基于带前馈注意力机制的LSTM模型的葡萄浆果温度多步预测

中文摘要 AI 辅助

准确预测葡萄浆果温度（Tb）对于葡萄园及时开展热胁迫管理至关重要。本研究开发并评估了一种集成前馈注意力机制的长短期记忆网络（FAM-LSTM），用于多步高分辨率Tb预测。模型使用美国华盛顿州普罗瑟尔2023年和2024年的环境数据进行训练，并在2025年夏季数据上进行验证。在从15分钟到72小时（288个时间步）的预测时域范围内，将FAM-LSTM与LSTM、GRU、RNN和随机森林（RF）进行基准测试。评估了两种输入场景：最近的露天气象站观测数据和葡萄园内部微气候测量数据。在所有时域和输入场景下，FAM-LSTM始终优于所有基准模型。纳入葡萄园内部微气候数据显著提高了长时域的预测准确性。使用露天数据时，FAM-LSTM的平均绝对误差（MAE）和均方根误差（RMSE）范围分别为0.58至1.70摄氏度和0.65至2.07摄氏度；葡萄园内部观测数据进一步提升了性能，MAE和RMSE范围分别为0.51至1.55摄氏度和0.71至1.87摄氏度。误差分析显示，预测不确定性在白天峰值时段（11:00至18:00）最高，并随预测时域增加而逐步上升。总体而言，FAM-LSTM框架提供了可靠的Tb预测，以支持葡萄园的精准热胁迫管理。

英文摘要

Accurate forecasting of grape berry temperature (Tb) is essential for enabling timely heat stress management in vineyards. In this study, a feed-forward attention mechanism integrated with a Long Short-Term Memory network (FAM-LSTM) was developed and evaluated for multi-step, high-resolution Tb prediction. Models were trained using environmental data from 2023 and 2024 at Prosser, WA, USA, and validated on 2025 summer data. FAM-LSTM was benchmarked against LSTM, GRU, RNN, and Random Forest (RF) across horizons ranging from 15 minutes to 72 hours (288 time steps). Two input scenarios were evaluated: nearest open-field weather station observations and in-vineyard microclimate measurements. FAM-LSTM consistently outperformed all benchmark models across all horizons and input scenarios. Incorporating in-vineyard microclimate data significantly improved forecasting accuracy at longer horizons. Using open-field data, FAM-LSTM achieved MAE and RMSE ranges of 0.58 to 1.70 deg C and 0.65 to 2.07 deg C, respectively. In-vineyard observations further improved performance, with MAE and RMSE in the ranges of 0.51 to 1.55 deg C and 0.71 to 1.87 deg C. Error analysis showed prediction uncertainty was highest during peak daytime periods (11:00 to 18:00) and increased progressively with forecast horizon. Overall, the FAM-LSTM framework offers robust Tb forecasting to support precision heat stress management in vineyards.

发表机构

• Washington State University（华盛顿州立大学）
• Cornell University（康奈尔大学）

机构由 AI 辅助整理，请以论文原文为准。