Predictive machine learning for resilient corn hybrids

Overview

This innovative research leverages machine learning (ML) to analyze and predict the performance of modern corn hybrids. By examining molecular, structural, and chemical transformations induced by selective breeding, this approach aims to develop corn varieties that are more resilient to climate variability and optimized for high yield and stress tolerance. The ultimate goal is to enhance food system resilience by providing a blueprint for developing crops that can thrive under future agronomic conditions.

Technical specifications

The research involves comprehensive analysis of modern corn hybrids through molecular (DNA/RNA sequencing), structural (imaging, HPSEC, FTIR, DSC, X-RAY), and chemical (mass spectrometry) techniques. These data inputs are used to train ML models capable of predicting phenotypic outcomes, such as yield and stress adaptability. The integration of these advanced methodologies allows for a deeper understanding of the biological mechanisms behind enhanced agronomic traits in corn, enabling the development of high-performing, resilient crop varieties.

Technology readiness level

This project is currently at Technology Readiness Level 2, indicating that the research is in the early stages of defining the technological principles and analytical methods required for future development. The work is focused on detailed analysis and model development to validate the approach, with the aim of guiding future breeding strategies for resilient corn varieties.