Monitoring and forecasting aerial animal migration benefit biological conservation, aviation safety, and agricultural production. Due to the lack of large-scale observation data and quantitative knowledge of aerial animal migration mechanisms, it is difficult to build a numerical simulation system for migration prediction. However, the extensive deployment of weather radars makes it possible to obtain large-scale aerial migration information. Meanwhile, artificial intelligence technologies provide new insights into the modeling of complex system. In this paper, we develop a deep-learning model to predict aerial migration from the perspective of spatio-temporal evolution. Specifically, an undirected graph is applied to describe the geographic structure of the weather radar network, and then graph convolution and gated recurrent unit are combined to extract spatio-temporal features of migration information. In addition, a multi-head self-attention mechanism is applied to enhance long-term dependence. Experiments are conducted to validate the effectiveness of the proposed model on the data from the Chinese weather radar network. The results show that our model can achieve state-of-the-art performance among the competing methods. Moreover, improvements from graph convolution and multi-head self-attention are also analyzed. In future applications, more weather radar data will be collected to enrich the dataset and build an aerial migration monitoring and prediction system.

Weather radar holds the capability to monitor the extensive migration of bird and insect species. In particular, polarimetric weather radar can enhance aerial ecological monitoring by quantifying target shape through the measurement of polarization moments. This paper introduces an intelligent algorithm to classify bird and insect migration using polarimetric weather radar data. A radar image dataset was formed by intentionally curating typical migratory data of birds and insects captured by the polarimetric weather radar. Next, point features and spatial texture features were extracted from the radar images in the dataset for training a classifier using a supervised learning approach, resulting in a classification accuracy of 93.56%. Furthermore, the importance of the features was analyzed, uncovering that the most influential attribute was the reflectivity factor at 33.83%, surpassing the cumulative influence of other dual-polarization moments. In addition, spatial textures also played an essential role for the classifier, collectively weighing 35.65%. Lastly, the proposed method was validated with bird radar data, attaining an accuracy level of 95.36%.

Weather radar data can capture large-scale bird migration information, helping solve a series of migratory ecological problems. However, extracting and identifying bird information from weather radar data remains one of the challenges of radar aeroecology. In recent years, deep learning was applied to the field of radar data processing and proved to be an effective strategy. This paper describes a deep learning method for extracting biological target echoes from weather radar images. This model uses a two-stream CNN (Atrous-Gated CNN) architecture to generate fine-scale predictions by combining the key modules such as squeeze-and-excitation (SE), and atrous spatial pyramid pooling (ASPP). The SE block can enhance the attention on the feature map, while ASPP block can expand the receptive field, helping the network understand the global shape information. The experiments show that in the typical historical data of China next generation weather radar (CINRAD), the precision of the network in identifying biological targets reaches up to 99.6%. Our network can cope with complex weather conditions, realizing long-term and automated monitoring of weather radar data to extract biological target information and provide feasible technical support for bird migration research.

Predicting aerial animal migration is of great significance for biological research, ecological conservation, and agricultural production. The mechanism of animal migration is deeply coupled with spatio-temporal and meteorological factors. However, existing large-scale prediction models using weather radar isolate the spatio-temporal characteristics and the meteorological factors. Additionally, their long-term prediction capabilities are limited, posing challenges in accurately forecasting long-term migration patterns to support applications such as ecological warnings. This paper introduces an aerial migration prediction neural network model combining multiple meteorological factors with weather radar data while expanding the horizon of the migration forecast to the scale of 7 days. Differentiated feature extraction methods are applied to different meteorological factors in the network. The transfer characteristics of the wind field in two-dimensional space are used to construct a dynamic migration model. The scalar meteorological data are encoded by entity embedding to perform feature fusion with the dynamic branch, collectively forming the forecast model that outputs future migration intensity. We validate the effectiveness of our model China weather radar network real data and reanalysis data, accurately forecasting migratory biomass within China for a horizon of up to 7 days. Moreover, our model is compared with two existing prediction models, demonstrating a maximum improvement of 14.00% in the coefficient of determination (R ² ) in long-term forecast. And the visualized results highlight the predictive effectiveness for the spring and autumn seasons. In future applications, more meteorological factors should be considered and radar data from more stations should be collected to enhance the dataset.

The migration of insects is an important way of material and energy transfer in nature. The accurate multitargets’ tracks are beneficial for studying insect flight mechanisms. Radar has been widely used in insect observation. Compared with a single radar system, a multiradar system can provide measurements from more dimensions and produce more accurate flight tracks. However, for insect observation, there are lots of targets and outliers in the measurement sets, which may challenge the measurement-to-measurement association between different radars. In addition, sensor bias estimation is needed to achieve good association and fusion results. We propose a joint association and registration method to simultaneously acquire bias estimates and association results for insect observation. The Gaussian-Seidel method is applied to solve the nonlinear least square bias estimate problem without any approximation. The Cramér-Rao bound is derived in the article. The simulation results show that our method can achieve the best association performance for different scenarios among the competing approaches, and bias estimation results are insensitive to the bias values, that can improve the accuracy of the fusion tracks.

Group targets such as birds and UAVs are the research hotspot in the radar field recently. Group target reconstruction that estimates the positions of individual targets becomes one of the core research requirements. But group targets are usually closely spaced with similar velocity and it is hard to distinguish multiple targets, resulting in angular glint. Meanwhile, they usually have weak echo and fly in a low altitude, which leads to lots of missed detection and false alarms. These characters increase the difficulty of group target reconstruction. Compared with a single radar, multiradar system with complementary multi-view observation can improve the accuracy and completeness of reconstruction. However, a large number of missed detection and false alarms make it difficult to correctly associate multisensor measurements. Moreover, large sensor bias further aggravate the difficulty. This paper proposed a topology feature aided joint association and registration algorithm to simultaneously acquire association and bias estimation results. The topology feature is applied in the association step to improve association correctness. A nonlinear least median of squares estimator is proposed in the registration step to improve the accuracy and robustness of bias estimation. Multi-frame information is used to further improve the association and registration performance. Simulation and experiment results show the better bias estimation and association performance of the proposed method compared with existing algorithms, and better reconstruction performance compared with a single radar.