OPAL-Flow: Orientation-aware rice panicle detection and minute-scale anthesis rhythm identification under field conditions

Abstract

Accurate timing of rice panicle anthesis is critical for quantifying sterility risk under heat and humidity, yet minute-scale field measurement remains challenging because anthesis is transient and spikelets are tiny and difficult to detect. To address this, we present OPAL-Flow, a pipeline that provides single-panicle anthesis start and peak times under field conditions, consisting of a detector for panicle detection and tracking, a super-resolution reconstruction model, and an event-time pinpointing model. For slender panicle detection and panicle pose normalization, YOLO-SnakePanNet was introduced by using Dynamic Snake Convolution with a lightweight box-rotated head. Ablation experiments show that YOLO-SnakePanNet achieved mAP@50 of 94.4%, improving by 3.6% over the YOLOv11 while reducing computation by 0.7 GFLOPs. For panicle-level anthesis pinpointing, PanicleTimeMAE was proposed by incorporating a pyramid-dilated temporal convolutional network and a confidence-aware smoothing gate into the transformer, reaching Acc@±1 of 0.85 on 5-min sampled sequences (±1 frame = ±5 min), yielding a 40% decrease in MAE over VideoMAEv2. Finally, correlation analysis between variety-level anthesis start time (T start ) and peak time (T peak ) and same-day meteorology showed that higher photosynthetically active radiation (r = -0.543/-0.573 for T start /T peak ) and temperature (r = -0.288/-0.272) advanced anthesis, whereas higher relative humidity (r = 0.397/0.438) and rainfall (r = 0.428/0.502) delayed anthesis. The variance decomposition within fixed-effects model for Tstart ( R2 = 0.651) and Tpeak ( R2 = 0.648) prediction shows that variance mainly attributed to meteorological effects (64%) and variety effects (33.5%). Overall, OPAL-Flow enables variety selection for heat- and humidity-resilient anthesis in rice breeding and supports ecophysiological dissection of anthesis regulation.

Code and data availability

The paper's Data availability statement explicitly states that the source code and test samples for OPAL-Flow are publicly available on GitHub at the authors' repository. This is a paper-specific, publicly actionable code asset. The phenotype datasets (panicle detection dataset, start/peak annotation sequences) are not