From Image Series to Resilient Soybean Genotypes: Transformer-Based Canopy Cover Extraction and Weather-Informed Nonlinear Modeling

2026 Preprint

View at publisher
Authors: Beat Keller, Jovin Koller, Corina Oppliger, Tatiana Bielakova, M. Lob, Paul Stephan, Andreas Hund, Christoph Barendregt, Claude‐Alain Bétrix, Fabio Sigrist, Martin Maechler, Achim Walter
DOI: 10.22541/au.177088529.95951774/v1
Cited by: 0

Abstract

Green canopy cover dynamics extracted from high-throughput RGB imagery via automated labeled segmentation enabled nonlinear modeling that accounted for short-term weather variation, explaining up to 56% of protein yield variation in 150 soybean genotypes across ten seasons and enabling prediction in new environments as well as identification of tolerant genotypes.

Fields of Study & Subjects

Remote Sensing in Agriculture Smart Agriculture and AI Soybean genetics and cultivation

Publication details

Publication date
12 February 2026
Language
EN
Document type
Preprint