Precipitation nowcasting is extremely important in disaster prevention and mitigation, and can improve the quality of meteorological forecasts. In recent years, deep learning-based spatiotemporal sequence prediction models have been widely used in precipitation nowcasting, obtaining better prediction results than numerical weather prediction models and traditional radar echo extrapolation results. Because existing deep learning models rarely consider the inherent interactions between the model input data and the previous output, model prediction results do not sufficiently meet the actual forecast requirement. We propose a Modified Convolutional Gated Recurrent Unit (M-ConvGRU) model that performs convolution operations on the input data and previous output of a GRU network. Moreover, this adopts an encoder–forecaster structure to better capture the characteristics of spatiotemporal correlation in radar echo maps. The results of multiple experiments demonstrate the effectiveness of the proposed model. The balanced mean absolute error (B-MAE) and balanced mean squared error (B-MSE) of M-ConvGRU are slightly lower than Convolutional Long Short-Term Memory (ConvLSTM), but the mean absolute error (MAE) and mean squared error (MSE) of M-ConvGRU are 6.29% and 10.25% lower than ConvLSTM, and the prediction accuracy and prediction performance for strong echo regions were also improved.
Early warning and forecasting of tornadoes began to combine artificial intelligence (AI) and machine learning (ML) algorithms to improve identification efficiency in the past few years. Applying machine learning algorithms to detect tornadoes usually encounters class imbalance problems because tornadoes are rare events in weather processes. The ADASYN-LOF algorithm (ALA) was proposed to solve the imbalance problem of tornado sample sets based on radar data. The adaptive synthetic (ADASYN) sampling algorithm is used to solve the imbalance problem by increasing the number of minority class samples, combined with the local outlier factor (LOF) algorithm to denoise the synthetic samples. The performance of the ALA algorithm is tested by using the supporting vector machine (SVM), artificial neural network (ANN), and random forest (RF) models. The results show that the ALA algorithm can improve the performance and noise immunity of the models, significantly increase the tornado recognition rate, and have the potential to increase the early tornado warning time. ALA is more effective in preprocessing imbalanced data of SVM and ANN, compared with ADASYN, Synthetic Minority Oversampling Technique (SMOTE), SMOTE-LOF algorithms.
Precipitation nowcasting plays an important role in mitigating the damage caused by severe weather. The objective of precipitation nowcasting is to forecast the weather conditions 0–2 h ahead. Traditional models based on numerical weather prediction and radar echo extrapolation obtain relatively better results. In recent years, models based on deep learning have also been applied to precipitation nowcasting and have shown improvement. However, the forecast accuracy is decreased with longer forecast times and higher intensities. To mitigate the shortcomings of existing models for precipitation nowcasting, we propose a novel model that fuses spatiotemporal features for precipitation nowcasting. The proposed model uses an encoder–forecaster framework that is similar to U-Net. First, in the encoder, we propose a spatial and temporal multi-head squared attention module based on MaxPool and AveragePool to capture every independent sequence feature, as well as a global spatial and temporal feedforward network, to learn the global and long-distance relationships between whole spatiotemporal sequences. Second, we propose a cross-feature fusion strategy to enhance the interactions between features. This strategy is applied to the components of the forecaster. Based on the cross-feature fusion strategy, we constructed a novel multi-head squared cross-feature fusion attention module and cross-feature fusion feedforward network in the forecaster. Comprehensive experimental results demonstrated that the proposed model more effectively forecasted high-intensity levels than other models. These results prove the effectiveness of the proposed model in terms of predicting convective weather. This indicates that our proposed model provides a feasible solution for precipitation nowcasting. Extensive experiments also proved the effectiveness of the components of the proposed model.
Besides collecting and broadcasting aviation surveillance parameters, Automatic Dependent Surveillance-Broadcast (ADS-B) is also a novel technique to sense and share meteorological information such as wind field with high update rate and accuracy. Many ADS-B devices on aircraft can construct a real-time and dynamic sensor network. Although the ADS-B message format reserves the items especially for wind information, few aircrafts broadcast these items at present. The current solution is to use the aircraft trajectory captured by ADS-B for wind vector inversion. Nevertheless, some algorithms still have some downsides, especially the stability in small-angle turning situations. This paper is committed to developing a novel algorithm capable of working in both small and large angle turning situations with high efficiency, with an emphasis on small angle situations. By virtue of the algorithm in our recent research which is derived from the Particle Filter model, this algorithm takes advantage of circle geometry property and Euclidean distance standard deviation (STD). In the simulation test, the effect of true airspeed (TAS) difference on the mean absolute error of wind estimate, the effect of true wind speed on wind estimate, the effect of maneuver turning angle on wind estimate, and the computational complexity are assessed, respectively. Moreover, for real ADS-B data, both large and small-angle turning maneuver situations are tested and compared separately. Also compared is the level of the results concentration for the wind speed and TAS along with the geometric height. Consequently, the simulation and the real data test shows that the proposed STD algorithm has performance superior to other two algorithms LS and LM especially in the small-angle turning situation such as below 40deg. STD’s performance is between other two algorithms in computational complexity. This property can help improve the algorithm’s stability and data utilization for small-angle turning significantly, which is very useful in real aviation surveillance operations.
Traditional deep learning-based prediction methods predominantly rely on weather radar data to quantify precipitation, often neglecting the integration of the thermal processes involved in the formation and dissipation of precipitation, which leads to reduced prediction accuracy. To address this limitation, we introduce the Dual-Attention Recurrent Neural Network (DA-RNN), a model that combines satellite infrared (IR) data with radar-derived vertically integrated liquid (VIL) content. This model leverages the fundamental physical relationship between temperature and precipitation in a predictive framework that captures thermal and water vapor dynamics, thereby enhancing prediction accuracy. The results of experimental evaluations on the SEVIR dataset demonstrate that the DA-RNN model surpasses traditional methods on the test set. Notably, the DA-TrajGRU model achieves reductions in mean squared error (MSE) and mean absolute error (MAE) of 30 () and 89 (), respectively, compared with those of the conventional TrajGRU model. Furthermore, our DA-RNN exhibits robust false alarm rates (FAR) for various thresholds, with only slight decreases in the critical success index (CSI) and Heidke skill score (HSS) when increasing the threshold. Additionally, we present a visualization of precipitation nowcasting, illustrating that the integration of multiple data sources effectively avoids overestimation of VIL values, further increasing the precision of precipitation forecasts.