GPU-Enhanced Predictive Models for Agricultural Genomics

EasyChair Preprint 14126

Abstract

In recent years, advancements in agricultural genomics have revolutionized crop breeding and management practices, driving the need for more efficient computational tools. This paper explores the application of GPU-enhanced predictive models to advance agricultural genomics, focusing on how GPU acceleration can improve the accuracy and speed of genomic analyses. We investigate various deep learning and machine learning techniques optimized for GPU architectures to handle large-scale genomic datasets, including single nucleotide polymorphisms (SNPs), gene expression profiles, and quantitative trait loci (QTLs). By leveraging GPUs' parallel processing capabilities, our approach significantly reduces the time required for data processing and model training, enabling real-time predictions and more precise genetic insights. Case studies highlight the effectiveness of these models in predicting crop yields, disease resistance, and stress tolerance, showcasing their potential to enhance crop management and breeding strategies. This study demonstrates that GPU-enhanced predictive models offer a transformative solution for tackling the complexities of agricultural genomics, ultimately contributing to more sustainable and productive agricultural practices.

Keyphrases: Central Processing Units (CPUs), Quantitative trait loci (QTLs), Single Nucleotide Polymorphisms (SNPs)

@booklet{EasyChair:14126,
  author    = {Abi Litty},
  title     = {GPU-Enhanced Predictive Models for Agricultural Genomics},
  howpublished = {EasyChair Preprint 14126},
  year      = {EasyChair, 2024}}