Lyndel W. Meinhardt

This study uses a GWAS and machine learning framework to identify genetic signals related to protein-synthesis pathways that influence cacao yield after correcting for population structure.

This paper develops a taxonomy-agnostic workflow using hyperspectral imaging and machine learning to predict fungal isolate crop-source labels with 86.7% accuracy.

This paper introduces a probabilistic UV-C control framework and a shape-only morphological fingerprint to predict postharvest pathogen survival and origin in cacao and coffee.

The paper introduces an eligibility-aware pipeline to improve ITS diagnostics in fungi by addressing database incompleteness and primer performance issues, demonstrating its utility in cacao pathosystems.

This study identifies population-specific genetic strategies for agronomic traits in Coffea canephora using genomic analysis and machine learning, revealing distinct biological pathways in two populations.

The paper investigates differential UVB and UVC responses in plant pathogenic fungi using hyperspectral imaging and machine learning, finding UVC more effective and Pestalotiopsis sp. more resistant than C. gloeosporioides.