The article proposes a solution for the problem of high-resolution remote sensing data classification by applying deep learning methods and algorithms in conditions of labeled data scarcity. The problem can be solved within the geosystem approach, through the analysis of the genetic uniformity of spatially adjacent entities of different scale and hierarchical level. Advantages of the proposed GeoSystemNet model rest on a large number of freedom degrees, admitting flexible configuration of the model contingent upon the task at hand. Testing GeoSystemNet for classification of EuroSAT dataset, algorithmically augmented after the geosystem approach, demonstrated the possibility to improve the classification precision in conditions of labeled data accuracy by 9% and to obtain the classification precision with a larger volume of training data (by 2%) which is slightly inferior in comparison with other deep models. The article also shows that synthesis of the geosystem approach with deep learning capabilities allows us to optimize the diagnostics of exogeodynamic processes, owing to the calculation of landscape differentiation regularities. Application of the presented approach enabled us to improve the accuracy in detecting landslides at the testing site “Mordovia” by 5% in comparison with the classical approach of using deep models for remote sensing data analysis. The authors advocate that application of the geosystem approach to improve the efficiency of remote sensing data classification through methods, proposed in the article, requires an individual project-based approach to source data augmentation.

Increasing accuracy of the data analysis of remote sensing of the Earth significantly affects the quality of decisions taken in the field of environmental management. The article describes the methodology for decoding multispectral space images based on the ensemble learning concept, which can effectively solve important problems of geosystems mapping, including diagnostics of the structure and condition of catchment basins, inventory of water bodies and assessment of their ecological state, study of channel processes; monitoring and forecasting of functioning, dynamics and development of geotechnical systems. The developed methodology is based on an algorithm for analyzing the structure of geosystems using ensemble systems based on a fundamentally new organization of the metaclassifier that allows for a weighted decision based on the efficiency matrix, which is characterized by an increase in accuracy of the decoding of space images and resistance to errors. The metaclassification training algorithm based on the method of weighted voting of monoclassifiers is proposed, in which the weights are calculated on the basis of error matrix metrics. The methodology was tested at the test site ‘Inerka’. The performed experiments confirmed that the use of ensemble systems increases the final accuracy, objectivity, and reliability of the analysis.

Soil erosion is a global environmental and economic problem that is significantly related to land-use changes. Over the last decades, several mountain areas in Serbia were exposed to strong human pressure caused by winter tourism development. The largest ski center in Serbia is situated on Kopaonik Mountain within the boundaries of Kopaonik National Park, where the conflict between economic and conservation goals is rapidly growing. In this study, we calculated the sedimentation and surface runoff in three sub-basins in the area of Kopaonik ski resort for two years (1984 and 2018) using the Soil and Water Assessment Tool (SWAT) and analyzed the changes that occurred during the observed period. The results show an increase in surface runoff and sediment yield in sub-basins 1 and 3 and a decrease in sub-basin 2. The analysis of land cover change shows an expansion of evergreen forests, appearance of barren soil and urban areas, reduction of mixed forests and pastures, and the appearance of deciduous forests. These findings indicate that in the area studied, the dominant processes are the development of tourism and natural revegetation of abandoned agricultural land. Application of remote sensing techniques and SWAT contributes to identifying and monitoring land degradation problems and improving conservation and management practices.

Planning based on reliable information about the Earth’s surface is an important approach to minimize economic expenses conditioned by natural factors. Data collected by Earth remote sensing (ERS), as well as the analysis of such data using automated classification methods, are becoming more and more important for research and practice activities related to assessing the spatio-temporal structure and sustainability of the Earth’s surface. The analysis of the authenticity of the surrounding areas enables a more objective classification of land plots on the basis of spatial patterns. Combined use of various environmental descriptors enables high-quality handling of neighborhood properties, as each descriptor provides its own specific information about a geospatial system. Experiments have shown that the diagnostics of the emergent properties of such internal structure by analyzing the diversity of dynamic characteristics allows reducing exposure to noise, obtaining a generalized result, and improving the classification accuracy.

Objectives. The paper aimed to develop and validate a neural network model for spatial data analysis. The advantage of the proposed model is the presence of a large number of degrees of freedom allowing its flexible configuration depending on the specific problem. This development is part of the knowledge base of a deep machine learning model repository including a dynamic visualization subsystem based on adaptive web interfaces allowing interactive direct editing of the architecture and topology of neural network models.Methods. The presented solution to the problem of improving the accuracy of spatial data analysis and classification is based on a geosystem approach for analyzing the genetic homogeneity of territorial-adjacent entities of different scales and hierarchies. The publicly available EuroSAT dataset used for initial validation of the proposed methodology is based on Sentinel-2 satellite imagery for training and testing machine learning models aimed at classifying land use/land cover systems. The ontological model of the repository including the developed model is decomposed into domains of deep machine learning models, project tasks and data, thus providing a comprehensive definition of the formalizing area of knowledge. Each stored neural network model is mapped to a set of specific tasks and datasets. Results. Model validation for the EuroSAT dataset algorithmically extended in terms of the geosystem approach allows classification accuracy to be improved under training data shortage within 9% while maintaining the accuracy of ResNet50 and GoogleNet deep learning models.Conclusions. The implemention of the developed model into the repository enhances the knowledge base of models for spatial data analysis as well as allowing the selection of efficient models for solving problems in the digital economy.

One of the indicators of water potential and water resources is specific runoff. Specific runoff for the whole territory of Serbia was obtained using the exponential relation between depth of runoff Y (mm) and precipitation P (mm). This relation is obtained on the basis of the mean annual amount of precipitation and annual water discharge, namely the depth of the runoff for 69 basins for the period 1961-2010. Coefficient of determination (R?) of relation between the depth of runoff and precipitation is 0.72. The differences between measured and modeled values of specific runoff vary from basin to basin, but at the level of the whole Serbia it is 3.5%. More precisely, the measured specific runoff amounts 5.6 l/s/km2, and the modeled specific runoff is 5.7 l/s/km2. The verification was done by applying the model to 11 large river basins in Serbia. Spatial distribution of the modeled specific runoff is presented by a digital map of specific runoff with pixel resolution 100 ? 100 m which enables the estimation of mean annual water discharge in any ungauged basin in Serbia.