A Plant-Level Survival Modeling Framework for Spatiotemporal Strawberry Canopy Decline Using UAV Multispectral Time Series

Abstract

Timely identification of canopy decline in commercial strawberry production is challenging because visual scouting often misses subtle or spatially heterogeneous symptoms. We developed a plant-level UAV-based monitoring framework that integrates repeated multispectral imagery, canopy-derived metrics, unsupervised clustering, and Random Survival Forest (RSF) time-to-event modeling. The framework was applied across three commercial strawberry fields in Oxnard, California using nine UAV surveys collected from December 2022 to June 2023, yielding 159,220 plant-level monitoring units. NDRE- and Redness Index-based classifications quantified proportional and absolute canopy dieback within standardized hexagonal units and supported survival-based modeling of canopy decline progression. Across withheld test plants from all survey dates, overall concordance indices ranged from 0.88 to 0.95 across fields, indicating strong ability to rank plants by time-to-decline risk under heterogeneous field conditions. Spatial risk maps revealed localized high-risk clusters that expanded over time in fields with greater canopy deterioration, while fields with minimal visible decline exhibited diffuse but stable risk distributions. Post-hoc comparison with operational fumigation rates (280, 336, and 392 kg Pic-Clor 60/ha) showed no consistent association with predicted canopy decline risk. These results demonstrate that framing repeated UAV observations as a time-to-event process enables fine-scale spatiotemporal modeling of canopy decline dynamics and supports risk stratification for targeted field monitoring in commercial strawberry systems.

Plant phenotyping relevance

UAVマルチスペクトル画像から植物体レベルのキャノピー衰退・枯死を抽出し、時系列解析と生存モデルで評価するフレームワークが研究の中心であり、性能検証も行っている。

Code and data availability

The paper's UAV multispectral imagery, derived plant-level metrics, and analysis scripts are paper-specific phenotyping assets, but the Data Availability Statement restricts them to on-request access due to data volume and grower confidentiality; no public repository or URL is provided.

No evidence-backed public reproduction asset is currently recorded.