Search

The relevance of this study is due to the challenges of the global pandemic, which has led to the large-scale development of education digitalization. In this regard, this article is devoted to revealing the features of remote learning in the context of a global pandemic, identifying the risks and benefits of digital learning. The article reveals the discursive content of the counter-pandemic vector of distance learning for University students; defines the classification of risks and advantages of large-scale digitalization of students' remote learning. Based on the results of the study, the authors justified the consolidated model of students distance learning, the counter-pandemic vector of which is a large-scale digitalization of the University educational process. The effectiveness of the model is proved by the results of its use in the process of large-scale digitalization of students' remote learning in the context of a global pandemic. The materials of the article have practical application and can be useful in the development and implementation of digital educational complexes. They are recommended to teachers and students of the University, methodologists, curators, Tutors.

This article is aimed at identifying the peculiarities of students' attitude to distance education. As a leading method, the questionnaire method was used, which made it possible to identify the students' positive and negative attitudes regarding distance learning more effectively. The article considers students' ideas about distance learning, identifies the positive and negative aspects of the distance learning process. The authors of the article in the process of research revealed that many students of various fields of study are interested in participating in distance courses, but within the framework of mastering a second education. Some students note the usefulness of distance courses, the use of their materials at any time, and the convenience of going back to the materials they have completed at any time to fill in gaps or recall a topic. Some students reported a violation of the educational process in the distance format due to the repeated lack of Internet or its poor quality. Most of the students expressed dissatisfaction with the lack of contact communication in the distance learning process. It is proved that the majority of students believe that distance education will never replace traditional education. Mainly students of technical areas of study gave a negative assessment of the distance education system. It was revealed that students of various fields of study took distance courses that were held in other cities or countries. From the point of view of many students, educational websites have an inconvenient interface.

The article analyses data for chemical composition, manufacturing and processing methods for promising heat-resistant alloys based upon orthorhombic titanium intermetallic Ti2AlNb (O-alloys) developed within Russia and abroad. Phase diagrams typical for alloys based upon Ti–Al–Nb and general data for the phases formed in these alloys are provided. Concepts of aluminum and niobium equivalents used for multicomponent alloys are considered. The effect of alloying elements on a combination of mechanical properties of O-alloys, alloying principles, and compositions of the alloys developed are summarized. Characteristics of phase transformations occurring within alloys during heat treatment, including continuous heating and isothermal treatment, are provided. Typical microstructures of the alloys are presented; processing methods for their production and the influence of structural parameters on a combination of properties are described. Methods for manufacturing and processing routes of O-alloys are presented, which provide a good set of properties at room and elevated temperatures, as well as possible operating temperatures for refractory use. [ABSTRACT FROM AUTHOR]

Currently, we can solve a wide range of tasks using computer vision algorithms, which reduce manual labor and enable rapid analysis of the environment. The remote sensing domain provides vast amounts of satellite data, but it also poses challenges associated with processing this data. Baseline solutions with intermediate results are available for various tasks, such as forest species classification, infrastructure recognition, and emergency situation analysis using satellite data. Despite these advances, two major issues with high-performing artificial intelligence algorithms remain in the current decade. The first issue relates to the availability of data. To train a robust algorithm, a reasonable amount of well-annotated training data is required. The second issue is the availability of satellite data, which is another concern. Even though there are a number of data providers, high-resolution and up-to-date imagery is extremely expensive. This paper aims to address these challenges by proposing an effective pipeline for building segmentation that utilizes freely available Sentinel-2 data with 10 m spatial resolution. The approach we use combines a super-resolution (SR) component with a semantic segmentation component. As a result, we simultaneously consider and analyze SR and building segmentation tasks to improve the quality of the infrastructure analysis through medium-resolution satellite data. Additionally, we collected and made available a unique dataset for the Russian Federation covering area of 1091.2 square kilometers. The dataset provides Sentinel-2 imagery adjusted to the spatial resolution of 2.5 m and is accompanied by semantic segmentation masks. The building footprints were created using OpenStreetMap data that was manually checked and verified. Several experiments were conducted for the SR task, using advanced image SR methods such as the diffusion-based SR3 model, RCAN, SRGAN, and MCGR. The MCGR network produced the best result, with a PSNR of 27.54 and SSIM of 0.79. The obtained SR images were then used to tackle the building segmentation task with different neural network models, including DeepLabV3 with different encoders, SWIN, and Twins transformers. The SWIN transformer achieved the best results, with an F1-score of 79.60. [ABSTRACT FROM AUTHOR]

The present stage of development of artificial intelligence (AI) is based on advanced technologies and modern methods and algorithms of machine learning (ML) including deep machine learning, intellectual data analysis and other fundamental scientific areas, which in turn play an important role in delivering applied solutions in almost all areas of digital economy. However, the corresponding expansion of the AI application range and complication of the class of problems, as well as of the spectrum and the volume of data used for creation of applied AI models and AI-based intelligent system call for a significant expansion of the theoretical and algorithmic basis of AI including development of ML methods that involve mathematical and physical models of objects and phenomena of domains, methods of fusion of multimodal data, methods for constructing geometric and topological components of deep neural networks, methods for modeling 3D objects, etc. In 2021, in order to cope well with these challenges, Skoltech Research Center for Applied Artificial Intelligence was created with support from the Federal Program "Artificial Intelligence." The aims of the Center are as follows: creation of a scientific and technological basis for solution of a wide range of relevant applied tasks for purposes of sustainable development of the economy of the Russian Federation including optimization problems of managerial decisions aimed at reduction of the carbon footprint and other urgent ESG tasks; environmental monitoring tasks for detection of anomalies and extreme situations forecast; assessment of economic and social risks and their dynamics caused by climatic changes; predictive analytic problems, etc. In the present paper, we describe new AI technologies, models, methods and algorithms developed in the Center, describe the main applied areas of research of the Center, and provide a briefly survey of the already developed scientific and applied results. [ABSTRACT FROM AUTHOR]

Remote sensing tasks play a very important role in the domain of sensing and measuring, and can be very specific. Advances in computer vision techniques allow for the extraction of various information from remote sensing satellite imagery. This information is crucial in making quantitative and qualitative assessments for monitoring of forest clearing in protected areas for power lines, as well as for environmental analysis, in particular for making assessments of carbon footprint, which is a highly relevant task. Solving these problems requires precise segmentation of the forest mask. Although forest mask extraction from satellite data has been considered previously, no open-access applications are able to provide the high-detailed forest mask. Detailed forest masks are usually obtained using unmanned aerial vehicles (UAV) that set particular limitations such as cost and inapplicability for vast territories. In this study, we propose a novel neural network-based approach for high-detailed forest mask creation. We implement an object-based augmentation technique for a minimum amount of labeled high-detailed data. Using this augmented data we fine-tune the models, which are trained on a large forest dataset with less precise labeled masks. The provided algorithm is tested for multiple territories in Russia. The F 1 - s c o r e , for small details (such as individual trees) was improved to 0.929 compared to the baseline score of 0.856 . The developed model is available in an SAAS platform. The developed model allows a detailed and precise forest mask to be easily created, which then be used for solving various applied problems. [ABSTRACT FROM AUTHOR]

The task of organizing ecosystem accounting and integrating the value of ecosystems and ecosystem services into the management process has been set in Russia. The municipal level is the key one in the system of ecological spatial planning. However, the analysis of the official documents on spatial planning in Russia revealed that ecosystem services are still to be integrated into them. This paper aims to develop guidelines for the formation and implementation of integrated plans for the development of rural areas in the aspect of ecosystem development. The suggested methods of ES evaluation and monetization are based on the use of open statistical data and available digital land cover maps. This way, ecosystem services were calculated in biophysical indicators by converting the area of different types of ecosystems into the demanded and supplied volumes of ecosystem services. The described approaches were approbated on four municipal districts in different federal subjects of Russia (Kiznerskiy district in the Udmurt Republic; Elizovskiy district in Kamchatskiy krai; Maikopskiy district in the Adygeya Republic; and Bobrovskiy district in Voronezh oblast). It reveals that carbon regulation makes up the major part of a total ecosystem services value in the studied districts, thus making regulating services constitute the largest share of the total supplied ecosystem services volume. Recreational and other cultural ecosystem services do not make up a considerable part of the total ES value in any district. These evaluations, on the one hand, form an incomplete and exaggerated idea of ecosystems' value as a source of natural resources; and on the other, detract their regulating and cultural services, which are also extremely significant for the sustainable development on different spatial levels. • Open data bases for Russian municipalities lack geospatial, statistical and monitoring materials, which are essential for accurate assessment of ES at the regional level. • Regulating services perform the largest and most valuable volume of ES in the districts, but their assessment is the most problematic one. • Districts with particularly valuable ecosystems have the most intense tourism development, straining the ecological potential. • The assessment of ES at the regional level in Russia requires an individual time-consuming approach that is hard to complete for all 1600 municipal districts 1 1 Statistical data for municipal districts of other federal subjects is available by adding the district's number at the end of the presented link at www.gks.ru: 30 – Kamchatskiy; 20 – Voronezhskaya; 79 – Maikopskiy; 94 – Udmurtskaya. [ABSTRACT FROM AUTHOR]

Information on forest composition, specifically tree types and their distribution, aids in timber stock calculation and can help to better understand the biodiversity in a particular region. Automatic satellite imagery analysis can significantly accelerate the process of tree type classification, which is traditionally carried out by ground-based observation. Although computer vision methods have proven their efficiency in remote sensing tasks, specific challenges arise in forestry applications. The forest inventory data often contain the tree type composition but do not describe their spatial distribution within each individual stand. Therefore, some pixels can be assigned a wrong label in the semantic segmentation task if we consider each stand to be homogeneously populated by its dominant species. Another challenge is the spatial distribution of individual stands within the study area. Classes are usually imbalanced and distributed nonuniformly that makes sampling choice more critical. This study aims to enhance tree species classification based on a neural network approach providing automatic markup adjustment and improving sampling technique. For forest species markup adjustment, we propose using a weakly supervised learning approach based on the knowledge of dominant species content within each stand. We also propose substituting the commonly used CNN sampling approach with the object-wise one to reduce the effect of the spatial distribution of forest stands. We consider four species commonly found in Russian boreal forests: birch, aspen, pine, and spruce. We use imagery from the Sentinel-2 satellite, which has multiple bands (in the visible and infrared spectra) and a spatial resolution of up to 10 meters. A data set of images for Leningrad Oblast of Russia is used to assess the methods. We demonstrate how to modify the training strategy to outperform a basic CNN approach from F1-score 0.68 to 0.76 . This approach is promising for future studies to obtain more specific information about stands composition even using incomplete data. [ABSTRACT FROM AUTHOR]