Context-aware quantile baselines for disturbance detection in non-stationary short-rotation forest plantations
Abstract
Disturbances such as pests, diseases, fire, windthrow, and drought are increasingly affecting forests and require near-real-time monitoring from satellite observations. Existing near-real-time methods often detect anomalies relative to historical vegetation index (VI) baselines based on periodic, parametric, or autoregressive models, which can be difficult to apply in short-rotation plantations with strongly non-stationary canopy dynamics. We introduce the FOrest plantation Canopy ALert system (FOCAL), a monitoring framework designed for relatively homogeneous, intensively managed short-rotation plantations that combines pixel-level Quantile Regression Forest baseline prediction with rule-based detection of persistent negative anomalies. For each new Sentinel-2 acquisition, FOCAL first predicts the range of VI values expected under undisturbed conditions from stand age, management variables, environmental conditions, acquisition geometry, and recent VI observations. A disturbance alert is then issued when observed VI values fall below the lower bound of this predicted contextual range for consecutive acquisitions. FOCAL was evaluated using 118 Eucalyptus plantation stands in Brazil affected by confirmed disturbance events, 141 undisturbed reference stands, and a controlled mortality-patch experiment. Using NDVI, FOCAL achieved a mean class accuracy of 0.78 and a binary F1-score of 0.76, outperforming benchmark time-series methods. Detection was particularly strong for fire (100%) and severe water stress (84%), and mortality patches as small as 12 × 12 m were identified. These results demonstrate FOCAL's potential for disturbance detection in intensively managed Eucalyptus plantations.
Related
- Soil parameters associated with Fusarium oxysporum f. sp. cubense incidence and their integration into an IoT-based monitoring system for banana plantations
- Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
- Restoration pathways reshape forest structure and multifunctionality in subtropical plantations and secondary forests
- Control of black leaf streak disease without mancozeb in commercial plantations of Colombia
- Variation in rhizosphere microbial communities and nitrogen- and phosphorus-cycling functional genes among rubber plantations in Yunnan, China
BibTeX
@article{maire2026contextaware,
title = {{Context-aware quantile baselines for disturbance detection in non-stationary short-rotation forest plantations}},
author = {Guerric Le Maire and Florian de Boissieu and Clayton Alcarde Alvares and Henrique Ferraço Scolforo and Evandro Nunes Mirand and Vitoria Barbosa Ferreira and Jean Baptiste Feret and Joannès Guillemot and Jose Luiz Stape},
journal = {International Journal of Applied Earth Observation and Geoinformation},
year = {2026},
month = sep,
doi = {10.1016/j.jag.2026.105555},
url = {https://hal.science/hal-05761921v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Context-aware quantile baselines for disturbance detection in non-stationary short-rotation forest plantations
AU - Guerric Le Maire
AU - Florian de Boissieu
AU - Clayton Alcarde Alvares
AU - Henrique Ferraço Scolforo
AU - Evandro Nunes Mirand
AU - Vitoria Barbosa Ferreira
AU - Jean Baptiste Feret
AU - Joannès Guillemot
AU - Jose Luiz Stape
PY - 2026
DA - 2026/09/24
JO - International Journal of Applied Earth Observation and Geoinformation
DO - 10.1016/j.jag.2026.105555
UR - https://hal.science/hal-05761921v1
AB - Disturbances such as pests, diseases, fire, windthrow, and drought are increasingly affecting forests and require near-real-time monitoring from satellite observations. Existing near-real-time methods often detect anomalies relative to historical vegetation index (VI) baselines based on periodic, parametric, or autoregressive models, which can be difficult to apply in short-rotation plantations with strongly non-stationary canopy dynamics. We introduce the FOrest plantation Canopy ALert system (FOCAL), a monitoring framework designed for relatively homogeneous, intensively managed short-rotation plantations that combines pixel-level Quantile Regression Forest baseline prediction with rule-based detection of persistent negative anomalies. For each new Sentinel-2 acquisition, FOCAL first predicts the range of VI values expected under undisturbed conditions from stand age, management variables, environmental conditions, acquisition geometry, and recent VI observations. A disturbance alert is then issued when observed VI values fall below the lower bound of this predicted contextual range for consecutive acquisitions. FOCAL was evaluated using 118 Eucalyptus plantation stands in Brazil affected by confirmed disturbance events, 141 undisturbed reference stands, and a controlled mortality-patch experiment. Using NDVI, FOCAL achieved a mean class accuracy of 0.78 and a binary F1-score of 0.76, outperforming benchmark time-series methods. Detection was particularly strong for fire (100%) and severe water stress (84%), and mortality patches as small as 12 × 12 m were identified. These results demonstrate FOCAL's potential for disturbance detection in intensively managed Eucalyptus plantations.
SN - 1569-8432
SN - 1872-826X
ER -