LCRA predicts event-aligned canopy responses across unseen Qinling landscapes
- 1College of Biological and Environmental Engineering, Xi’an University
- 2Institute of Remote Sensing Satellite, China Academy of Space Technology
Abstract
Introduction: Predicting event-aligned canopy variation in mountains requires integrating vegetation state, phenology, irregular satellite observations, and landform context. We asked whether a task-structured predictor could improve spatial transfer of short-horizon EVI responses across unseen Qinling landscapes.
Methods: We studied 80 response-blind matched sets in the Qinling Mountains, each comprising one mapped landform and two same-event non-landslide controls, yielding 991 set-events and 2,973 member responses across 32 spatial blocks. The landform-conditioned canopy response aggregator (LCRA) integrated dated MODIS EVI with climate-season, terrain, canopy-state summaries, and matched-member relations to predict subsequent-minus-pre-event (S-P) and subsequent-minus-impact (S-I) EVI. Models were evaluated with block-exclusive outer folds, and nominal composite-start-window results were compared with a complete 16-day support analysis.
Results: In the nominal analysis, the compact LCRA core ensemble achieved member R ² = 0.8219 versus 0.7964 for the EVI-state-plus-season linear reference Δ R ² = +0.0254; 95%; block × shared-onset interval 0.0037−0.0532; matched-contrast R ² was comparable (0.3684 versus 0.3677). Requiring complete 16-day input support to end before the target window yielded member R ² = 0.7810 in 80 sets and 0.7988 in all 90 eligible sets; in the latter, Δ R ² versus linear was +0.0240 −0.0037 to 0.0547), while MAE decreased by 0.0041 EVI (0.0002–0.0087). Validation-based variance scaling reduced primary-task 95% interval width by 38.6% and brought empirical coverage from 99.4% to 92.9%, with improved probabilistic scores. Observed responses showed seasonal sign reversal: mean S-P was +0.0710 EVI in May–June and −0.1814 and −0.1849 in July–August and September. Pre-event canopy state provided a second ordered axis; calendar-standardized severity responses were negative but non-monotonic. The regional landform contrast centered near zero, with bidirectional conditional spatial variation.
Discussion: LCRA combines accurate spatial transfer with a phenology-centered account of event-aligned canopy trajectories. Complete temporal separation retained strong absolute accuracy, although relative R ² gains remained uncertain. These observational contrasts describe canopy variation rather than causal effects of hot–dry exposure.
Related
- Emotional arousal predicts pupil responses following a single attention shift between bright and dark moving stimuli
- DELPHAI predicts heterogeneous perturbation responses with learned single-cell fitness
- Light-defined cold acclimation reprograms organ-specific metabolic and transcriptional landscapes for salt stress responses in maize.
- Climate change, infectious disease, and the spread of microblades across the Qinling-Huaihe line
- Stand and Landscape Drivers of Trap Captures of the Pine Wilt Disease Vector Monochamus alternatus (Coleoptera: Cerambycidae) in the Qinling Mountains
BibTeX
@article{shen2026lcra,
title = {{LCRA predicts event-aligned canopy responses across unseen Qinling landscapes}},
author = {Yuanyuan Shen and Xuyue Shen and Guozhen Liu and Tao Zhou and Chunyang Gu and Yan Wang and Donghui Zhang},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1955922},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1955922/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - LCRA predicts event-aligned canopy responses across unseen Qinling landscapes
AU - Yuanyuan Shen
AU - Xuyue Shen
AU - Guozhen Liu
AU - Tao Zhou
AU - Chunyang Gu
AU - Yan Wang
AU - Donghui Zhang
PY - 2026
DA - 2026/10/28
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1955922
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1955922/full
AB - Introduction: Predicting event-aligned canopy variation in mountains requires integrating vegetation state, phenology, irregular satellite observations, and landform context. We asked whether a task-structured predictor could improve spatial transfer of short-horizon EVI responses across unseen Qinling landscapes. Methods: We studied 80 response-blind matched sets in the Qinling Mountains, each comprising one mapped landform and two same-event non-landslide controls, yielding 991 set-events and 2,973 member responses across 32 spatial blocks. The landform-conditioned canopy response aggregator (LCRA) integrated dated MODIS EVI with climate-season, terrain, canopy-state summaries, and matched-member relations to predict subsequent-minus-pre-event (S-P) and subsequent-minus-impact (S-I) EVI. Models were evaluated with block-exclusive outer folds, and nominal composite-start-window results were compared with a complete 16-day support analysis. Results: In the nominal analysis, the compact LCRA core ensemble achieved member R ² = 0.8219 versus 0.7964 for the EVI-state-plus-season linear reference Δ R ² = +0.0254; 95%; block × shared-onset interval 0.0037−0.0532; matched-contrast R ² was comparable (0.3684 versus 0.3677). Requiring complete 16-day input support to end before the target window yielded member R ² = 0.7810 in 80 sets and 0.7988 in all 90 eligible sets; in the latter, Δ R ² versus linear was +0.0240 −0.0037 to 0.0547), while MAE decreased by 0.0041 EVI (0.0002–0.0087). Validation-based variance scaling reduced primary-task 95% interval width by 38.6% and brought empirical coverage from 99.4% to 92.9%, with improved probabilistic scores. Observed responses showed seasonal sign reversal: mean S-P was +0.0710 EVI in May–June and −0.1814 and −0.1849 in July–August and September. Pre-event canopy state provided a second ordered axis; calendar-standardized severity responses were negative but non-monotonic. The regional landform contrast centered near zero, with bidirectional conditional spatial variation. Discussion: LCRA combines accurate spatial transfer with a phenology-centered account of event-aligned canopy trajectories. Complete temporal separation retained strong absolute accuracy, although relative R ² gains remained uncertain. These observational contrasts describe canopy variation rather than causal effects of hot–dry exposure.
SN - 1664-462X
ER -