The change in landscape is a never-ending process. In this article information regarding watermills and small-scale hydroelectric power plants historical development in Latvia has been summarized. The research was conducted from September 2010 till April 2011 with the aim of summarizing information regarding impacts to landscape from changes occurring from 12th century till 21st century. The research had a detailed view about the usage history of the watermills, small-scale hydroelectric power plants buildings, and energy producing constructions. The fundamental changes in energy producing mechanisms and legislation regulations changes that have an impact on river open space landscape and on landscape use in surrounded territories of watermills and small-scale hydroelectric power plants landscape were analyzed and studied carefully. The territories were described and analysed using historical, monographic, and comparative methods. The paper gives possible descriptive historical classification of these industrial landscape elements. The historical progress and legislation evolution until the 21st century has also been summarized.

Multiple information systems have been developed during the last decade to gain more from collaboration, knowledge management and ideas. One type of such tools is the idea management systems (IMS) – a manageable systematic tool to generate and evaluate ideas. However, there is a lack of research which explores what web-based IMS are, and how they materialize practically. To fill the gap, the paper aims to create classification and application description of web-based IMS by adapting the theoretical and empirical research approaches. To achieve this aim, first, scientific papers, book chapters, and proceedings focused on the idea management and IMS were analysed using a systematic literature review method and content analysis technique. Based on the analyses, several possible classifications of IMS criteria were found. Second, commercially available web-based IMS evaluation was conducted to verify the criteria and to add data-based classification criteria. Analysis of IMS has helped to characterize parities and disparities of web-based IMS. Results prove that IMS could be classified by their application focus – as ‘active’ and ‘passive’. Dominant type is the active IMS. IMS could also be classified by the sources involved in the idea management – internal, external or mixed IMS. The main structural features of the web-based IMS are idea generation, idea evaluation, and idea retention. Results prove that there are no important differences between theoretical and empirical research results. .

Yellow rust caused by Puccinia striiformis is a significant wheat disease in cereal growing areas worldwide. On average, yellow rust can cause 50% big yield damages resulting in economic losses. Yellow rust damages wheat leaves, leaf sheaths, awns, and glumes. Puccinia striiformis is divided into four lineages – P. striiformis sensu stricto, P. pseudostriiformis, P. striiformoides, P. gansensis. Different races of yellow rust have been determined. After 2000 three new aggressive races – ‘Warrior’, ‘Kranich’ and ‘Triticale aggressive’ have been identified. New races are characterized by shorter latent period, extended spore germination and tolerance to a high temperature in comparison with the races determined before 2000. These characteristics allowed the new races to replace races dominant before 2000. Yellow rust is a biotrophic heteroecious fungus with a complicated life cycle. For successful development, Puccinia striiformis requires cereals as primary hosts and Berberis spp. as alternate hosts. The history of studies regarding yellow rust is more than two hundred years old but only in 2010 the ecidiospores of yellow rust were found on the alternate host Berberis spp. Two types of resistance – seedling (or all-stage) resistance and adult plant resistance (APR) were discovered. Since 2000 multiple severe epidemics of yellow rust have been observed in cereal growing areas with warmer climate. In recent years, the incidence of yellow rust in Latvia has increased. Particular studies about the biology, distribution, and races of Puccinia striiformis in Latvia are necessary. This article summarizes the information about the classification, biology and harmfulness of the yellow rust.

Social entrepreneurship plays an increasingly important role in tackling socio-economic problems. It has gained recognition in Latvia among politicians, academicians and social entrepreneurs; consequently, the number of social enterprises increased in the country, yet there is a lack of research studies on social enterprise models and their classification. Accordingly, the research aim is to examine the theoretical models of social enterprises in Latvia. In the scientific literature, there is no strict classification of social enterprises, but based on different criteria, it is possible to distinguish several types or models. In Latvia, there are relatively few social enterprises; for this reason, it is quite difficult to categorise them. However, social enterprises are divided by sector, field of activity, target group, scale of activity and other criteria. The research stresses the following key social entrepreneurship models: the Selfinitiative Model, the Government Participation Model, the Municipal Participation Model and the Company-initiated Development Model. These models are based on two key criteria – support intensity and taking the initiative in establishing and developing a social enterprise.

In this study, forest type mapping data set taken from UCI (University of California, Irvine) machine learning repository database has been classified using different machine learning algorithms including Multilayer Perceptron, k-NN, J48, Naïve Bayes, Bayes Net and KStar. In this dataset, there are 27 spectral values showing the type of three different forests (Sugi, Hinoki, mixed broadleaf). As the performance measure criteria, the classification accuracy has been used to evaluate the classifier algorithms and then to select the best method. The best classification rates have been obtained 90.43% with MLP, and 89.1013% with k-NN classifier (for k=5). As can be seen from the obtained results, the machine learning algorithms including MLP and k-NN classifier have obtained very promising results in the classification of forest type with 27 spectral features.

This study investigates the distribution and carbon content of organic soils in Latvia, leveraging machine learning techniques alongside remote sensing and National Forest Inventory (NFI) data to enhance the precision of organic soil mapping. Our approach integrates data from various sources, including airborne laser scanning (ALS) data, digital elevation models (DEM), depth-to-water (DTW) and wet area maps (WAM), and historical organic soil data. By classifying over 24,000 soil probing measurements across Latvia into distinct peat layer thickness categories, we develop a machine learning model that categorizes the thickness of the organic layer with notable accuracy. Our findings indicate that the model, particularly when employing the xgbTREE algorithm and over-sampling method, successfully identifies areas with peat layers thicker than 40 cm, demonstrating a significant improvement over traditional mapping methods. The study reveals an underestimation of organic soil coverage in Latvia by previous estimates, suggesting a broader distribution than recognized, with the model achieving an accuracy of 0.86 and a kappa value of 0.67. This research not only underscores the efficacy of integrating machine learning and remote sensing for soil mapping but also highlights the critical role of accurate data and models in determining organic soil distribution. The insights gained from this study are vital for policy-making and environmental planning, offering a more detailed understanding of Latviaʼs peatland resources and their conservation needs.

The paper presents the results of the research on oil spill detection using machine learning methods such as Support Vector Machine (SVM) for classification of infrared images and Logistic regression for water quality parameters. This paper focuses on real time detection of oil spills using infrared images and water quality data obtained by RPA equipped with multi-sensor payload. The developed Naïve Bayes (NB), SVM and Logistic regression classification models for prediction of oil spill have been successfully tested in real experiment conditions. All developed classification models were tuned using grid search method and main tuning parameters to determine the optimal parameters. The proposed complex algorithm for identification of oil spills using infrared images and water quality parameters is evaluated by experiments in real environment conditions. The proposed algorithm is based on the binary SVM and NB classification of infrared images and the classification of water quality parameters using the machine learning method logistic regression allows to rapidly and with high accuracy identify any oil pollution of water. Proposed complex algorithm achieves higher accuracy and efficiency; moreover, the developed machine learning models will further reduce the probability of human error and save man-hours of work.