# Agro-meteorological Time Series

The study reformulates vineyard mildew risk prediction as an event-onset warning task—after a minimum disease-free gap, will a new treatment-associated risk event begin within the following 3–7 days?—and, under a chronological 2020–2021/2022/2023 train-validation-test split, compares calendar-only, environmental-only, and combined representations with logistic regression, XGBoost, LSTM, and TCN, finding that calendar-only models were highly competitive (calendar-only LSTM and TCN detected 7 of 8 test events in every run, while a monthly climatological baseline detected 6), that environmental-only models were substantially weaker, that gains from adding environmental variables varied across model families, and that event-onset prediction and conventional daily-status classification show dif

The study reformulates vineyard mildew risk prediction as an event-onset warning task—after a minimum disease-free gap, will a new treatment-associated risk event begin within the following 3–7 days?—and, under a chronological 2020–2021/2022/2023 train-validation-test split, compares calendar-only, environmental-only, and combined representations with logistic regression, XGBoost, LSTM, and TCN, finding that calendar-only models were highly competitive (calendar-only LSTM and TCN detected 7 of 8 test events in every run, while a monthly climatological baseline detected 6), that environmental-only models were substantially weaker, that gains from adding environmental variables varied across model families, and that event-onset prediction and conventional daily-status classification show dif