Permanent record · RIR–2048

Developing Predictive Models for Dynamic Intermediate Phenotypes in Climate-Resilient Crop Breeding Programs

Static snapshots of crop traits often fail to capture the dynamic responses required for climate resilience. This study explores the integration of explainable AI to predict intermediate phenotypes throughout the crop growth cycle.

Open to researchQualified 90/100P4 provenance

Primary research question

Can explainable machine learning models accurately predict dynamic intermediate phenotypes to improve climate-resilient crop selection?

Knowledge gap

What remains worth asking

The source suggests that current breeding methods rely on static data, potentially missing critical growth-stage-specific responses to climate stress.

Potential contribution

Why it may matter

Improving the accuracy of trait prediction will significantly shorten breeding cycles for climate-adapted crop varieties.

Academic placement

OECD fields and topic tags

4.4Agricultural biotechnology

Plant BreedingComputational BiologyAgricultural Technology

Scope: Controlled environment and field-based crop breeding trials. · Method signals: Machine Learning, Phenotyping, Time-series Analysis

Possible study pathways

One question, different levels

Research master’s

Plant genomics and data science

Doctoral

Computational plant science

originalityAdvanced

methodologyAdvanced

Data accessModerate

ethicsAccessible

Qualification signal

90/100

Requires high-quality longitudinal phenotypic data
Focus on model interpretability
Open-access scholarly source and DOI metadata verified

Provenance

Research Idea Registry curation

DOI and bibliographic metadata independently resolved
Open-access status verified
The research direction is transparently marked as AI-inferred

The public contributor code contains no name or account email.

APA 7 source

Jiang, S., & Yan, J. (2026). Beyond static snapshots: predicting dynamic, explainable intermediate phenotypes for climate-resilient crop breeding. Frontiers in Plant Science, 17, Article 1873747. https://doi.org/10.3389/fpls.2026.1873747

Paper abstract and discussion context; AI-inferred direction

Open source ↗