Browsing by Author "Okello, David Kalule"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Comparing Regression and Classification Models to Estimate Leaf Spot Disease in Peanut (Arachis hypogaea L.) for Implementation in Breeding Selection
    Chapu, Ivan; Chandel, Abhilash; Sie, Emmanuel Kofi; Okello, David Kalule; Oteng-Frimpong, Richard; Okello, Robert Cyrus Ongom; Hoisington, David; Balota, Maria (MDPI, 2024-04-30)
    Late leaf spot (LLS) is an important disease of peanut, causing global yield losses. Developing resistant varieties through breeding is crucial for yield stability, especially for smallholder farmers. However, traditional phenotyping methods used for resistance selection are laborious and subjective. Remote sensing offers an accurate, objective, and efficient alternative for phenotyping for resistance. The objectives of this study were to compare between regression and classification for breeding, and to identify the best models and indices to be used for selection. We evaluated 223 genotypes in three environments: Serere in 2020, and Nakabango and Nyankpala in 2021. Phenotypic data were collected using visual scores and two handheld sensors: a red–green–blue (RGB) camera and GreenSeeker. RGB indices derived from the images, along with the normalized difference vegetation index (NDVI), were used to model LLS resistance using statistical and machine learning methods. Both regression and classification methods were also evaluated for selection. Random Forest (RF), the artificial neural network (ANN), and k-nearest neighbors (KNNs) were the top-performing algorithms for both regression and classification. The ANN (R2: 0.81, RMSE: 22%) was the best regression algorithm, while the RF was the best classification algorithm for both binary (90%) and multiclass (78% and 73% accuracy) classification. The classification accuracy of the models decreased with the increase in classification classes. NDVI, crop senescence index (CSI), hue, and greenness index were strongly associated with LLS and useful for selection. Our study demonstrates that the integration of remote sensing and machine learning can enhance selection for LLS-resistant genotypes, aiding plant breeders in managing large populations effectively.
  • Thumbnail Image
    Exploration of Alternative Approaches to Phenotyping of Late Leaf Spot and Groundnut Rosette Virus Disease for Groundnut Breeding
    Chapu, Ivan; Okello, David Kalule; Okello, Robert C. Ongom; Odong, Thomas Lapaka; Sarkar, Sayantan; Balota, Maria (Frontiers, 2022-06-14)
    Late leaf spot (LLS), caused by Nothopassalora personata (Berk. & M.A Curt.), and groundnut rosette disease (GRD), [caused by groundnut rosette virus (GRV)], represent the most important biotic constraints to groundnut production in Uganda. Application of visual scores in selection for disease resistance presents a challenge especially when breeding experiments are large because it is resource-intensive, subjective, and error-prone. High-throughput phenotyping (HTP) can alleviate these constraints. The objective of this study is to determine if HTP derived indices can replace visual scores in a groundnut breeding program in Uganda. Fifty genotypes were planted under rain-fed conditions at two locations, Nakabango (GRD hotspot) and NaSARRI (LLS hotspot). Three handheld sensors (RGB camera, GreenSeeker, and Thermal camera) were used to collect HTP data on the dates visual scores were taken. Pearson correlation was made between the indices and visual scores, and logistic models for predicting visual scores were developed. Normalized difference vegetation index (NDVI) (r = -0.89) and red-green-blue (RGB) color space indices CSI (r = 0.76), v* (r = -0.80), and b* (r = -0.75) were highly correlated with LLS visual scores. NDVI (r = -0.72), v* (r = -0.71), b* (r = -0.64), and GA (r = -0.67) were best related to the GRD visual symptoms. Heritability estimates indicated NDVI, green area (GA), greener area (GGA), a*, and hue angle having the highest heritability (H-2 > 0.75). Logistic models developed using these indices were 68% accurate for LLS and 45% accurate for GRD. The accuracy of the models improved to 91 and 84% when the nearest score method was used for LLS and GRD, respectively. Results presented in this study indicated that use of handheld remote sensing tools can improve screening for GRD and LLS resistance, and the best associated indices can be used for indirect selection for resistance and improve genetic gain in groundnut breeding.