between these components are also discussed.

Not only does construction activity in the regions play a crucial role in the regional development, as it not only provides employment opportunities and thus contributes to the well-being of the population, but also creates favourable conditions for access to modern housing and requires the mobility of human resources to the regions. At the same time, construction in regions and rural areas often implies more difficult conditions than in urban environments, which are associated with both funding opportunities and working conditions. The availability of financial investments to the private sector is limited for the construction of housing outside Riga and Pierīga region, which significantly reduces construction opportunities in the regions of Latvia. The study evaluates the possibilities of obtaining new housing in the regions of Latvia, analyses the trends in construction volume and costs from 2015, modelling forecasts until 2026. The study looks at various economic instruments that could contribute to the development of construction and new housing in the regions. The study uses surveys of municipalities, entrepreneurs and experts in the field of construction, in-depth interviews, focus groups and statistical data processing methods. It has been concluded that Latvian entrepreneurs tend to postpone investments or invest only in the economically strongest moments, which further aggravates the gap between urban and rural areas. The trends identified in the study indicate a possible further direction of stagnation or recession in the construction sector of new housing in the regions of Latvia, which will directly affect regional development in the next five years. The study highlights the necessary interventions for more productive regional housing stock cohesion.

The objective of this research was to design an economically efficient logistics management model for fuel retail enterprises to improve their competitiveness. In the current global market situation, fuel retail enterprises face various challenges, such as sharp increase in raw material price, intense market competition, high price sensitivity, low profitability, and significant logistics costs. By combining theoretical and practical insights, an improved logistics management model was designed, which provides significant competitive advantage for fuel retail enterprises. The designed model incorporates and integrates three distinct logistics arrangements, resulting in considerable advantages for fuel retail enterprises. These advantages include a reduction in logistics costs and increased independency from the fluctuating logistics service expenses. To determine the economic efficiency of the designed logistics management model, it was validated by using data obtained from a fuel retail enterprise based in Sweden. Results of the research indicated that the fuel retail enterprise can anticipate an annual reduction in logistics costs ranging from 2.91% to 3.32% from the implementation of the improved logistics management model. On top of that, the developed logistics management model is projected to be economically viable until 2027, assuming the continuation of the current market trends and conditions. The findings of the research suggest that other fuel retail enterprises may also benefit from implementation of the designed model in the current market conditions.