In one embodiment, a method includes determining, by a controller, a first wind direction relative to a first vehicle and determining, by the controller, a first wind speed relative to the first vehicle. The method also includes calculating, by the controller, an absolute wind direction relative to ground using the first wind direction relative to the first vehicle and calculating, by the controller, an absolute wind speed relative to the ground using the first wind speed relative to the first vehicle. The method further includes calculating, by the controller, a second wind direction relative to a second vehicle using the absolute wind direction and calculating, by the controller, a second wind speed relative to the second vehicle using the absolute wind speed. A front end of the first vehicle and a front end of the second vehicle face different directions.

In one embodiment, a method includes determining, by a controller, a first wind direction relative to a first vehicle and determining, by the controller, a first wind speed relative to the first vehicle. The method also includes calculating, by the controller, an absolute wind direction relative to ground using the first wind direction relative to the first vehicle and calculating, by the controller, an absolute wind speed relative to the ground using the first wind speed relative to the first vehicle. The method further includes calculating, by the controller, a second wind direction relative to a second vehicle using the absolute wind direction and calculating, by the controller, a second wind speed relative to the second vehicle using the absolute wind speed. A front end of the first vehicle and a front end of the second vehicle face different directions.

A device for preventing, in real time, risk of atmospheric disturbance (DIS) for an aircraft in the air or on the ground includes acquisition means configured to acquire data corresponding to said risk. The device further includes design means configured to produce a predictive map of at least one critical area corresponding to at least one level of risk of disturbance that has been determined, and protection means (MP) configured to protect electronic components on board the aircraft which are liable to be damaged if the aircraft passes through said at least one critical area.

A device for preventing, in real time, risk of atmospheric disturbance (DIS) for an aircraft in the air or on the ground includes acquisition means configured to acquire data corresponding to said risk. The device further includes design means configured to produce a predictive map of at least one critical area corresponding to at least one level of risk of disturbance that has been determined, and protection means (MP) configured to protect electronic components on board the aircraft which are liable to be damaged if the aircraft passes through said at least one critical area.

A rendering method for a drone game includes the following steps. Firstly, a drone, a control device, a display device and an information node are provided. The drone includes a plurality of cameras. Then, a plurality of images acquired from the plurality of cameras of the drone are stitched as a panoramic image by the control device, and the panoramic image is displayed on the display device. Then, a ready signal is issued from the information node to the display device, and the control device accesses the drone game through an authorization of the information node in response to the ready signal. Then, at least one virtual object is generated in the panoramic image. Consequently, the sound, light and entertainment effects of the drone game are effectively enhanced, and the fun and diversity of the drone game are increased.

A rendering method for a drone game includes the following steps. Firstly, a drone, a control device, a display device and an information node are provided. The drone includes a plurality of cameras. Then, a plurality of images acquired from the plurality of cameras of the drone are stitched as a panoramic image by the control device, and the panoramic image is displayed on the display device. Then, a ready signal is issued from the information node to the display device, and the control device accesses the drone game through an authorization of the information node in response to the ready signal. Then, at least one virtual object is generated in the panoramic image. Consequently, the sound, light and entertainment effects of the drone game are effectively enhanced, and the fun and diversity of the drone game are increased.

A crop yield estimation method based on spatio-temporal deep learning including: obtaining regional historical crop yield data and meteorological data, preprocessing the meteorological data and the yield data to respectively obtain meteorological parameters and a detrended yield as input and output of the crop yield spatio-temporal deep learning model; constructing the spatio-temporal deep learning model for crop yield estimation, and optimizing hyperparameters; and building a training set by taking the meteorological parameters as an input and the detrended yield as output to train the model and obtain parameters of the model; for the crop yield to be estimated, feeding meteorological parameters into the trained model, and obtaining the crop yield estimation result. The model combined temporal and spatial learning to achieve better crop yield estimation accuracy and stability at large spatial scales.

A crop yield estimation method based on spatio-temporal deep learning including: obtaining regional historical crop yield data and meteorological data, preprocessing the meteorological data and the yield data to respectively obtain meteorological parameters and a detrended yield as input and output of the crop yield spatio-temporal deep learning model; constructing the spatio-temporal deep learning model for crop yield estimation, and optimizing hyperparameters; and building a training set by taking the meteorological parameters as an input and the detrended yield as output to train the model and obtain parameters of the model; for the crop yield to be estimated, feeding meteorological parameters into the trained model, and obtaining the crop yield estimation result. The model combined temporal and spatial learning to achieve better crop yield estimation accuracy and stability at large spatial scales.

A computer-implemented method for power grid anomaly detection using a convolutional neural network (CNN) trained to detect anomalies in electricity demand data and electricity supply data includes receiving (i) electricity demand data comprising time series measurements of consumption of electricity by a plurality of consumers, and (ii) electricity supply data comprising time series measurements of availability of electricity by one or more producers. An input matrix is generated that comprises the electricity demand data and the electricity supply data. The CNN is applied to the input matrix to yield a probability of anomaly in the electricity demand data and the electricity supply data. If the probability of anomaly is above a threshold value, an alert message is generated for one or more system operators.

A computer-implemented method for power grid anomaly detection using a convolutional neural network (CNN) trained to detect anomalies in electricity demand data and electricity supply data includes receiving (i) electricity demand data comprising time series measurements of consumption of electricity by a plurality of consumers, and (ii) electricity supply data comprising time series measurements of availability of electricity by one or more producers. An input matrix is generated that comprises the electricity demand data and the electricity supply data. The CNN is applied to the input matrix to yield a probability of anomaly in the electricity demand data and the electricity supply data. If the probability of anomaly is above a threshold value, an alert message is generated for one or more system operators.