arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.15411cs.AIcs.LG
收藏

一种通过动态参数校准和多任务学习的作物预测混合建模框架

A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning

Oregon State University(俄勒冈州立大学);Washington State University(华盛顿州立大学)

William Solow, Paola Pesantez-Cabrera, Markus Keller, Lav Khot, Sandhya Saisubramanian, Alan Fern

AI总结:

本文提出了一种混合建模方法,通过动态参数校准和多任务学习,提高作物预测的准确性,特别是在数据有限的情况下,利用神经网络对生物物理模型进行参数化,并在不同作物品种间高效共享数据,从而提升预测精度和生物合理性。

摘要:

准确预测作物状态(例如物候阶段和耐寒性)对于及时进行灌溉、施肥和树冠管理等农场管理决策至关重要,以优化作物产量和质量。虽然传统生物物理模型可以用于季节性预测,但它们缺乏用于特定地点管理所需的精度。深度学习方法是一种有吸引力的替代方案,但可能会产生生物上不合理的预测,并需要大规模数据。我们提出了一种混合建模方法,使用神经网络对可微分的生物物理模型进行参数化,并利用多任务学习在数据有限的情况下在不同作物品种之间高效共享数据。通过预测生物物理模型的参数,我们的方法在提高预测精度的同时保持生物合理性。使用真实世界和合成数据集的实证评估表明,与部署的生物物理模型相比,我们的方法在物候预测方面提高了60%,在耐寒性预测方面提高了40%。

英文摘要:

Accurate prediction of crop states (e.g., phenology stages and cold hardiness) is essential for timely farm management decisions such as irrigation, fertilization, and canopy management to optimize crop yield and quality. While traditional biophysical models can be used for season-long predictions, they lack the precision required for site-specific management. Deep learning methods are a compelling alternative, but can produce biologically unrealistic predictions and require large-scale data. We propose a \emph{hybrid modeling} approach that uses a neural network to parameterize a differentiable biophysical model and leverages multi-task learning for efficient data sharing across crop cultivars in data limited settings. By predicting the \emph{parameters} of the biophysical model, our approach improves the prediction accuracy while preserving biological realism. Empirical evaluation using real-world and synthetic datasets demonstrates that our method improves prediction accuracy by 60\% for phenology and 40\% for cold hardiness compared to deployed biophysical models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑