IMPROVEMENT OF AUTOMATION OF GEOINFORMATION DATA PROCESSING USING NEURAL NETWORK TECHNOLOGY

Abstract

The purpose of the article is to present a new approach to geographic data processing using deep neural networks, which provides more efficient, accurate and automated analysis.
The methodology includes the use of deep neural networks for automatic identification of characteristics of geographic objects without prior manual processing.
Findings include numerical data in the form of tables and graphs demonstrating the performance improvement of GeoDNN compared to traditional methods.
This article presents an improved approach to geographic data processing based on the use of deep neural networks (GeoDNN). The proposed technique provides a more efficient and automated analysis of geodata.GeoDNN uses deep neural networks to automatically identify the characteristics of geographic objects without prior manual processing. This avoids human errors and increases the accuracy of the analysis, and self-learning mechanisms ensure continuous improvement using new data. GeoDNN is characterized by high performance when processing large volumes of geodata due to its optimized structure and parallel computations. The GeoDNN architecture is described in detail, including flowcharts, mathematical formulas, and algorithms. Processes of data preparation, their normalization and augmentation, as well as model training with parameters, optimization methods and loss functions are considered.
Originality is the application of deep neural networks to automate the processing of geographic data, which allows to avoid human errors, increases the accuracy of the analysis and ensures constant improvement with the use of new data.
The practical value of GeoDNN lies in its ability to automate the analysis of geodata, which significantly reduces processing time and reduces the need for manual labor. This makes the system efficient for use in real-world applications such as automating land parcel analysis.