Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design
Micro-terrain classification is an indispensable part of the regular grid digital elevation model and is important in urban landscape design. Given the shortcomings of the regular grid digital elevation model, a micro-terrain classification method integrating a GA-BPNN algorithm is proposed. Firstly...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10746477/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846163854188347392 |
|---|---|
| author | Dianmei Geng |
| author_facet | Dianmei Geng |
| author_sort | Dianmei Geng |
| collection | DOAJ |
| description | Micro-terrain classification is an indispensable part of the regular grid digital elevation model and is important in urban landscape design. Given the shortcomings of the regular grid digital elevation model, a micro-terrain classification method integrating a GA-BPNN algorithm is proposed. Firstly, a micro-terrain classification model based on a regular grid DEM network is constructed by combining BPNN with the regular grid. Secondly, to address the issue of the slow convergence rate of BPNN, the GA is proposed as a means of optimization. On this basis, an improved GA-BPNN model is constructed and its efficacy is evaluated. The results demonstrated that the GA-BPNN model commenced convergence after 70 iterations, with a stable loss value of 0.4. The overall classification accuracy reached 95%, with the classification effect of the mountain shoulder being the best at 96.7%, representing a 6.4% improvement over the highest accuracy of the BPNN model. Therefore, the improved model reduces classification errors, improves the accuracy of micro-terrain classification, reduces time costs, and accelerates operational efficiency. It also improves the performance of the regular grid micro-terrain classification model, which is conducive to promoting the intelligence and modernization of urban landscape design. |
| format | Article |
| id | doaj-art-91613e6549074d669531e4638a0272f3 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-91613e6549074d669531e4638a0272f32024-11-19T00:02:02ZengIEEEIEEE Access2169-35362024-01-011216730016731210.1109/ACCESS.2024.349312310746477Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape DesignDianmei Geng0https://orcid.org/0009-0002-8172-503XSchool of Arts, Huangshan University, Huangshan, ChinaMicro-terrain classification is an indispensable part of the regular grid digital elevation model and is important in urban landscape design. Given the shortcomings of the regular grid digital elevation model, a micro-terrain classification method integrating a GA-BPNN algorithm is proposed. Firstly, a micro-terrain classification model based on a regular grid DEM network is constructed by combining BPNN with the regular grid. Secondly, to address the issue of the slow convergence rate of BPNN, the GA is proposed as a means of optimization. On this basis, an improved GA-BPNN model is constructed and its efficacy is evaluated. The results demonstrated that the GA-BPNN model commenced convergence after 70 iterations, with a stable loss value of 0.4. The overall classification accuracy reached 95%, with the classification effect of the mountain shoulder being the best at 96.7%, representing a 6.4% improvement over the highest accuracy of the BPNN model. Therefore, the improved model reduces classification errors, improves the accuracy of micro-terrain classification, reduces time costs, and accelerates operational efficiency. It also improves the performance of the regular grid micro-terrain classification model, which is conducive to promoting the intelligence and modernization of urban landscape design.https://ieeexplore.ieee.org/document/10746477/SBPNNgenetic algorithmregular griddigital elevationlandscape |
| spellingShingle | Dianmei Geng Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design IEEE Access SBPNN genetic algorithm regular grid digital elevation landscape |
| title | Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design |
| title_full | Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design |
| title_fullStr | Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design |
| title_full_unstemmed | Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design |
| title_short | Application of Digital Terrain Editing Technology Based on Regular Grid Structure in Urban Landscape Design |
| title_sort | application of digital terrain editing technology based on regular grid structure in urban landscape design |
| topic | SBPNN genetic algorithm regular grid digital elevation landscape |
| url | https://ieeexplore.ieee.org/document/10746477/ |
| work_keys_str_mv | AT dianmeigeng applicationofdigitalterraineditingtechnologybasedonregulargridstructureinurbanlandscapedesign |