Abstract
The article proposes the methodology for the automated classification of uplands using Geographic Information System (GIS) and Neural Expert System (NES). Quantitative indicators of topography are used as the basis of the proposed classification. A database consisting of topographic, soil, and land use maps was created using ArcGIS 10 geographic information system. A topologically correct digital elevation model (DEM) was created by the ANUDEM interpolation method. The DEM contains the following maps: hypsometric, steepness and slopes exposure, plan, profile, common curvature of the ground surface, and cumulative runoff maps. The boundaries of elementary surfaces (ES), which are homogeneous morphological formations, are established. Parameters characterizing the Stream Power Index (SPI) are taken into account. The essence of the proposed classification consists in attributing of ES to a certain group of lands based on aggregate of features. To do this, partial scales were created, containing indicators of topography, soil cover, land drainage conditions, as well as the degree of erosion development. The authors formed knowledge base for traning the NES using GIS database and partial scales of estimates. Teaching of neural network was carried out. The classification and topology of land was carried out by means of the NES. The uplands are distributed in flat and slightly convex areas. They are characterized by the following indicators: the curvature of the ground surface: plan curvature (0 – 0.03), profile curvature (0 – 0.15), common curvature (0 – 0.22); slope angles (less than 1.5о); horizontal dissection in elevation (less than 0.5 km/km2), vertical dissection (less than 5 m); and SPI (from -13.80 to -6.47). Electronic map of uplands of LLC «Salair» land-use area was created in the ArcGIS 10 environment.
Highlights
The classification of agricultural lands is a necessary step in the design of agricultural systems [1]
Land classification consisted of the following interrelated stages: - conducting preliminary thematic processing of space images to allocate the elementary surfaces (ES) in the study area; - forming the Geographic Information System (GIS) territory by integrating different materials in the form of raster and vector layers; - collecting and systematizing scientific research to form assessment scales; - developing cartographic knowledge base; - integrating the knowledge about the territory and performing computational experiments aimed at training the Neural Expert System (NES); - using of trained NES for land classification and displaying results;
In consequence of the joint analysis of plan and profile curvature maps and the slope angles’ map, various types of ES were established in the area under study, namely flat surfaces, convex surfaces with different slope angles, and concave surfaces
Summary
The classification of agricultural lands is a necessary step in the design of agricultural systems [1]. The classification is closely related to the agroecological assessment and involves the analysis of land by the most significant natural factors affecting the nature of their use in agricultural production. The classification or categorization of a particular area of the ground surface to a certain agro-ecological group of lands has been carried out by an expert, usually manually according to a declarative model based on the qualitative and partly quantitative characteristics of this area. The development of contemporary information processing technologies makes it possible to formalize topographic description process, to present this information in a form convenient for simulation. The purpose of the present research is to develop methodological bases of the automated method of uplands’ classification using the analysis and simulation procedures of geomorphometric topography indicators by integrating the GIS and NES
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering & Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
