1
Return

Integrating spatiotemporal prior knowledge from co-segmented time-series into factor-driven modeling for forest insect damage warning

delete2026-08-10
delete0
delete
OA
AI
H
Haoyan Zhang
S
Shiming Li
潘耀忠 (Yaozhong Pan) *
DOI:10.1016/j.jag.2026.105518delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
• A hybrid approach couples spatiotemporal priors with factor-driven FID modeling. • Multi-index co-segmentation ensures a consistent temporal reference across indices. • Geographic priors from historical clustering cut healthy-forest false alarms. • Area control aligns predicted FID area with historical trends, cutting false alarms. • Spatiotemporal priors offset coarse driver resolution and sample scarcity.
Keywords:
Forest insect damage
Hybrid warning approach
Spatiotemporal prior knowledge
Co-segmentation
Satellite time series
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

International Journal of Applied Earth Observation and Geoinformation cover
International Journal of Applied Earth Observation and Geoinformation
IF:
8.6
Papers:
5.1K
Citations:
2.4W

Organization

C
chinese academy of forestry
Scholars:
1.4K
Papers: 472
Citations: 0
B
beijing normal university
Scholars:
4.1K
Papers: 1.7K
Citations: 0
Cited Papers

Cited Papers

Citing Papers

Citing Papers