Yangyang Song’s research while affiliated with Mississippi State University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (11)


HyperPRI: A dataset of hyperspectral images for underground plant root study
  • Article

October 2024

·

21 Reads

·

2 Citations

Computers and Electronics in Agriculture

Spencer J. Chang

·

·

Yangyang Song

·

[...]

·

Alina Zare

Relationship between relative pod yield and soil test potassium using a linear quadratic plateau model. Data is separated by soil series of Marietta (top) and Leeper (bottom). Critical point (CP) is the segment at which the slope is equal to zero.
Normalized difference vegetative index (NDVI) for each soil test potassium (STK) treatment during the 2019 growing season. The STK treatments, denoted as K0 (128 lbs ac⁻¹), K1 (167 lbs ac⁻¹), K2 (191 lbs ac⁻¹), and K3 (225 lbs ac⁻¹), were determined through soil sample analysis taken right after planting in 2019. These values were then averaged across two distinct soil series, Leeper and Marietta. Data points were presented as mean value ± standard error.
Relationship between leaflet potassium and soil test potassium for the Leeper (left) and Marietta (right) soil series. Leaflet samples were collected at 65 (top) and 100 (bottom) days after planting (DAP) in 2019 and 2020. Dashed lines represent the leaflet potassium amounts (y‐axis) at the critical soil test potassium amount (x‐axis) where pod yield ceased to increase. Data points in each panel were leaflet potassium values from plants that were cultivated on Leeper or Marietta soil at 65 or 100 DAP in 2019 and 2020.
Peanut cultivar response to residual soil test potassium in North Mississippi
  • Article
  • Publisher preview available

September 2024

·

30 Reads

The average U.S. peanut (Arachis hypogaea L.) yield has increased by approximately 25% with the adoption of peanut cultivar ‘Georgia‐06G’. Since this adoption, many new high yielding runner cultivars with similar yield potential have been released. However, current nutrient recommendations are based on soil tests that were developed prior to the release of Georgia‐06G. Particularly for potassium, current soil test potassium (STK) critical values were established on soil textures with relatively low cation exchange capacity (CEC) but were not validated on soil textures with high CEC. This study aimed to evaluate the growth and yield response of five recently released peanut cultivars to four STK levels ranging from very low to medium based on Mississippi State University Extension soil testing recommendations. The STK classification levels were also based on two soil series categorized with high CEC—Leeper (∼38.4 meq 100 g⁻¹) and Marietta (∼15.9 meq 100 g⁻¹) soil series. Cultivars Georgia‐06G, ‘Georgia‐16HO’, ‘Georgia‐18RU’, FloRun ‘331’, and ‘AU‐NPL‐17’ were evaluated in this study. No STK × variety interaction occurred, indicating similar K requirements across all varieties evaluated. However, a positive pod yield response occurred in both soil types when the average STK increased from 128 to 167 lbs ac⁻¹ for all cultivars and site years. Critical STK values on both soils were greater than many current Extension recommendations, and the critical STK value of Leeper is greater than the Marietta soil series, likely due to the higher CEC value. These results demonstrate the need to adjust peanut STK sufficiency levels based on soil CEC. Further evaluation of modern peanut cultivar productivity response to STK sufficiency levels is needed for soils with moderate CEC.

View access options

Cost-efficient Active Illumination Camera For Hyper-spectral Reconstruction

June 2024

·

53 Reads

·

1 Citation

Hyper-spectral imaging has recently gained increasing attention for use in different applications, including agricultural investigation, ground tracking, remote sensing and many other. However, the high cost, large physical size and complicated operation process stop hyperspectral cameras from being employed for various applications and research fields. In this paper, we introduce a cost-efficient, compact and easy to use active illumination camera that may benefit many applications. We developed a fully functional prototype of such camera. With the hope of helping with agricultural research, we tested our camera for plant root imaging. In addition, a U-Net model for spectral reconstruction was trained by using a reference hyperspectral camera's data as ground truth and our camera's data as input. We demonstrated our camera's ability to obtain additional information over a typical RGB camera. In addition, the ability to reconstruct hyperspectral data from multi-spectral input makes our device compatible to models and algorithms developed for hyperspectral applications with no modifications required.


Hyperspectral signals in the soil: Plant-soil hydraulic connection and disequilibrium as mechanisms of drought tolerance and rapid recovery

June 2024

·

73 Reads

·

3 Citations

Plant Cell and Environment

Predicting soil water status remotely is appealing due to its low cost and large‐scale application. During drought, plants can disconnect from the soil, causing disequilibrium between soil and plant water potentials at pre‐dawn. The impact of this disequilibrium on plant drought response and recovery is not well understood, potentially complicating soil water status predictions from plant spectral reflectance. This study aimed to quantify drought‐induced disequilibrium, evaluate plant responses and recovery, and determine the potential for predicting soil water status from plant spectral reflectance. Two species were tested: sweet corn ( Zea mays ), which disconnected from the soil during intense drought, and peanut ( Arachis hypogaea ), which did not. Sweet corn's hydraulic disconnection led to an extended ‘hydrated’ phase, but its recovery was slower than peanut's, which remained connected to the soil even at lower water potentials (−5 MPa). Leaf hyperspectral reflectance successfully predicted the soil water status of peanut consistently, but only until disequilibrium occurred in sweet corn. Our results reveal different hydraulic strategies for plants coping with extreme drought and provide the first example of using spectral reflectance to quantify rhizosphere water status, emphasizing the need for species‐specific considerations in soil water status predictions from canopy reflectance.



Effect of Spray Adjuvant and Prohexadione Calcium Formulation on Peanut (Arachis hypogaea L.) Productivity

January 2024

·

5 Reads

Peanut Science

Prohexadione calcium (calcium 3-oxido-5-oxo-4-propionylcyclohex-3-enecarboxylate) is used to manage excessive vegetative growth in peanut (Arachis hypogaea L.). This practice has traditionally been more widespread in Virginia market-type cultivars that generally have more vigorous canopy growth. However, the use of this active ingredient in runner peanut cultivation continues to increase. Prohexadione calcium was initially formulated as a water dispersible granule (WDG) and a new oil dispersion (OD) formulation has been introduced. Limited information is available regarding optimal adjuvants and application rates for the OD formulation of prohexadione calcium. This study aims to assess the efficacy of the new OD formulation of prohexadione calcium on pod yield, grade and economic return. Six experiments were conducted across locations in Mississippi and Georgia in 2022. The findings indicate that the OD formulation yields similar effects in managing excessive vine growth when using either crop oil concentrate or non-ionic surfactant adjuvants, thereby resulting in comparable yield, grade, and economic return to that of the WDG formulation. Moreover, prohexadione calcium exhibits the capacity to suppress excessive vegetative growth and enhance pod yield at reduced application rates, specifically at105 g ai/ha. This reduction in application rate, coupled with the improvement in yield, translated into a higher return on investment, ranging from 30 to 400 U.S. dollars per hectare, across three out of four experimental sites when compared to the non-treated control. These results suggest that profitability could be increased by applying prohexadione calcium on runner peanuts if excessive vine growth occurs.


Figure 5: SpectralUNET architecture. The numbers represent the dimensionality of a layer's output. Blocks in green represent concatenated information from previous feedforward layers.
Figure 7: Raw reflectance comparisons between root and soil spectral signatures across 15 peanut rhizoboxes. Both root and soil plots show their distributions are skewed toward a higher reflectance compared to their means.
Figure 8: Precision-Recall curves for UNET, SpectralUNET, and CubeNET on the five splits of data. Across multiple confidence thresholds, CubeNET demonstrates more robustness.
Figure 9: Validation confusion matrix results for UNET, SpectralUNET, and CubeNET across the five splits of data. Utilizing both hyperspectral and spatial features, CubeNET achieves improved precision and greater consistency in predicting roots.
Figure 11: Selected dataset annotation comparisons for two annotators' ground truth masks. Darkened and green pixels represent consistent annotations between Person 1 and 2, while red and blue show differing true positive annotations for Person 1 and 2, respectively.
HyperPRI: A Dataset of Hyperspectral Images for Underground Plant Root Study

September 2023

·

105 Reads

·

1 Citation

Collecting and analyzing hyperspectral imagery (HSI) of plant roots over time can enhance our understanding of their function, responses to environmental factors, turnover, and relationship with the rhizosphere. Current belowground red-green-blue (RGB) root imaging studies infer such functions from physical properties like root length, volume, and surface area. HSI provides a more complete spectral perspective of plants by capturing a high-resolution spectral signature of plant parts, which have extended studies beyond physical properties to include physiological properties, chemical composition, and phytopathology. Understanding crop plants' physical, physiological, and chemical properties enables researchers to determine high-yielding, drought-resilient genotypes that can withstand climate changes and sustain future population needs. However, most HSI plant studies use cameras positioned above ground, and thus, similar belowground advances are urgently needed. One reason for the sparsity of belowground HSI studies is that root features often have limited distinguishing reflectance intensities compared to surrounding soil, potentially rendering conventional image analysis methods ineffective. In the field of machine learning (ML), there are currently no publicly available datasets containing the heavy correlation, highly textured background, and thin features characteristic of belowground root systems. Here we present HyperPRI, a novel dataset containing RGB and HSI data for in situ, non-destructive, underground plant root analysis using ML tools. HyperPRI contains images of plant roots grown in rhizoboxes for two annual crop species - peanut ( Arachis hypogaea ) and sweet corn ( Zea mays ). Drought conditions are simulated once, and the boxes are imaged and weighed on select days across two months. Along with the images, we provide hand-labeled semantic masks and imaging environment metadata. Additionally, we present baselines for root segmentation on this dataset and draw comparisons between methods that focus on spatial, spectral, and spatial-spectral features to predict the pixel-wise labels. Results demonstrate that combining HyperPRI's hyperspectral and spatial information improves semantic segmentation of target objects.


Effects of reduced rainfall on coffee quality and volatile composition

September 2023

·

203 Reads

·

1 Citation

BACKGROUND For a significant subset of agricultural products, including coffee, wine and tea, sensory perceptions of terroir (i.e., characteristic flavors imparted by the growing environment) are tightly linked to the product's value. With increasing climate change, it is critical to understand how shifts in climate, such as changes in precipitation, may interact with management practices (e.g., cultivar selection) to impact sensory quality in terroir‐driven crops, and what biochemical compounds may be associated with those impacts. Here, sensory quality and volatile profile composition were assessed for four Arabica coffee (Coffea arabica) cultivars grown in a field experiment where precipitation was reduced by rainout shelters, resulting in 14% lower soil moisture on average. RESULTS Our results indicate an overall increase in yield coincident with a moderate decrease in sensory quality in response to reduced precipitation. The presence and magnitude of the sensory quality shift varied by cultivar and sensory attribute, though the Acidity attribute was consistently negatively impacted across cultivars, albeit with a high degree of uncertainty. Additionally, 31 volatile compounds were identified across green coffee samples that were variably impacted by reduced precipitation. Hierarchical clustering analysis identified patterns in volatile clustering associated with sensory attributes suggesting that reduced precipitation effects on sensory attributes may depend on nonlinear combinations of secondary metabolites. CONCLUSION Ultimately, our results advance efforts to improve predictions of climate impacts on coffee‐growing landscapes and communities and highlight the value of considering indicators of harvest value beyond yield to improve economic forecasts for agroecosystems under climate change.


Genotypic stability in root system architecture and aboveground biomass revealed diverse adaptability of peanut ( Arachis hypogaea L.) to moderate water deficit

August 2023

·

16 Reads

Journal of Agronomy and Crop Science

Many crop species, including cultivated peanut ( Arachis hypogaea L.), modify their above‐ and below‐ground growth to cope with water deficit stress. This acclimation to water deficit often triggers a biomass partitioning shift—allocating more biomass to the roots, to increase the accessibility of roots to water resources. However, additional carbon partitioning to roots may not always translate into increased water use and maintenance of aboveground biomass (ABM) and yield. Therefore, selecting an efficient root system architecture (RSA) should aim to sustain a high ABM production under a water deficit scenario. To better understand the associations of above and belowground biomass partitioning under moderate water deficit, this study evaluated the genotypic stability of 40 peanut genotypes in ABM and RSA in greenhouse experiments and further assessed genotypic differences in 4 site‐year field experiments. Our results suggested that higher ABM‐producing genotypes generally had high plasticity when subjected to water deficit whereas the low ABM‐producing genotypes had relatively high stability. Hierarchical clustering analysis further revealed that genotypes with a high root‐to‐shoot ratio potentially had increased genotypic stability in ABM underwater deficit. Interestingly, genotypes that maintained the highest ABM underwater deficit did not have the highest total root biomass and length. Instead, these genotypes had the highest root length in the top layer of soil (0–0.3 m) and relatively fewer roots in the deeper layer of soil (0.3–1 m). Greenhouse‐screened stable genotypes exhibited minimal yield reduction when subjected to mid‐season water deficit in some of the field validation experiments, but it also happened to some plastic genotypes, indicating that further validation of controlled environment screenings for genotypic water‐deficit tolerance in the field is necessary.


Impact of seed maturity on season-long physiological performance and offspring seed quality in peanut (Arachis hypogaea L.)

November 2022

·

51 Reads

·

11 Citations

Field Crops Research

Cultivated peanut produces pods of varying maturity throughout most of the plant developmental stages, often leading to a considerable proportion of immature seeds at harvest. Plants originating from immature seeds not only have reduced emergence and physiological performance, but also reduced vigor of both mature and immature seeds produced in subsequent generations. Therefore, seed maturity effects on plant performance could potentially extend from physiology to the initiation and progression of reproduction. This study aimed to elucidate the impacts of seed maturity on plant performance and productivity. In this two-year experiment, season-long physiological and reproductive performance was compared among plants established from mature and immature seed of eight peanut cultivars differing in maturity potential. Our results suggest that plants produced from mature seeds had higher emergence and canopy coverage than plants produced from immature seeds over the season. Further, descendent seed quality was also affected: plants that originated from immature seeds produced mature seeds with average 9.91 % decreased mass, particularly for those formed earliest in plant development, and average 37.18 % less mature pods formed latest in plant development. At harvest, seeds were collected and tested for biochemical characteristics. Seeds that were produced by plants originating from mature seeds generally had higher carbohydrates, protein, oleic acids and lower lipid content than seeds produced by plants originating from immature seeds. Given these results, the use of mature seeds in production appears to be of utmost importance for both the performance of the subsequent plant and the resulting quality of the seed produced by these plants.


Citations (6)


... Additionally, VNIR HSI has been utilized to predict lead stress levels in oilseed rape leaves and roots [15], classify growth years of Kudzu roots [16], and distinguish between leaf mold and soil in the rhizosphere [17]. VNIR HSI has also recently been used to monitor the roots of peanut and sweet corn under varying drought conditions, with this data available in a publicly accessible HyperPRI dataset [18]. This dataset was useful to develop models that predict root and soil water potentials, enhancing our understanding of drought tolerance and recovery in crops [18,19]. ...

Reference:

Advancing hyperspectral imaging techniques for root systems: a new pipeline for macro- and microscale image acquisition and classification
HyperPRI: A dataset of hyperspectral images for underground plant root study
  • Citing Article
  • October 2024

Computers and Electronics in Agriculture

... Image segmentation and classification is a vital aspect of HSI analysis, which have proven to be challenging for agricultural tasks such as detecting disease and pest damage on leaves [41,42], or identifying weeds in crops fields [43]. Segmenting roots from soil presents even greater challenges due the heterogenous nature of soil and, depending on the soil type, the potential spectral similarities between dry soil and living roots or wet soil and dead roots [18,44]. Thus, high resolution hyperspectral images are necessary to accurately classify soil-grown root systems. ...

Cost-efficient Active Illumination Camera For Hyper-spectral Reconstruction

... VNIR HSI has also recently been used to monitor the roots of peanut and sweet corn under varying drought conditions, with this data available in a publicly accessible HyperPRI dataset [18]. This dataset was useful to develop models that predict root and soil water potentials, enhancing our understanding of drought tolerance and recovery in crops [18,19]. The availability of such data, along with detailed acquisition methodologies and spectral signatures, is crucial for advancing research on rhizosphere processes. ...

Hyperspectral signals in the soil: Plant-soil hydraulic connection and disequilibrium as mechanisms of drought tolerance and rapid recovery
  • Citing Article
  • June 2024

Plant Cell and Environment

... Direct measurements of plant water status have predominantly focused on above-ground tissues, while monitoring root water status has been limited due to the difficulty in accessing roots (Chang et al., 2023). Commonly used leaf water status metrics include leaf equivalent water thickness (EWT), relative water content (RWC), and leaf water potential (Ψ leaf ). ...

HyperPRI: A Dataset of Hyperspectral Images for Underground Plant Root Study

... At this point, the seed has its maximum accumulation of oil content, a chemical compound that fundamentally contributes to its vigor [18,52] (Figure 1A). Two notable examples of these contributions are: (i) protection against reactive oxygen species (ROS) to delay cellular aging during storage (e.g., tocopherol) [19,53]; and (ii) serving as an energy source for the establishment of high-performance seedlings months after harvesting [14,54] (Figure 1F). Notably, the contributions of oil reserves to ROS stability are exclusive to seeds at late stages [9,55]. ...

Impact of seed maturity on season-long physiological performance and offspring seed quality in peanut (Arachis hypogaea L.)
  • Citing Article
  • November 2022

Field Crops Research

... The advancement of real-time spectral prediction techniques enables the continuous and noninvasive assessment of leaf water status, such as leaf EWT (Féret et al., 2019), leaf RWC (Ihuoma & Madramootoo, 2019) and the turgor loss point (Castillo-Argaez et al., 2024). However, recent root imaging technologies, such as digging out and imaging (Le Bot et al., 2010;Shen et al., 2020), magnetic resonance imaging (Haber-Pohlmeier et al., 2019;Pflugfelder et al., 2017), minirhizotron (MR) systems (Gloaguen et al., 2019;Zurweller et al., 2018) and rhizoboxes Song et al., 2021), have primarily focused on root phenology and structure, including rooting depth, root length, root surface area and root volume. Among the various options, for field studies of root water status, the MR system would be ideal if appropriate spectral reflectance sensing technology could be developed. ...

Multiple‐generation seed maturity effects on seedling vigour in a production environment
  • Citing Article
  • October 2021

Journal of Agronomy and Crop Science