Natural ecology early warning model by integrating IGA and remote sensing imagery
Abstracts: The study focuses on enhancing early detection and intelligent warning of forest fires by leveraging deep learning coupled with remote sensing imagery. The research adaptively enhances the genetic algorithm to optimize target detection algorithms for long and short-term memory networks. T...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Systems and Soft Computing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772941924001030 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstracts: The study focuses on enhancing early detection and intelligent warning of forest fires by leveraging deep learning coupled with remote sensing imagery. The research adaptively enhances the genetic algorithm to optimize target detection algorithms for long and short-term memory networks. This approach aims to detect fire features from multi-temporal remote sensing data, enabling the construction of a forest fire early warning model. The experiment results indicated that the improved genetic algorithm stabilized fitness values by the 17th generation, significantly enhancing target detection efficiency and accuracy. The forest fire early warning model, developed using the improved genetic algorithm and remote sensing imagery, demonstrated impressive performance with only a 0.25 % absolute error between predicted and actual fire extent within the 11–318 m2 range. These findings suggest that the research model excels in providing precise early-stage warnings for small-scale forest fires. The results of this research have significantly improved the response to sudden forest fires. |
|---|---|
| ISSN: | 2772-9419 |