Method and system for evaluating site selection of a waste dump

By segmenting remote sensing images using an improved UNet network and combining it with regulations for spoil disposal site selection, the problem of inaccurate evaluation results in existing methods is solved, achieving accurate evaluation and efficient judgment of spoil disposal site selection.

CN122135034APending Publication Date: 2026-06-02JIANGXI ACAD OF WATER RESOURCES (JIANGXI PROVINCE DAM SAFETY MANAGEMENT CENT JIANGXI PROVINCE WATER RESOURCES MANAGEMENT CENT)
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JIANGXI ACAD OF WATER RESOURCES (JIANGXI PROVINCE DAM SAFETY MANAGEMENT CENT JIANGXI PROVINCE WATER RESOURCES MANAGEMENT CENT)
Filing Date
2026-03-23
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing methods for selecting spoil disposal sites rely on traditional empirical methods and GIS multi-factor overlay analysis, which lack objectivity and lead to inaccurate evaluation results.

Method used

An improved UNet network is used to process remote sensing images and geographic parameters. Through residual convolutional units, intermediate multi-scale fusion modules, and spatial channel attention blocks, the target remote sensing parameter images are segmented and accurately evaluated in conjunction with the site selection regulations for spoil disposal sites.

Benefits of technology

It improves the accuracy and efficiency of spoil disposal site selection, can accurately determine whether spoil disposal sites occupy sensitive areas, reduces computing resource requirements, and improves segmentation accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122135034A_ABST
    Figure CN122135034A_ABST
Patent Text Reader

Abstract

This application discloses a method and system for evaluating the site selection of a spoil disposal site, belonging to the field of artificial intelligence technology. The method includes constructing a dataset and an improved UNet network, and training and testing the improved UNet network based on the dataset; acquiring a target remote sensing parameter image of the target spoil disposal site, and processing the target remote sensing parameter image using the improved UNet network to obtain a land use segmentation map of the target remote sensing parameter image; and determining whether the target spoil disposal site is qualified based on the land use segmentation map. This application segments the target remote sensing parameter image corresponding to the target spoil disposal site using the improved UNet network to obtain a land use segmentation map that segments various land types, rivers, and human living areas. By combining spoil disposal site selection regulations with the land use segmentation map, an accurate evaluation of the qualification of the target spoil disposal site can be achieved.
Need to check novelty before this filing date? Find Prior Art