A hybrid LSTM approach was developed for irrigation scheduling in maize crops, aiming to predict soil moisture content (MC) reduction in two fields in Turkey. The study used the Aquacrop 7.0 model to simulate MC data due to limitations in sensor data. The LSTM model was trained using soil, weather, and satellite-based vegetation data to predict MC reduction. The model achieved R² values ranging from 0.7602 to 0.9181 for Field 1 and 0.8163 to 0.8417 for Field 2, demonstrating its effectiveness in predicting MC reduction across different phases of the growing season. The model's performance was evaluated using R² and RMSE metrics, with results indicating high accuracy and reliability. The hybrid approach combined the LSTM model with Aquacrop simulations to overcome data limitations and improve irrigation scheduling. The study highlights the potential of this approach for efficient and precise agricultural irrigation practices.A hybrid LSTM approach was developed for irrigation scheduling in maize crops, aiming to predict soil moisture content (MC) reduction in two fields in Turkey. The study used the Aquacrop 7.0 model to simulate MC data due to limitations in sensor data. The LSTM model was trained using soil, weather, and satellite-based vegetation data to predict MC reduction. The model achieved R² values ranging from 0.7602 to 0.9181 for Field 1 and 0.8163 to 0.8417 for Field 2, demonstrating its effectiveness in predicting MC reduction across different phases of the growing season. The model's performance was evaluated using R² and RMSE metrics, with results indicating high accuracy and reliability. The hybrid approach combined the LSTM model with Aquacrop simulations to overcome data limitations and improve irrigation scheduling. The study highlights the potential of this approach for efficient and precise agricultural irrigation practices.