Multi-Step Forecasting of Grape Berry Temperature based on LSTM Model with Feed-Forward Attention
Artificial Intelligence
Summary
The authors developed a new method called FAM-LSTM to predict grape berry temperatures in vineyards, which helps manage heat stress. They trained their model using weather data from different years and compared it to other models, finding that it predicted better at various time lengths. Using detailed local vineyard climate data made predictions more accurate, especially for longer times. They also found that the model’s errors were bigger during the hottest parts of the day and grew as they predicted further into the future.
Authors
Srikanth Gorthi, L. G. Divyanth, Dattatray Bhalekar, Markus Keller, Lav Khot
Abstract
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.