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.

Agriculture is a unique sector, because it is associated with negative outcomes stemming from imperfectly predictable biological and climatic variables. These variables include natural adversities (for example, pests and diseases), climatic factors are not within the control of agricultural producers. So in agriculture it is very important to identify and evaluate risk, only then decisions made in farm will bring profit and other positive results. Scientific literature distinguishes a lot of methods for risk evaluation, but it is not clear what methods could be adapted in agriculture sector. This article presents main risk types in agriculture and their features as well as introduces most popular risk evaluation methods and their possible use in assessing risks in agriculture.

The aim of the research was to assess food safety risks in catering establishments. To analyse food safety risks during production and distribution of ready-to-eat food in catering establishments, internal database of the Food and Veterinary service of the Republic of Latvia was used. Catering establishments, food items, technological processing methods, as well as environmental objects were encoded to perform mathematical analyses of state's monitoring and surveillance data. The probability of the microbiological risk factors coliforms and S.aureus in food and environmental samples as well as the total plate count in ready-to-eat food was assessed to forecast common risks in catering establishments and to set hygiene management priorities in frame of HACCP procedures. For estimation of individual risk factors, results were statistically analysed using SPSS statistical package and a p is less than 0.05 was considered to be statistically significant. The significant differences were established between certain bacteria presence in food and such factors as food group, method of technological processing, and type of catering establishment. The results on bacterial contamination of food correlate with the results on contamination of environmental objects. The research suggests that control of food safety risks that is built on testing of pathogenic bacteria is not effective enough to evaluate actual level of implementation of hygiene measures in catering establishments. Risk assessment during routine monitoring both in state's official control level and catering establishments' self-control level should be concentrated on testing of hygiene indicator microorganisms rather than pathogenic microorganisms to establish and prevent food safety risks.

Company - oriented risk analyses is the necessary precondition to establish, validate and improve HACCP procedures in catering enterprise. In catering area no microbiological criteria exist for ready-to eat food in both European and Latvian level. The objective of the study was to apply risk assessment approach to evaluate microbiological risks during food preparation processes in school catering establishments. The aim of the author's research was to assess the level of microbiological contamination of food as well as the changes of microbial contamination during technological processing of food to motivate the necessity for controlling of food contamination levels in frame of HACCP procedures. It was concluded that no significant risk in consumption of cooked minced meat food if cooking temperature is adequate and food is stored at correct temperature after cooking. The storage of salads in ambient air temperature causes a significant increase of bacterial contamination due to high initial contamination level that may create a serious risk in case of pathogenic bacteria. On the basis of research it was concluded that microbiological investigation should be a recommended way to test step-by step the performance of technological processes because the hygiene situation is specific to each catering establishment and safety of the end-products may vary considerably. Microbiological testing of food and environmental samples could be a helpful tool for development and validation of HACCP procedures to assess potential risks and to establish critical limits for managing of technological steps in school food service area.