SBShannon Baker

Shannon Baker

*This is an algorithmically generated author record based on publicly available information.

Shannon Baker has a total of 48 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Strategically timed UAS data acquisition for wheat yield prediction using explainable AI: A multi-year phenology-aligned study

    by Shannon Baker, Md Nafiul Islam, Mahendra Bhandari, Anjin Chang, Amir Mh Ibrahim, Jinha Jung, Juan Landivar, Shuyu Liu, Varenya Sri Mudumba, Ritik Pokharel, et al.

  • Open Access

    Strategically Timed UAS Data Acquisition for Wheat Yield Prediction Using Explainable AI: A Multi-Year Phenology-Aligned Study

    by Shannon Baker, Nafiul Islam, Mahendra Bhandari, Anjin Chang, Amir Ibrahim, Jinha Jung, Juan Landivar, Shuyu Liu, Varenya Sri Mudumba, Ritik Pokharel, et al.

    Accelerating genetic gain in wheat breeding requires high-throughput phenotyping (HTP) to overcome labor-intensive bottlenecks and subjectivity associated with traditional field assessments. Unoccupied Aerial Systems (UAS) provide scalable, non-destructive phenotyping of crop development across breeding plots. Selecting optimal flight timing and predictive models is critical to ensure consistency across seasons. This study optimized UAS flight timing for wheat yield prediction by evaluating multi-year vegetation indices (VIs), including Normalized Difference Vegetation Index (NDVI), Normalized Difference Red Edge Index (NDRE), and Excess Green (ExG), aligned using Days Relative to Heading (DRH). Data from ten flights per year during the 2018–2021 growing seasons were used to assess predictive accuracy of machine learning models, including XGBoost, Ridge Regression, Random Forest, ExtraTrees, Partial Least Squares Regression, and Neural Networks. To address seasonal differences in planting date and sampling intervals, VIs were synchronized using DRH. Models were trained on 2018–2020 data and validated using an independent 2021 dataset. To enhance model explainability and ensure the reliability of the results, feature importance was evaluated over 100 iterations to identify the most consistent phenological window for yield prediction. XGBoost, ExtraTrees, and Random Forest achieved the lowest prediction errors (RMSE = 6.03 bu ac−1; NRMSE = 9.59%, RMSE = 6.1 bu ac-1; NRMSE = 9.7, RMSE = 6.58 bu ac-1, NRMSE = 10.47%) and showed negligible performance change in 2021 (ΔRMSE = -0.12 bu ac−1), indicating robust out-of-year generalization. VIs near heading were the most critical predictors, underscoring the importance of canopy condition during the transition to reproductive development. Concentrating UAS flights at heading therefore provides a resource-efficient approach for accurate yield prediction. Within the tested production environments, this framework supports high-throughput selection by identifying temporally stable canopy–yield relationships and optimizing UAS flight timing to reduce operational redundancy and cost.

  • Open Access

    Genetic Variations and Epistatic Interactions for Agronomic and Yield Traits in Winter Wheat Population Derived from ‘TAM 204’ and ‘Iba’ Cultivars

    by Yahya Rauf, Jorge Luis Valenzuela-Antelo, Mehmet Dogan, Chenggen Chu, Shannon A. Baker, Jason A. Baker, Daniel Hathcoat, Geraldine Opena, Qingwu Xue, Jackie C. Rudd, et al.

    Background: Improving grain yield in wheat remains a top priority, requiring integrated breeding and genetic strategies. This complexity poses a major challenge, driven by quantitative polygenic inheritance, environmental influence, and intricate genetic interactions. We investigated genetic factors and their interactions for agronomic and yield traits in two high-yielding winter wheat cultivars adapted to the US Southern Great Plains. Methods: A bi-parental mapping population consisting of 221 F7 recombinant inbred lines (RIL) derived from ‘TAM 204’ and ‘Iba’ was evaluated for three years in 11 Texas environments. Both parents and RIL population were genotyped on Illumina NovaSeq 6000 and sequences were aligned to IWGSC RefSeq v1.0 using Bowtie2 for SNP calling. For QTL analyses, each trait was analyzed by individual environment, across multiple environments and mega-environments. Results: A total of 86 QTL were mapped for five traits and among them 32 were consistent in more than one environment or analysis. Among consistent QTL, four were pleiotropic to more than one agronomic or yield traits mapped on chromosomes 2B (57.18, 59.47 Mb) and 2D (29.34, 40.64 Mb). The consistent QTL on chromosome 2D (29.34 Mb) was pleiotropic to GYLD, DTH, TW, TKW and explained maximum phenotypic variation for all traits, representing photoperiod gene (Ppd-D1). Another QTL on chromosome 2D (40.64 Mb) was pleiotropic to GYLD and TW and based on the physical position comparisons it likely reflects a unique locus in Iba. The pleiotropic consistent QTL Qgyld.tamu.2B.59 from TAM 204 represents Ppd-B1 gene. Moreover, it is more likely that Qdth.tamu.5B.575 represents the Vrn-B1 gene in Iba. A total of 23 digenic epistatic interactions involved consistent QTL for all traits. Amongst these, epistatic interactions between the consistent QTL on 2B (57.18 Mb) and 2D (29.34 Mb) were observed for GYLD, DTH and TKW. Conclusions: Our findings revealed key allelic diversity and interaction effects in elite wheat cultivars, paving the way for marker development for identified pleiotropic loci and implementation in marker-assisted selection and recombination breeding.

  • Open Access

    A double-sigmoid approach for high-throughput phenotyping of winter wheat growth dynamics

    by Shannon Baker, Lei Zhao, Jose Landivar Scott, Jackie Rudd, Amir Mh Ibrahim, Juan Landivar, Jinha Jung, Shuyu Liu, Kevin Nowka, Mahendra Bhandari


  • Open Access

    Association Mapping for Biomass and Kernel Traits in Doubled-Haploid Population Derived from Texas Wheat Cultivars

    by Yahya Rauf, Zhen Wang, Kyle Parker, Shannon A. Baker, Jason A. Baker, Jackie C. Rudd, Qingwu Xue, Amir Ibrahim, Shuyu Liu

    Background: Genetic improvement in wheat yield is the most focused research area for the breeding community to ensure sustainable production. Wheat kernel traits and biomass are considered key contributors to enhance crop yield. Methods: This study was designed to explore the genetic diversity of kernel and biomass traits in popular wheat varieties from the US Southern Great Plains using 264 doubled haploid (DH) lines mainly derived from TAM 114 or TAM 204. This population was evaluated in two field environments planted in alpha lattice design during the 2020 crop season. Kernel traits were collected using the hp Scanjet G4010 photo scanner for image capturing and GrainScan v3. software for image analysis. Biomass parameters were collected and processed manually. For genotyping genomic libraries were prepared and sequenced on Illumina NovaSeq 6000 to generate paired end reads of 150 bp. Sequences were aligned to the IWGSC RefSeq genome assembly v2.1 using the Burrows Wheeler Aligner for SNP calling. Results: A total of 59,482 polymorphic SNP markers were retained for genetic analysis after the filtration at 50% missing data and 5% minor allele frequency. To investigate the marker–trait association and the genomic regions, four genome-wide association study models were implemented using the R package GAPIT version 3.5. Based on the Bonferroni correction −7 was used as a threshold to declare marker-trait associations (MTAs) significant. The BLINK model identified 12 MTAs on chromosomes 1A, 2A, 2B, 4A, 4B, and 6B. Conclusions: The identified MTAs can be used to develop diagnostic markers for efficient selection and utilization in recombination breeding and cultivar development process.

  • Open Access

    Association Mapping for Biomass and Kernel Traits in Doubled Haploid Population Derived from Texas Wheat Cultivars

    by Yahya Rauf, Zhen Wang, Kyle Parker, Shannon Baker, Jason Baker, Jackie Rudd, Qingwu Xue, Amir Ibrahim, Shuyu Liu

    Genetic improvement in wheat yield is the most focused research area for the breeding community to ensure food security and sustainable production. Wheat kernel traits and biomass are considered key contributors to enhance crop yield. A set of 264 doubled haploid (DH) lines mainly derived from two popular Texas wheat cultivars, TAM 114 and TAM 204, were developed at the AgriLife Research Center in Amarillo. The other parents are widely adopted and improved cultivars from the Southern Great Plains. Lines were evaluated in two field environments (Bushland-irrigated & Bush-land-dryland) planted in alpha lattice design during the 2020 crop season. Kernel traits (seed length, width, area, perimeter, and 1000 kernel weight) were collected using the hp Scanjet G4010 photo scanner for image capturing and GrainScan software for image analysis. This procedure offered a high throughput, precise, robust, and cost-effective seed phenotyping platform. Biomass parameters (plant weight, head count, head weight) were collected and processed manually. For genotyping genomic libraries were prepared and sequenced on Illumina NovaSeq 6000 to generate paired end reads of 150 bp. For single nucleotide polymorphism (SNP) calling, sequences were aligned to the IWGSC RefSeq genome assembly v2.1 using the Burrows Wheeler Aligner. The SNP filtration was performed at 50% missing data and 5% minor allele frequency. Finally, a set of 59842 polymorphic markers were retained for genetic analysis. To investigate the marker-trait association and the genomic regions, four genome-wide-association study (GWAS) models were implemented using the R package ‘Genome Association and Prediction Integrated Tool’ (GAPIT). Based on the Bonferroni correction < 8.41E-07 was used as a threshold to declare maker trait associations (MTA) significant. The BLINK model identified 12 MTA on chromosomes 1A, 2A, 2B, 4A, 4B, and 6B. 45% of the lines carried S2A_251496962 marker for the seed perimeter, while 42% and 39% lines carried S2A_498737202 and S2B_792756832 makers for 1000 KW and seed width, respectively. The identified MTA might be representing some known/major genes which need fur-ther confirmation.


  • Open Access

    Assessing the Effect of Drought on Winter Wheat Growth Using Unmanned Aerial System (UAS)-Based Phenotyping

    by Mahendra Bhandari, Shannon Baker, Jackie C. Rudd, Amir M. H. Ibrahim, Anjin Chang, Qingwu Xue, Jinha Jung, Juan Landivar, Brent Auvermann

    Drought significantly limits wheat productivity across the temporal and spatial domains. Unmanned Aerial Systems (UAS) has become an indispensable tool to collect refined spatial and high temporal resolution imagery data. A 2-year field study was conducted in 2018 and 2019 to determine the temporal effects of drought on canopy growth of winter wheat. Weekly UAS data were collected using red, green, and blue (RGB) and multispectral (MS) sensors over a yield trial consisting of 22 winter wheat cultivars in both irrigated and dryland environments. Raw-images were processed to compute canopy features such as canopy cover (CC) and canopy height (CH), and vegetation indices (VIs) such as Normalized Difference Vegetation Index (NDVI), Excess Green Index (ExG), and Normalized Difference Red-edge Index (NDRE). The drought was more severe in 2018 than in 2019 and the effects of growth differences across years and irrigation levels were visible in the UAS measurements. CC, CH, and VIs, measured during grain filling, were positively correlated with grain yield (r = 0.4–0.7, p < 0.05) in the dryland in both years. Yield was positively correlated with VIs in 2018 (r = 0.45–0.55, p < 0.05) in the irrigated environment, but the correlations were non-significant in 2019 (r = 0.1 to −0.4), except for CH. The study shows that high-throughput UAS data can be used to monitor the drought effects on wheat growth and productivity across the temporal and spatial domains.


  • Open Access

    Genome wide identification of QTL associated with yield and yield components in two popular wheat cultivars TAM 111 and TAM 112

    by Yan Yang, Smit Dhakal, Chenggen Chu, Shichen Wang, Qingwu Xue, Jackie C. Rudd, Amir M.H. Ibrahim, Kirk Jessup, Jason Baker, Maria Pilar Fuentealba, et al.

    Two drought-tolerant wheat cultivars, ‘TAM 111’ and ‘TAM 112’, have been widely grown in the Southern Great Plains of the U.S. and used as parents in many wheat breeding programs worldwide. This study aimed to reveal genetic control of yield and yield components in the two cultivars under both dryland and irrigated conditions. A mapping population containing 124 F 5:7 recombinant inbred lines (RILs) was developed from the cross of TAM 112/TAM 111. A set of 5,948 SNPs from the wheat 90K iSelect array and double digest restriction-site associated DNA sequencing was used to construct high-density genetic maps. Data for yield and yield components were obtained from 11 environments. QTL analyses were performed based on 11 individual environments, across all environments, within and across mega-environments. Thirty-six unique consistent QTL regions were distributed on 13 chromosomes including 1A, 1B, 1D, 2A, 2D, 3D, 4B, 4D, 6A, 6B, 6D, 7B, and 7D. Ten unique QTL with pleiotropic effects were identified on four chromosomes and eight were in common with the consistent QTL. These QTL increased dry biomass grain yield by 16.3 g m −2 , plot yield by 28.1 g m −2 , kernels spike −1 by 0.7, spikes m −2 by 14.8, thousand kernel weight by 0.9 g with favorable alleles from either parent. TAM 112 alleles mainly increased spikes m −2 and thousand kernel weight while TMA 111 alleles increased kernels spike −1 , harvest index and grain yield. The saturated genetic map and markers linked to significant QTL from this study will be very useful in developing high throughput genotyping markers for tracking the desirable haplotypes of these important yield-related traits in popular parental cultivars.