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. INDEX TERMS Convolutional neural networks, deep learning, geospatial analysis, geosystems, image classification, machine learning.

Ge eo oJ Jo ou ur rn na al l o of f T To ou ur ri is sm m a an nd d G Ge eo os si it te es s Year X XI II II I, vol. 29, no. 2 2, 2 20 02 20 0, p.4 44 40 0-4 44 49 9

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.

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.

The Spanish flu appeared at the end of the First World War and spread around the world in three waves: spring-summer in 1918, which was mild; autumn fatal wave, in the same year; and winter wave in 1919, which also had great consequences. From the United States of America, as the cradle of its origin, the Spanish flu spread to all the inhabited continents, and it did not bypass Serbia either. Research on the Spanish flu, as the deadliest and most widespread pandemic in the human history, was mostly based on statistical researches. The development of the geographic information systems and spatial analyses has enabled the implementation of the information of location in existing researches, allowing the identification of the spatial patterns of infectious diseases. The subject of this paper is the spatial patterns of the share of deaths from the Spanish flu in the total population in Valjevo Srez (in Western Serbia), at the settlement level, and their determination by the geographical characteristics of the studied area-the average altitude and the distance of the settlement from the center of the Srez. This paper adopted hot spot analysis, based on Gi* statistic, and the results indicated pronounced spatial disparities (spatial grouping of values), for all the studied parameters. The conclusions derived from the studying of historical spatial patterns of infectious diseases and mortality can be applied as a platform for defining measures in the case of an epidemic outbreak with similar characteristics.