Development of a Temperature Prediction Method Combining Deep Neural Networks and a Kalman Filter

抄録

Numerical weather forecast models have biases caused by insufficient grid resolution and incomplete physical processes, especially near the land surface. Therefore, the Japan Meteorological Agency (JMA) has been operationally post-processing the forecast model outputs to correct the biases. The operational post-processing method uses a Kalman filter (KF) algorithm for surface temperature prediction. Recent reports showed that deep convolutional neural networks (CNNs) were better than the JMA operational method in correcting the temperature forecast biases. This study combined the CNN-based bias correction scheme with the JMA operational KF algorithm. We expected that the combination of CNNs and a KF would improve the post-processing performance, as the CNNs modify large horizontal structures, and then, the KF corrects minor spatiotemporal deviations. As expected, we confirmed that the combination outperformed both CNNs and the KF alone. This study demonstrates the advantages of the new method in correcting coastal front, heat wave, and radiative cooling biases.