Godfree Chigeza - Academia.edu (original) (raw)

Uploads

Papers by Godfree Chigeza

Research paper thumbnail of Estimation of soybean grain yield from multispectral high-resolution UAV data with machine learning models in West Africa

Remote Sensing Applications: Society and Environment

Soybean (Glycine max (L.) Merr.) is a leguminous and oil crop with rapidly growing importance and... more Soybean (Glycine max (L.) Merr.) is a leguminous and oil crop with rapidly growing importance and demand in Africa following the increasing demand for oil and livestock and poultry feed in sub-Saharan Africa. However, soybean productivity is low in most countries of sub-Saharan Africa, especially in West Africa, where productivity is below one ton per ha. Hence, concerted soybean varietal development and testing efforts have been underway by the International Institute of Tropical Agriculture (IITA), collaborating with the various African and US-based soybean breeding programs. Integrating new varietal evaluation approaches based on advanced phenotyping techniques into IITA's soybean breeding program is crucial for designing efficient crop genetic improvement techniques. Hence, this work aims to investigate machine learning (ML) models and Unmanned Aerial vehicles (UAVs) to aid rapid high throughput phenotypic workflow for soybean yield estimation. We acquired multispectral images through a Sequoia® camera aboard a senseFly eBee X UAV from five variety trials during the 2020 growing season in Nigeria. UAV-based spectral bands, canopy height, vegetation indices (VI), and texture features were generated by gray level co-occurrence matrix (GLCM) and integrated to predict crop grain yield using five machine learning (ML) regression models, including Cubist, Extreme Gradient Boosting (XGBoost), Stochastic Gradient Boosting (GBM), Support vector machine (SVM), and Random Forest (RF). The main findings are the textural information generated using gray level co-occurrence matrix (GLCM) slightly outperformed predictors based mainly on vegetation indices (VI) and provided a promising alternative to the conventional use of VI in crop yield estimation. All the five ML models performed moderately well in predicting grain yield for all the soybean trials investigated, though the Cubist and RF model stood out, with R2 reaching 0.89. The study provides a framework to perform crop breeding trial assessments more effectively and consistently at high spatial scales that African crop breeding programs did not commonly apply. The workflow can also be successfully modified and applied for high throughput phenotyping of breeding platforms in other crops.

Research paper thumbnail of Genotype by environment effects on promiscuous nodulation in soybean (Glycine max L. Merrill

Background: Understanding factors influencing the expression of a trait is key in designing a bre... more Background: Understanding factors influencing the expression of a trait is key in designing a breeding program. Genotype by environment interaction has great influence on most quantitative traits. Promiscuous nodulation is a trait of importance for soybean production in Africa, because of the soil bacteria Bradyrhizobium japonicum not being indigenous in most African soils. Most soybean cultivars require B. japonicum for nodulation leading to the need for seed inoculation before sowing soybean in Africa. Few cultivars have capability to nodulate with Bradyrhizobia spp. that are different from B. japonicum and native in African soils. Such cultivars are termed " promiscuous cultivars. " Field experiments were conducted in six locations in Uganda for two seasons, to investigate the extent of environmental influences on the nodulation ability of promiscuous soybean genotypes. Results: Additive main effect and multiplicative interaction effects showed highly significant environment and genotype by environment (G × E) interaction effects on all nodulation traits. G × E interaction contributed more to the total variation than genotypes. The genotypes Kabanyolo I and WonderSoya were the most stable for nodules' dry weight (NDW), which is the nodulation trait the most correlated with grain yield. Genotype UG5 was the most stable for nodules' number (NN), and Nam II for nodules' effectiveness (NE). The genotype NamSoy 4M had the highest performance for NN, NFW, and NDW, but was less stable. WonderSoya had the highest NE. Genotype and genotype by environment analysis grouped environments into mega-environments (MEs), and four MEs were observed for NDW, with NamSoy 4M the winning genotype in the largest ME, and Kasese B the ideal environment for that nodulation trait. Conclusion: This study provides information that can guide breeding strategies. The low genetic effect that led to high environmental and G × E interaction effects raised the need for multi-environments testing before cultivar selection and recommendation. The study revealed genotypes that are stable and others that are high performing for nodulation traits, and which can be used as parental lines in breeding programs.

Research paper thumbnail of Fingerprinting of Zimbabwean maize hybrids and some elite lines to study heterotic patterns and genetic diversity for gray leaf spot resistance

Research paper thumbnail of Combining ability, indirect and correlated response to selection for oil yield in sunflower (Helianthus annuus) under contrasting moisture environments

Field Crops Research, 2014

ABSTRACT

Research paper thumbnail of The use of combining ability analysis to identify elite parents for Artemisia annua F1 hybrid production

PloS one, 2013

Artemisia annua is an important medicinal crop used for the production of the anti-malarial compo... more Artemisia annua is an important medicinal crop used for the production of the anti-malarial compound artemisinin. In order to assist in the production of affordable high quality artemisinin we have carried out an A. annua breeding programme aimed at improving artemisinin concentration and biomass. Here we report on a combining ability analysis of a diallel cross to identify robust parental lines for hybrid breeding. The parental lines were selected based on a range of phenotypic traits to encourage heterosis. The general combining ability (GCA) values for the diallel parental lines correlated to the positive alleles of quantitative trait loci (QTL) in the same parents indicating the presence of beneficial alleles that contribute to parental performance. Hybrids generated from crossing specific parental lines with good GCA were identified as having an increase in both artemisinin concentration and biomass when grown either in glasshouse or experimental field trials and compared to co...

Research paper thumbnail of Seed yield and associated trait improvements in sunflower cultivars over four decades of breeding in South Africa

Field Crops Research, 2012

Genetic improvement for seed yield and oil-content in sunflower cultivars was initiated in the ea... more Genetic improvement for seed yield and oil-content in sunflower cultivars was initiated in the early 1970s in South Africa. Since then no study has been carried out to assess the progress and contribution of new cultivars to seed yield improvement to justify continued investment into breeding new cultivars. The aim of this study was therefore to quantify the contribution of new cultivars to seed yield and associated traits in sunflower over four decades of breeding in South Africa. Two data-sets were used in this study:

Research paper thumbnail of Advanced cycle pedigree breeding in sunflower. I: Genetic variability and testcross hybrid performance for seed yield and other agronomic traits

Research paper thumbnail of Quantifying the relationship between heterosis and genetic distance for Gray Leaf Spot resistance in eight sub-tropical elite maize inbred lines using simple sequence repeats

Research paper thumbnail of Mode of inheritance of promiscuous nodulation and combining abilities in soybean genotypes

Knowledge of the mode of inheritance of a trait can be a powerful decision-making tool in a breed... more Knowledge of the mode of inheritance of a trait can be a powerful decision-making tool in a breeding program, as it helps predicting selection gain, defining breeding strategy and choosing parental lines. This study aimed at estimating genetic parameters to infer the mode of inheritance of promiscuous nodulation in soybean. Half diallel crosses were made among nine parental lines. F2 progenies were field evaluated together with parents for nodulation characteristics and grain yield in response to Bradyrhizobium sp. strain USDA 3456. Data on nodule number (NN), percent of effective nodules (NE), fresh and dry weight of nodules (NFW and NDW), and grain yield were subjected to analysis of variance, and progenies' means regression against parents' was performed following Griffing's Method2/Model 1. General and specific combining abilities, broad and narrow sense heritabilities, and Baker's ratio were estimated. The study showed predominant GCA effect for all measured traits except NE. Broad and narrow sense heritabilities were high for grain yield and NDW, moderate for NN and NFW, and low for NE. Baker's ratio was high for all measured traits except for NE. Overall, additive gene action was more important for all measured traits, except NE where non-additive gene action was more important. The high to moderate heritabilities for most traits showed that substantial gain can be achieved through selection.

Research paper thumbnail of Estimation of soybean grain yield from multispectral high-resolution UAV data with machine learning models in West Africa

Remote Sensing Applications: Society and Environment

Soybean (Glycine max (L.) Merr.) is a leguminous and oil crop with rapidly growing importance and... more Soybean (Glycine max (L.) Merr.) is a leguminous and oil crop with rapidly growing importance and demand in Africa following the increasing demand for oil and livestock and poultry feed in sub-Saharan Africa. However, soybean productivity is low in most countries of sub-Saharan Africa, especially in West Africa, where productivity is below one ton per ha. Hence, concerted soybean varietal development and testing efforts have been underway by the International Institute of Tropical Agriculture (IITA), collaborating with the various African and US-based soybean breeding programs. Integrating new varietal evaluation approaches based on advanced phenotyping techniques into IITA's soybean breeding program is crucial for designing efficient crop genetic improvement techniques. Hence, this work aims to investigate machine learning (ML) models and Unmanned Aerial vehicles (UAVs) to aid rapid high throughput phenotypic workflow for soybean yield estimation. We acquired multispectral images through a Sequoia® camera aboard a senseFly eBee X UAV from five variety trials during the 2020 growing season in Nigeria. UAV-based spectral bands, canopy height, vegetation indices (VI), and texture features were generated by gray level co-occurrence matrix (GLCM) and integrated to predict crop grain yield using five machine learning (ML) regression models, including Cubist, Extreme Gradient Boosting (XGBoost), Stochastic Gradient Boosting (GBM), Support vector machine (SVM), and Random Forest (RF). The main findings are the textural information generated using gray level co-occurrence matrix (GLCM) slightly outperformed predictors based mainly on vegetation indices (VI) and provided a promising alternative to the conventional use of VI in crop yield estimation. All the five ML models performed moderately well in predicting grain yield for all the soybean trials investigated, though the Cubist and RF model stood out, with R2 reaching 0.89. The study provides a framework to perform crop breeding trial assessments more effectively and consistently at high spatial scales that African crop breeding programs did not commonly apply. The workflow can also be successfully modified and applied for high throughput phenotyping of breeding platforms in other crops.

Research paper thumbnail of Genotype by environment effects on promiscuous nodulation in soybean (Glycine max L. Merrill

Background: Understanding factors influencing the expression of a trait is key in designing a bre... more Background: Understanding factors influencing the expression of a trait is key in designing a breeding program. Genotype by environment interaction has great influence on most quantitative traits. Promiscuous nodulation is a trait of importance for soybean production in Africa, because of the soil bacteria Bradyrhizobium japonicum not being indigenous in most African soils. Most soybean cultivars require B. japonicum for nodulation leading to the need for seed inoculation before sowing soybean in Africa. Few cultivars have capability to nodulate with Bradyrhizobia spp. that are different from B. japonicum and native in African soils. Such cultivars are termed " promiscuous cultivars. " Field experiments were conducted in six locations in Uganda for two seasons, to investigate the extent of environmental influences on the nodulation ability of promiscuous soybean genotypes. Results: Additive main effect and multiplicative interaction effects showed highly significant environment and genotype by environment (G × E) interaction effects on all nodulation traits. G × E interaction contributed more to the total variation than genotypes. The genotypes Kabanyolo I and WonderSoya were the most stable for nodules' dry weight (NDW), which is the nodulation trait the most correlated with grain yield. Genotype UG5 was the most stable for nodules' number (NN), and Nam II for nodules' effectiveness (NE). The genotype NamSoy 4M had the highest performance for NN, NFW, and NDW, but was less stable. WonderSoya had the highest NE. Genotype and genotype by environment analysis grouped environments into mega-environments (MEs), and four MEs were observed for NDW, with NamSoy 4M the winning genotype in the largest ME, and Kasese B the ideal environment for that nodulation trait. Conclusion: This study provides information that can guide breeding strategies. The low genetic effect that led to high environmental and G × E interaction effects raised the need for multi-environments testing before cultivar selection and recommendation. The study revealed genotypes that are stable and others that are high performing for nodulation traits, and which can be used as parental lines in breeding programs.

Research paper thumbnail of Fingerprinting of Zimbabwean maize hybrids and some elite lines to study heterotic patterns and genetic diversity for gray leaf spot resistance

Research paper thumbnail of Combining ability, indirect and correlated response to selection for oil yield in sunflower (Helianthus annuus) under contrasting moisture environments

Field Crops Research, 2014

ABSTRACT

Research paper thumbnail of The use of combining ability analysis to identify elite parents for Artemisia annua F1 hybrid production

PloS one, 2013

Artemisia annua is an important medicinal crop used for the production of the anti-malarial compo... more Artemisia annua is an important medicinal crop used for the production of the anti-malarial compound artemisinin. In order to assist in the production of affordable high quality artemisinin we have carried out an A. annua breeding programme aimed at improving artemisinin concentration and biomass. Here we report on a combining ability analysis of a diallel cross to identify robust parental lines for hybrid breeding. The parental lines were selected based on a range of phenotypic traits to encourage heterosis. The general combining ability (GCA) values for the diallel parental lines correlated to the positive alleles of quantitative trait loci (QTL) in the same parents indicating the presence of beneficial alleles that contribute to parental performance. Hybrids generated from crossing specific parental lines with good GCA were identified as having an increase in both artemisinin concentration and biomass when grown either in glasshouse or experimental field trials and compared to co...

Research paper thumbnail of Seed yield and associated trait improvements in sunflower cultivars over four decades of breeding in South Africa

Field Crops Research, 2012

Genetic improvement for seed yield and oil-content in sunflower cultivars was initiated in the ea... more Genetic improvement for seed yield and oil-content in sunflower cultivars was initiated in the early 1970s in South Africa. Since then no study has been carried out to assess the progress and contribution of new cultivars to seed yield improvement to justify continued investment into breeding new cultivars. The aim of this study was therefore to quantify the contribution of new cultivars to seed yield and associated traits in sunflower over four decades of breeding in South Africa. Two data-sets were used in this study:

Research paper thumbnail of Advanced cycle pedigree breeding in sunflower. I: Genetic variability and testcross hybrid performance for seed yield and other agronomic traits

Research paper thumbnail of Quantifying the relationship between heterosis and genetic distance for Gray Leaf Spot resistance in eight sub-tropical elite maize inbred lines using simple sequence repeats

Research paper thumbnail of Mode of inheritance of promiscuous nodulation and combining abilities in soybean genotypes

Knowledge of the mode of inheritance of a trait can be a powerful decision-making tool in a breed... more Knowledge of the mode of inheritance of a trait can be a powerful decision-making tool in a breeding program, as it helps predicting selection gain, defining breeding strategy and choosing parental lines. This study aimed at estimating genetic parameters to infer the mode of inheritance of promiscuous nodulation in soybean. Half diallel crosses were made among nine parental lines. F2 progenies were field evaluated together with parents for nodulation characteristics and grain yield in response to Bradyrhizobium sp. strain USDA 3456. Data on nodule number (NN), percent of effective nodules (NE), fresh and dry weight of nodules (NFW and NDW), and grain yield were subjected to analysis of variance, and progenies' means regression against parents' was performed following Griffing's Method2/Model 1. General and specific combining abilities, broad and narrow sense heritabilities, and Baker's ratio were estimated. The study showed predominant GCA effect for all measured traits except NE. Broad and narrow sense heritabilities were high for grain yield and NDW, moderate for NN and NFW, and low for NE. Baker's ratio was high for all measured traits except for NE. Overall, additive gene action was more important for all measured traits, except NE where non-additive gene action was more important. The high to moderate heritabilities for most traits showed that substantial gain can be achieved through selection.