Yield accuracy is not enough: diagnosing greenhouse world models across four evidence axes
Year: 2026
Type: preprint
Abstract: Yield accuracy can make greenhouse AI appear decision-ready even when management actions are ignored. In public Autonomous Greenhouse Challenge records, a cherry-tomato yield model reached an R² of 0.851 after future actions were removed, and 46 of 50 shuffled-action tests matched or improved the full-action baseline. We use this schedule-memory trap to motivate a four-axis evidence contract: endpoint prediction, state rollout, action response and generalization. Across three hourly greenhouse records spanning cucumber, cherry tomato and dwarf tomato, this contract provides a reproducible template for auditing greenhouse AI before it enters production decisions.
Authors: Bie, Yuhui, Xu, Guowei, Wang, Yaojun
Institution: China Agricultural University
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDGs: Zero hunger, Climate action
Open Access status: green
OpenAlex ID: W7171302683
Cites:
Cited by:
Related to: