Deep kernel of genomic and near infrared predictions in multi-environment breeding trials

Carlos Guzman Jose Crossa (2019, [Dataset])

In genomic prediction deep learning artificial neural network are part of machine learning methods that incorporate parametric, non-parametric and semi-parametric statistical models. Kernel methods are seeing more flexible, and easier to interpret than neural networks. Kernel methods used in genomic predictions comprise the linear genomic best linear unbiased predictor (GBLUP) kernel (GB) and the Gaussian kernel (GK). These kernels have being used with two statistical models, single environment and genomic × environment (GE) models. Recently near infrared spectroscopy (NIR) has being used as phenotype method for prediction of unobserved line performance in plant breeding trials. In this study, we used a non-linear Arc-cosine kernel (AK) that emulates deep learning artificial neural network. We compared AK prediction accuracy with GB and GK kernel methods in four genomic data sets one of them including also pedigree (ABLUP) and NIR (NBLUP) information. Results show that for all four data sets AK and GK kernels gave higher prediction accuracy than the linear GB kernel for single environment as well as GE multi-environment models. In addition, AK gave similar or slightly higher prediction accuracy than the GK kernel.

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

21st High Rainfall Wheat Yield Trial

Ravi Singh Thomas Payne (2019, [Dataset])

CIMMYT annually distributes improved germplasm developed by its researchers and partners in international nurseries trials and experiments. The High Rainfall Wheat Yield Trial (HRWYT) contains very top-yielding advance lines of spring bread wheat (Triticum aestivum) germplasm adapted to high rainfall, Wheat Mega-environment 2 (ME2HR).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

17th High Rainfall Wheat Yield Trial

Ravi Singh Thomas Payne (2019, [Dataset])

CIMMYT annually distributes improved germplasm developed by its researchers and partners in international nurseries trials and experiments. The High Rainfall Wheat Yield Trial (HRWYT) contains very top-yielding advance lines of spring bread wheat (Triticum aestivum) germplasm adapted to high rainfall, Wheat Mega-environment 2 (ME2HR).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

15th High Rainfall Wheat Yield Trial

Ravi Singh Thomas Payne (2019, [Dataset])

CIMMYT annually distributes improved germplasm developed by its researchers and partners in international nurseries trials and experiments. The High Rainfall Wheat Yield Trial (HRWYT) contains very top-yielding advance lines of spring bread wheat (Triticum aestivum) germplasm adapted to high rainfall, Wheat Mega-environment 2 (ME2HR).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

12th High Rainfall Wheat Yield Trial

Ravi Singh Thomas Payne (2019, [Dataset])

CIMMYT annually distributes improved germplasm developed by its researchers and partners in international nurseries trials and experiments. The High Rainfall Wheat Yield Trial (HRWYT) contains very top-yielding advance lines of spring bread wheat (Triticum aestivum) germplasm adapted to high rainfall, Wheat Mega-environment 2 (ME2HR).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

25th High Rainfall Wheat Yield Trial

Ravi Singh Thomas Payne (2019, [Dataset])

CIMMYT annually distributes improved germplasm developed by its researchers and partners in international nurseries trials and experiments. The High Rainfall Wheat Yield Trial (HRWYT) contains very top-yielding advance lines of spring bread wheat (Triticum aestivum) germplasm adapted to high rainfall, Wheat Mega-environment 2 (ME2HR).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

15th High Rainfall Wheat Screening Nursery

Ravi Singh Thomas Payne (2019, [Dataset])

CIMMYT annually distributes improved germplasm developed by its researchers and partners in international nurseries trials and experiments. The High Rainfall Wheat Screening Nursery (HRWSN) contains spring bread wheat (Triticum aestivum) germplasm adapted to high rainfall areas (Mega-environment 2).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

13th Semi-Arid Wheat Yield Trial

Ravi Singh Thomas Payne (2015, [Dataset])

The Semi-Arid Wheat Yield Trial (SAWYT) is a replicated yield trial that contains spring bread wheat (Triticum aestivum) germplasm adapted to low rainfall, drought prone environments typically receiving less than 500 mm of water available during the cropping cycle. The combination of water-use efficiency and water responsive broad adaptation plus yield potential is important in drought environments where rainfall is frequently erratic across and within years. Stripe rust, leaf rust and stem rust, root rots, nematodes, and bunts are the key biotic constraints. Typical target environments include winter rain or Mediterranean-type drought associated with post-flowering moisture stress and heat stress such as those found at Aleppo (Syria), Settat (Morocco) and Marcos Juarez (Argentina), all classified by CIMMYT within Wheat Mega Environment 4 (Low rainfall, semi-arid environment; ME4: SA). It is distributed to 150 locations, and contains 50 entries.

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

Use of hyperspectral reflectance-derived relationship matrices for genomic prediction of grain yield in wheat - data for publication

Suchismita Mondal Margaret Krause Philomin Juliana Jesse Poland Susanne Dreisigacker Ravi Singh (2018, [Dataset])

Genomic, pedigree, grain yield and hyperspectral data for the manuscript

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

31st Elite Selection Wheat Yield Trial

Ravi Singh Thomas Payne (2017, [Dataset])

The Elite Selection Wheat Yield Trial (ESWYT) is a replicated yield trial that contains spring bread wheat (Triticum aestivum) germplasm adapted to Mega-environment 1 (ME1) which represents the optimally irrigated, low rainfall areas. Major stresses include leaf, stem and yellow rusts, Karnal bunt, and lodging. Representative areas include the Gangetic Valley (India), the Indus Valley (Pakistan), the Nile Valley (Egypt), irrigated river valleys in parts of China (e.g. Chengdu), and the Yaqui Valley (Mexico). This ME encompasses 36 million hectares spread primarily over Asia and Africa between 350S -350N latitudes. White (amber)-grained types are preferred by consumers of wheat in the vast majority of the areas. It is distributed to upto 200 locations and contains 50 entries.

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA