Temperature Data Correction of Fast Updating Assimilation System Based on Machine Learning Algorithms

In order to improve the accuracy of near-ground temperature forecasting under winter rain, snow, and freezing weather conditions, three machine learning algorithms, namely neural network, random forest, and support vector machine, were used to train various ground and air elements in the rapidly updated assimilation model of Zhejiang Province based on multi-source observation data, reducing the error of temperature in the model field and forming hourly and 3 km horizontal resolution ground and air temperature datasets for two rainy, snowy, and frozen weather processes. After calibration using the backpropagation neural network algorithm, random forest algorithm, and support vector machine algorithm, the MAE of the simulated field temperature forecast decreased from 1.29 °C to 0.937 °C, 1.01 °C, and 0.988 °C, respectively. The backpropagation neural networks and support vector machine algorithms perform well, but support vector machine algorithms have relatively short computation times. Using 10 feature points for training achieves optimal performance; more points may not necessarily lead to better calibration results. Adding actual data at the initial time of the target point significantly improved the correction effect, and the improvement effect was even better when the forecast lead time was less than 10. The correction effect of the prediction field shows that when the forecast lead time is between 15 h and 24 h, it becomes unstable over time. The mean prediction accuracy of whether the temperature exceeds the 0 °C temperature threshold at 24 forecast moments before calibration is 0.928. After correction, it has been increased to 0.956.