Agronomic Characterization and Time-Series UAV Phenotyping to Support Field Pea Breeding in Iowa

Yanben Shen; Joscif Raigne; Asheesh Singh; Arti Singh

cs.CVOct 13, 2026

Agronomic Characterization and Time-Series UAV Phenotyping to Support Field Pea Breeding in Iowa

Authors: Yanben Shen, Joscif Raigne, Asheesh Singh, Arti Singh

Organizations: Department of Agronomy, Iowa state univeristy, Ames, U.S.A

Abstract

Field pea has gained interest in the Midwest U.S. and has the potential to benefit Iowa cropping systems. This study evaluated 17 accessions and 7 Canadian varieties for agronomic and seed yield performance. This study found that PI accession trials exhibit genetic diversity in phenology and canopy traits, whereas the Canadian elite varieties demonstrated great yield potential under Iowa conditions. The accession genotypes matured between 75 DAP (late June) and 95 DAP (late July) across six site-years. The top-yielding Canadian varieties averaged 1961 kg/ha across two site-years. To comprehensively assess field pea performance, this study extracted time-series Unmanned Aerial Vehicle(UAV)-derived traits, assessed UAV-derived traits, and evaluated their correlations with multiple agronomic traits and yield. The results found that UAV-derived time-series canopy area was the most yield-relevant trait (r = 0.63) among all UAV-derived canopy features, vegetation indices, and manually collected measurements. Compared with yield, UAV-derived canopy area showed higher selection reliability (H2 = 0.87, CV = 13.46%), making it suitable for phenotypic selection and accelerating Midwest field pea breeding programs. This study identifies useful UAV-derived features for pea breeding and demonstrates the value of integrating diverse germplasm, elite commercial varieties, and time-series UAV phenotyping. Combining genetic variation from the accession trial with the yield potential of high-performing commercial varieties provides valuable breeding materials and phenotyping strategies for developing locally adapted, high-yielding field pea varieties for future production in the Midwest.

Figures & tables

Trait	2022 AEA	2022 Burkey	2024 Bruner	2024 Burkey	2025 Bruner	2025 Burkey
Planting date	4/19/2022	4/19/2022	6/3/2024	4/10/2024	4/17/2025	4/17/2025
Plant count	6/1/2022	6/1/2022	6/20/2024	5/3/2024	5/12/2025	5/14/2025
Early seedling vigor	–	–	6/20/2024	5/10/2024	5/12/2025	5/14/2025
Days to first flower	5/29–6/16/2022	5/29–6/13/2022	6/27–7/20/2024	5/26–6/10/2024	5/26–6/16/2025	5/26–6/16/2025
Canopy height	6/28/2022	6/28/2022	7/31/2024	6/27/2024	6/30/2025	6/30/2025
Plant height	6/28/2022	6/28/2022	7/31/2024	6/27/2024	6/30/2025	6/30/2025

Table 1: Dates of planting and data collection for six site-years in central Iowa, U.S.

Figure 1: Overview of UAV-derived variable extraction from time-series RGB imagery. a)Example plot extracted from time-series RGB orthomosaics across seedling, early vegetative, late vegetative, reproductive, and maturing growth stages. b) Canopy area extraction and soil background removal using the Excess Green (ExG) vegetation index (threshold $>0.1$ ). c) Canopy height model (CHM) calculated from canopy and soil digital surface models (DSMs). d) Extraction of RGB-based vegetation indices. The completed vegetation index list is in Supplementary Table S1. e) Time-series averaged canopy area for each site-year. Each dot represents a UAV flight date at a specific DAP, and the line shows the seasonal trend of canopy area within each site-year. f) UAV traits extracted from the GAM fitting curve in the time-series canopy area. g) Time-series distribution of canopy area across DAP. The ridgeline density plots show changes in canopy area distribution across the growing season for all genotypes.

Panel of Figure 2 — Figure 2: Comparison of manual agronomic traits and yield performance across pea genotypes, including (a) grain yield, (b) early seedling vigor, (c) days to first flower, (d) days to maturity, (e) canopy height, and (f) plant height.

Figure 3: Seed yield (kg/ha) for Canadian elite varieties. Mean of two site-years in 2024 and 2025

Figure 4: UAV-derived trait relevant to the agronomic traits. The x-axis represents the days after planting, and the y-axis lists agronomic traits. The blue dots represent the correlation of the UAV trait to the agronomic trait. Dot is darker, representing a higher correlation.

Panel of Figure 5 — Figure 5: Principal component analysis (PCA) for field pea traits: a) Phenotype PCA for time-series canopy area, agronomic, and yield traits; and b) Genotype PCA mapping genotype performance across site-year distributions.

Figure 6: Comparison of the correlation between canopy area and yield throughout the growing season in each site-year. Each dot represents a correlation value at a specific DAP, and the solid line shows the variation in correlation within each site-year. The blue dashed line represents the averaged correlation across the season. The red dot indicates the flight date with the highest correlation. The blue circled dot indicates a flight during 60–65 DAP, at which the correlation was relatively close to, or at, the best single-date flight timing.

Panel of Figure 7 — Figure 7: Comparison of agronomic and UAV traits across site-years: (a) grain yield, (b) canopy height, (c) peak canopy, and (d) averaged canopy area.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Figure S1 : The averaged yield of different cropping system of pea plus milo (sorghum), pea plus soybean, soybean monoculture, and corn monoculture. The data source was pull from [ 15 ] .

Figure S2 : Mean seed yield ( $\text{\lx@text@lbrace}kg/ha\}$ ) by genotype across each site-year. The trend of genotype seed yields varied across site-years.

Panel of Figure 11 — Figure S3 : Means of yield and agronomic performance of seven Canadian genotypes across two site-years: (a) grain yield, (b) canopy height, (c) days to flowering (DTF), (d) days to maturity (DTM), (e) plant height, and (f) seedling vigor. The letter represents the significant difference between genotypes in the canopy height, plant height, days to flower, and days to maturity with Tukey’s test.

Figure S4 : Pearson correlation of all UAV-derived and agronomic traits with seed yield.

Trait	Abbreviation	Formula	Citation
Green	G	$G/(G+R+B)$
Excess green index	ExG	$(2G-R-B)$	[ 66 ]
Excess blue index	ExB	$(1.4B-G)$	[ 39 ]
Excess red index	ExR	$(1.4R-G)$	[ 39 ]
Excess green-red index	ExGR	$\mathrm{ExG}-\mathrm{ExR}$	[ 39 ]
Normalized green-red difference index	NGRDI	$\frac{G-R}{G+R}$	[ 21 ]

Appendix

Table S1 : RGB-based vegetation indices used in this study.

Trait	$n\_F$	$F$ -value	$df_{num}$	$df_{den}$	$p$ -value	$H^{2}$	$V_{g}$	$V_{gxe}$	$V_{e}$	E	R	Mean $y$	$\sigma_{e}$	CV (%)
Seed yield	204	3.60	16	80.00	$6.90\times 10^{-5}$	0.722	13918.49	24862.41	14475.64	6	2	468.37	120.31	25.69
Canopy Height (manual)	204	31.11	16	176.00	$6.83\times 10^{-43}$	0.968	133.10	0.00	53.05	6	2	40.19	7.28	18.12
Plant Height (manual)	204	17.72	16	80.00	$5.80\times 10^{-20}$	0.944	344.82	77.69	92.02	6	2	63.95	9.59	15.00
Days to Flower	204	54.67	16	80.00	$2.94\times 10^{-36}$	0.982	21.70	1.61	1.64	6	2	50.78	1.28	2.52
Days to Maturity	136	21.84	16	48.00	$1.03\times 10^{-16}$	0.954	44.64	7.01	3.11	4	2	85.17	1.76	2.07
Seedling Vigor	136	2.99	16	50.21	0.0016	0.666	0.35	0.53	0.33	4	2	3.11	0.58	18.51

Appendix

Table S2 : Genetic variance components, heritability (

H^{2}

), and ANOVA statistics for agronomic and UAV-derived traits.

Plant Phenotyping

Plant phenotyping uses imaging, sensing, and computational methods to measure plant traits, growth, health, and responses to the environment.

See all 68 papers

Automated Maize Ear Phenotyping Using 3D Reconstructions
Sep 1, 2026Ritwesh A. Kumar, Som Tripathi, Peja Matthews +5Plant Phenotyping
Department of Electrical and Computer Engineering, Iowa State University, Ames, IA 50011, USA · Translational AI Research and Education Center, Iowa State University, Ames, IA 50011, USA · Department of Mathematics and Computer Science, Fayetteville State University, Fayetteville, NC 28301, USA +3
A UAV-Based Multispectral and RGB Dataset for Multi-Stage Paddy Crop Monitoring in Indian Agricultural Fields
Jan 3, 2026Adari Rama Sukanya, Puvvula Roopesh Naga Sri Sai, Bodduru Neshika +1Agricultural Remote Sensing UAV Remote Sensing
IIT Tirupati
USU-Corn-WeedDB: A UAV RGB Image Dataset for Multi-Species Weed Detection in Forage Corn
Jun 4, 2026Utsav Bhandari, Saroj Burlakoti, Rhonda Miller +3Agricultural Image Analysis Weed Detection
Department of Applied Sciences, Technology, and Education, Utah State University, Logan, UT, USA · Department of Plants, Soils & Climate, Utah State University, Logan, UT, USA · Department of Civil and Environmental Engineering, Utah State University, Logan, UT, USA

Sep 1, 2026J/K move · Enter open · S save

Automated Maize Ear Phenotyping Using 3D Reconstructions

Ritwesh A. Kumar, Som Tripathi, Peja Matthews, Srikar Reddy+4

Department of Electrical and Computer Engineering, Iowa State University, Ames, IA 50011, USA · Translational AI Research and Education Center, Iowa State University, Ames, IA 50011, USA · Department of Mathematics and Computer Science, Fayetteville State University, Fayetteville, NC 28301, USA+3

Plant Phenotyping

Open paper AskPDF arXiv

Maize kernel traits such as row number, kernels per row, and kernel size vary largely for genetic reasons and are consistently associated with regions of the genome that influence yield. Manual measurement of these traits, however, cannot keep pace with the volume of maize generated in a breeding program. To address this, we developed and validated a fully automated pipeline for extracting these traits from 3D point clouds of corn ears, built on a recently developed video-to-point-cloud platform. Raw video frames are processed through COLMAP and NeRF, the ear is isolated via density-based separation, and the point cloud is distance-calibrated to physical units. The calibrated ear point cloud was Z-axis aligned via PCA and cylindrically unwrapped to a 2D image. We enhanced contrast and performed zero-fine-tuning instance segmentation using Cellpose-SAM. A triple-juxtaposed unwrap strategy was used to prevent double-counting at the seam. The pipeline achieved kernel count R^2 = 0.921 (MAPE = 10.33%) and kernel row number within +-2 rows for 95.2% of ears (MAE = 0.75 rows) on a 168-ear held-out set from the 268-ear labeled dataset. The resulting multi-trait dataset has known genotype identity for each ear, positioning it for phenotype-to-genotype association analyses.

Abstract

Plant Phenotyping

Explore similar work

Automated Maize Ear Phenotyping Using 3D Reconstructions

A UAV-Based Multispectral and RGB Dataset for Multi-Stage Paddy Crop Monitoring in Indian Agricultural Fields

USU-Corn-WeedDB: A UAV RGB Image Dataset for Multi-Species Weed Detection in Forage Corn