Accurate and timely prediction of crop growth is of great significance to
ensure crop yields and researchers have developed several crop models for the
prediction of crop growth. However, there are large difference between the
simulation results obtained by the crop models and the actual results, thus in
this paper, we proposed to combine the simulation results with the collected
crop data for data assimilation so that the accuracy of prediction will be
improved. In this paper, an EnKF-LSTM data assimilation method for various
crops is proposed by combining ensemble Kalman filter and LSTM neural network,
which effectively avoids the overfitting problem of existing data assimilation
methods and eliminates the uncertainty of the measured data. The verification
of the proposed EnKF-LSTM method and the comparison of the proposed method with
other data assimilation methods were performed using datasets collected by
sensor equipment deployed on a farm.

通过将集合卡尔曼滤波器和 LSTM 神经网络相结合，本文提出了一种适用于各种作物的 EnKF-LSTM 数据同化方法，该方法有效避免了现有数据同化方法的过拟合问题，并消除了测量数据的不确定性，从而提高了预测的准确性。通过农田上部署的传感器设备收集的数据集进行了所提出的 EnKF-LSTM 方法的验证，并与其他数据同化方法进行了比较。