A dynamic graph includes a plurality of nodes and edges at a plurality of time steps; each node corresponds to a geographic location in a first area where pest infestation information is available for a subset of locations. Each edge connects two of the nodes which are geographically proximate, has a direction based on wind direction, and has a weight based on relative wind speed. Assign node features based on weather data as well as labels corresponding to pest infestation severity. Train a graph convolutional network on the dynamic graph. Based on predicted future weather conditions for a second area different than the first area, use the trained graph convolutional network to predict, via inductive learning, pest infestation severity for future times for a new set of nodes corresponding to new geographic locations in the second area for which no pest infestation information is available.

A bad weather judgment apparatus and a bad weather judgment method thereof are disclosed. The apparatus includes a target recognizer configured to recognize targets in detection areas of a plurality of heterogeneous sensors based on sensor recognition information received from the heterogeneous sensors, a counter configured to count the number of cases based on detection states of the heterogeneous sensors about a same target among the targets, and a bad weather judger configured to determine whether the same target is present in bad weather judgment zones of the detection areas of the heterogeneous sensors, control the counter to increment or decrement the number of the cases based on detection states of the heterogeneous sensors about whether the same target is present in the bad weather judgment zones, and judge current weather to be bad weather when the number of the cases is greater than a threshold value.

A bad weather judgment apparatus and a bad weather judgment method thereof are disclosed. The apparatus includes a target recognizer configured to recognize targets in detection areas of a plurality of heterogeneous sensors based on sensor recognition information received from the heterogeneous sensors, a counter configured to count the number of cases based on detection states of the heterogeneous sensors about a same target among the targets, and a bad weather judger configured to determine whether the same target is present in bad weather judgment zones of the detection areas of the heterogeneous sensors, control the counter to increment or decrement the number of the cases based on detection states of the heterogeneous sensors about whether the same target is present in the bad weather judgment zones, and judge current weather to be bad weather when the number of the cases is greater than a threshold value.

A method of calculating a return period wind speed for a proposed wind turbine site is provided. Wind speed measurements and modeled wind speeds associated with the proposed site are provided. The measured and modeled wind speeds are transformed into the frequency domain, and combined to generate a hybrid spectrum. The hybrid spectrum is transformed into the time domain to generate a set of hybrid wind speed measurements, which are used to calculate the return period wind speed.

A method of calculating a return period wind speed for a proposed wind turbine site is provided. Wind speed measurements and modeled wind speeds associated with the proposed site are provided. The measured and modeled wind speeds are transformed into the frequency domain, and combined to generate a hybrid spectrum. The hybrid spectrum is transformed into the time domain to generate a set of hybrid wind speed measurements, which are used to calculate the return period wind speed.

Systems and methods are disclosed for estimating slipperiness of a road surface. This estimate may be obtained using an image sensor mounted on a vehicle. The estimated road slipperiness may be utilized when calculating a risk index for the road, or for an area including the road. If a predetermined threshold for slipperiness is exceeded, corrective actions may be taken. For instance, warnings may be generated to human drivers that are in control of driving vehicle, and autonomous vehicles may automatically adjust vehicle speed based upon road slipperiness detected.

Systems and methods are disclosed for estimating slipperiness of a road surface. This estimate may be obtained using an image sensor mounted on a vehicle. The estimated road slipperiness may be utilized when calculating a risk index for the road, or for an area including the road. If a predetermined threshold for slipperiness is exceeded, corrective actions may be taken. For instance, warnings may be generated to human drivers that are in control of driving vehicle, and autonomous vehicles may automatically adjust vehicle speed based upon road slipperiness detected.

In some implementations, a system performs proactive performance tests for an appliance before a time for an operational change in usage of the appliance. Usage data for an appliance associated with a property may be obtained. The obtained usage data indicates past activity of the appliance and present operational status of the appliance. Weather forecast data associated with a location of the property can be obtained. A time for an operational change in usage of the appliance can be predicted based at least on the obtained usage data for the appliance and the obtained weather forecast data. An operation directed to conducting one or more performance tests on the appliance can be performed before the predicted time for the operational change in usage of the appliance. One or more communications related to the one or more performance tests of the appliance can be provided to a client device.

In some implementations, a system performs proactive performance tests for an appliance before a time for an operational change in usage of the appliance. Usage data for an appliance associated with a property may be obtained. The obtained usage data indicates past activity of the appliance and present operational status of the appliance. Weather forecast data associated with a location of the property can be obtained. A time for an operational change in usage of the appliance can be predicted based at least on the obtained usage data for the appliance and the obtained weather forecast data. An operation directed to conducting one or more performance tests on the appliance can be performed before the predicted time for the operational change in usage of the appliance. One or more communications related to the one or more performance tests of the appliance can be provided to a client device.

A method, apparatus, and computer program product provide for crowdsourcing data from a plurality of aircraft systems to determine cloud ceiling information. In the context of a method, the method receives a set of sensor data from a first aircraft system captured during a first event. The method determines, based on the set of sensor data, a cloud ceiling value for a location and a time at which the first set of sensor data was captured. The method also stores the cloud ceiling value in association with a landing region and causes transmission of the cloud ceiling value to one or more additional aircraft systems.