VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!

Browsing by Author "Rajan, Nithya"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Detection of Italian Ryegrass in Wheat and Prediction of Competitive Interactions Using Remote-Sensing and Machine-Learning Techniques
    Sapkota, Bishwa; Singh, Vijay; Neely, Clark; Rajan, Nithya; Bagavathiannan, Muthukumar V. (MDPI, 2020-09-13)
    Italian ryegrass (Lolium perenne ssp. multiflorum (Lam) Husnot) is a troublesome weed species in wheat (Triticum aestivum) production in the United States, severely affecting grain yields. Spatial mapping of ryegrass infestation in wheat fields and early prediction of its impact on yield can assist management decision making. In this study, unmanned aerial systems (UAS)-based red, green and blue (RGB) imageries acquired at an early wheat growth stage in two different experimental sites were used for developing predictive models. Deep neural networks (DNNs) coupled with an extensive feature selection method were used to detect ryegrass in wheat and estimate ryegrass canopy coverage. Predictive models were developed by regressing early-season ryegrass canopy coverage (%) with end-of-season (at wheat maturity) biomass and seed yield of ryegrass, as well as biomass and grain yield reduction (%) of wheat. Italian ryegrass was detected with high accuracy (precision = 95.44 ± 4.27%, recall = 95.48 ± 5.05%, F-score = 95.56 ± 4.11%) using the best model which included four features: hue, saturation, excess green index, and visible atmospheric resistant index. End-of-season ryegrass biomass was predicted with high accuracy (R2 = 0.87), whereas the other variables had moderate to high accuracy levels (R2 values of 0.74 for ryegrass seed yield, 0.73 for wheat biomass reduction, and 0.69 for wheat grain yield reduction). The methodology demonstrated in the current study shows great potential for mapping and quantifying ryegrass infestation and predicting its competitive response in wheat, allowing for timely management decisions.
  • Thumbnail Image
    Modeling Carbon Uptake of Dryland Maize Using High Resolution Satellite Imagery
    Menefee, Dorothy; Rajan, Nithya; Shafian, Sanaz; Cui, Song (Frontiers, 2022-03)
    Quantifying carbon uptake or gross primary production (GPP) from agroecosystems is important for understanding the spatial and temporal dynamics of carbon fixation by crops. The availability of high-resolution remote sensing data can significantly improve GPP estimation of small-scale agricultural fields. Multispectral satellite data with 3-m spatial resolution and frequent global coverage are available from the PlanetScope network of satellites. However, this data remains largely unexplored for studying the carbon dynamics of agroecosystems. The overarching goal of this study was to develop a simple empirical method for quantifying the GPP of dryland maize (Zea mays L.) using remotely sensed vegetation indices along with in-situ measurements of photosynthetically active radiation and leaf area index by linking it with carbon uptake data from an eddy covariance flux tower. Four vegetation indices were investigated: the normalized difference vegetation index (NDVI), the soil adjusted vegetation index (SAVI), the weighted difference vegetation index (WDVI), and the two-band enhanced vegetation index (EVI2). This study was conducted over a three-year period from 2017 to 2019 in East-Central Texas. A total of 12 GPP prediction models were developed using individual yearly data and were used for predicting GPP of the other 2 years. Predicted maize GPP values were then compared against tower-based GPP. The NDVI models were the least successful in predicting GPP and had the highest root mean square error (average: 10.1 3 gC m−2; maximum: 26.3 gC m−2). Models based on SAVI performed especially well with error ranging from 0.05 to 0.94 gC m−2. The slope of the regression between SAVI-based estimated GPP and measured GPP was not different from 1.0 in all combinations of years. The success of the SAVI-based GPP models for predicting dryland maize carbon uptake indicates that it was the least affected vegetation index by changing soil background condition in this row cropping system.