Beddows, Matthew, Durrant, Aiden
ORCID: https://orcid.org/0000-0002-8375-4523 and Leontidis, Georgios
(2026)
Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts.
Frontiers in Artificial Intelligence, 9.
ISSN 2624-8212
Preview |
PDF (frai-9-1911884)
- Published Version
Available under License Creative Commons Attribution. Download (897kB) | Preview |
Abstract
Accurate crop yield forecasting in commercial soft fruit production is constrained by the data available in typical commercial farm records, which lack the sensor networks, satellite imagery, and high-resolution meteorological inputs that most state-of-the-art approaches assume. Even when provided with recent historical observations, existing forecasting models exhibit systematic, season-specific errors that growers can readily identify but that the models have no mechanism to self-correct. This work proposes a structured LLM agent framework that performs post-hoc correction of existing model predictions without requiring additional data or retraining, encoding agricultural domain knowledge across a five-tool pipeline covering seasonal phase detection, bias learning, range validation, cross-plot similarity search, and correction synthesis. The framework operates as a model-agnostic layer on top of any base forecaster, with each correction traceable to an explicit reasoning step. Evaluated on a proprietary strawberry yield dataset and a public USDA corn harvest dataset, agent refinement of XGBoost reduced MAE by 22% and MASE by 54% on strawberry, with consistent improvements across Moirai2 (MAE −25%, MASE −22%) and Random Forest (MAE −31%, MASE −61%) baselines. Using Llama 3.1 8B as the agent produced the strongest LLM-based corrections across all configurations, the Deterministic baseline was competitive with or outperformed Llama 3.1 8B on XGBoost and Random Forest, suggesting that domain-tool correction alone recovers much of the available gain. LLaVA 13B showed inconsistent gains, highlighting sensitivity to the choice of refinement model.
| Item Type: | Article |
|---|---|
| Additional Information: | Data Availability: The strawberry yield dataset was provided under a commercial agreement and cannot be made publicly available. The corn dataset is publicly available from the USDA NASS QuickStats database at https://quickstats.nass.usda.gov/ and can be reproduced using the queries described in Section 3. |
| Uncontrolled Keywords: | llm agents,moirai2,xgboost,agricultural yield prediction,time series forecasting,artificial intelligence ,/dk/atira/pure/subjectarea/asjc/1700/1702 |
| Faculty \ School: | Faculty of Science > School of Computing Sciences |
| UEA Research Groups: | Faculty of Science > Research Groups > Data Science and AI |
| Related URLs: | |
| Depositing User: | LivePure Connector |
| Date Deposited: | 16 Sep 2026 11:51 |
| Last Modified: | 02 Nov 2026 09:29 |
| URI: | https://ueaeprints.uea.ac.uk/id/eprint/104563 |
| DOI: | 10.3389/frai.2026.1911884 |
Downloads
Downloads per month over past year
Actions (login required)
![]() |
View Item |
Tools
Tools