ProbStab: A probabilistic ML-assisted pipeline for genotype performance, stability, and risk evaluation in multi-environment trials
Mohammadreza Shiri · 2026
Read ProbStab: A probabilistic ML-assisted pipeline for genotype performance, stability, and risk evaluation in multi-environment trials by Mohammadreza Shiri (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0352098.txt.
Description
Shiri introduced a software package for judging crop varieties across many trial sites in a 2026 paper. A variety that shines in one field may flop in another, so breeders need yield, stability, and risk judged together. The package uses a forest-based method that gives prediction ranges rather than single guesses.
Separate modules handle performance, stability, risk, and confidence ranges, with repeat sampling for honesty. Breeders can favor varieties with high average yield and low chance of very poor results. Risk-aware selection matters more as weather grows less predictable, and a ready package spreads the method beyond statisticians.
Catalog record
| CREATOR | Mohammadreza Shiri |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53773 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |