Asheesh Kumar Singh

This study examines how soybean gene expression responds to heat stress and soil microbiome conditions, identifying gene targets for improving heat tolerance.

This study identifies genetic and environmental factors influencing soybean reproductive stages and develops a model to predict their effects.

This study examines how heat stress and soil microbial disturbance affect soybean root metabolites, microbiome profiles, and nodulation.

This study uses aerial imagery to phenotype iron deficiency chlorosis in soybean and performs GWAS to identify SNPs associated with IDC tolerance.

This paper compares genomic and phenomic prediction for soybean seed yield, protein, and oil content, finding phenomic prediction outperforms genomic for yield while genomic is better for protein and oil.

This paper identifies mega-environments in soybean breeding using historical field trial data and integrates genetic and non-genetic factors to analyze genotype by environment interactions.

The paper compares spatial adjustment methods in plant breeding trials, finding that XGBoost improves yield estimates by incorporating soil feature modeling at different scales.

This study identifies SNPs and heat-tolerant soybean accessions using GWAS and genomic prediction to improve breeding for heat stress tolerance.

The paper evaluates models to estimate genetic gain in soybean seed yield from multi-environment trials and finds all models are biased, recommending multiple models for accurate estimation.

PATRIOT improves genomic prediction accuracy in self-pollinating crops by tracing identical-by-descent segments, increasing accuracy by 16.6% over traditional methods.

This study performs a meta-GWAS on soybean data to identify quantitative trait loci (QTL) associated with various traits, finding 483 QTL at 393 unique loci and 66 candidate genes.

This paper uses deep learning to predict soybean yield by integrating genotype and weather data from historical trials.