Indexed in

License and use

Citations

Altmetrics

Grant support

This work was supported by the Spanish projects "HolisticWheat" (PID2022-138307OB-C21) , Ministerio de Ciencia e Innovacion, Spain and "DENSIPLANT" from the CERCA Center Agrotecnio, Generalitat de Catalunya, Spain J.J.-B. was supported by INVESTIGO 2022 program from Plan de Recuperacion, Transformacion y Resiliencia (NextGenerationEU) . Currently J.J.-B. is recipient of a FPI doctoral fellowship PREP2022000560 funded by MICIU/AEI/10.13039/501100011033 and FSE+. C.S.C. held a Maria Zambrano's fellowship from the University of Lleida funded by Spanish Ministry of Universities and the European Social Fundand currently is contracted by the project PID2021127415OB-I00 funded by AEI (State Research Agency of Spain) . S.C.K. is supported by the Ramon y Cajal RYC-2019-027818-I research fellowship from the Ministerio de Ciencia e Innovacion, MINECO, Spain. We also acknowledge the support from the Institut de Recerca de l'Aigua and the Universitat de Barcelona.

Analysis of institutional authors

Share

Winter wheat plant density determination: Robust predictions across varied agronomic conditions using multiscale RGB imaging

Publicated to:Smart Agricultural Technology. 11 100921- - 2025-08-01 11(), DOI: 10.1016/j.atech.2025.100921

Authors: Jauregui-Beso, Jara; Gracia-Romero, Adrian; Carrera, Constanza S; Lopes, Marta da Silva; Araus, Jose Luis; Kefauver, Shawn Carlisle

Affiliations

Abstract

Cereal plant density is a crucial agronomic factor affecting resource management and yield. This study automated wheat density estimation using multiscale imaging from ground and Unmanned Aerial Vehicles (UAV) at 15, 30, and 50m Conducted over two agronomic seasons (2022 and 2023) with different water profiles, it analyzed three wheat genotypes (cv. Bologna, Hondia, and Marcopolo) sown at five densities ranging from 35 to 560 seeds m-2. Images collected through RGB sensors across Haun's developmental stages 2.6-12.2 provided data for calculating 15 Vegetation Indexes (VIs), which, along with their Principal Components (PCs), were used as inputs for Ridge and Principal Component Regression (PCR) models. Training was conducted on the 2022 datasets using 4-fold, 10-repeated cross-validation to determine the most predictive growth stages, with Haun stages 5.3 to 7.3 yielding the best results, irrespective of resolution. Testing on 2023 datasets showed that Ridge models consistently outperformed PCR, especially for medium to high-density ranges (140-560 seeds m-2), though they underperformed at lower densities, leading to their exclusion from the testing data. The top-performing Ridge model, trained on Haun stages 7.1-7.3 at 50 m (1.18 cm pixel-1), achieved Mean Absolute Percentage Error (MAPE) 17.91% - 28.54% (0.9-0.68 R2) values across various test sets, with stable performance throughout resolutions and stages (4.4-4.8). These findings show robust prediction capabilities across a broader developmental range and from the lowest resolution recorded, especially when vegetation coverage is abundant. The study highlights the practicality of high-throughput RGB imaging for scalable, flexible and affordable plant density estimation.

Keywords