The present disclosure describes various embodiments of systems, apparatuses, and methods for large-scale processing of weather-related data. For one such system, the system comprises a database of weather-related data providing from at least one weather monitoring station and at least one processor for coordinating a data processing job for processing a set of input weather-related data from the database. Accordingly, the input data comprises sensor data from the at least one weather monitoring station positioned on an open shoreline during a hydrodynamic event, weather model data for the hydrodynamic event, and at least one of air-craft reconnaissance data or satellite reconnaissance data regarding the hydrodynamic event, wherein the at least one processor is configured to assimilate the input data and generate, using machine learning, an improved weather prediction model for the hydrodynamic event. Other systems, apparatuses, and methods are also provided.

A wind direction and a wind speed are readily and accurately estimated at a desired position without using a wind direction and velocity sensor. Movement instruction means of a wind estimation system instructs an unmanned aerial vehicle (UAV), which includes a sensor unit that detects information about a position change, to move. Fall control means causes the UAV to free fall after the UAV is moved according to the instruction of the movement instruction means. Estimation means estimates at least one of a wind direction and a wind speed at a fall position based on the information about the position change detected by the sensor unit during a fall of the UAV.

A wind direction and a wind speed are readily and accurately estimated at a desired position without using a wind direction and velocity sensor. Movement instruction means of a wind estimation system instructs an unmanned aerial vehicle (UAV), which includes a sensor unit that detects information about a position change, to move. Fall control means causes the UAV to free fall after the UAV is moved according to the instruction of the movement instruction means. Estimation means estimates at least one of a wind direction and a wind speed at a fall position based on the information about the position change detected by the sensor unit during a fall of the UAV.

The disclosure concerns biometeorological sensing devices including a processor communicatively coupled to a memory, and a plurality of sensors communicatively coupled to the processor. The plurality of sensors includes a humidity sensor, a UV sensor, an anemometer, an atmospheric thermometer, a globe thermometer, and a camera. The device also includes a network interface communicatively coupled to the processor. The processor is configured to estimate a mean radiant temperature (MRT) using data received from the plurality of sensors, identify a person in an image received from the camera, determine a bounding box that encloses the person in the image, generate a shadow map from the image, calculate an intersection over union (IOU) of the bounding box with the shadow map to determine if the person is in the shade, and transmit observed space usage and estimated MRT to a server communicatively coupled to the network interface.

The disclosure concerns biometeorological sensing devices including a processor communicatively coupled to a memory, and a plurality of sensors communicatively coupled to the processor. The plurality of sensors includes a humidity sensor, a UV sensor, an anemometer, an atmospheric thermometer, a globe thermometer, and a camera. The device also includes a network interface communicatively coupled to the processor. The processor is configured to estimate a mean radiant temperature (MRT) using data received from the plurality of sensors, identify a person in an image received from the camera, determine a bounding box that encloses the person in the image, generate a shadow map from the image, calculate an intersection over union (IOU) of the bounding box with the shadow map to determine if the person is in the shade, and transmit observed space usage and estimated MRT to a server communicatively coupled to the network interface.

A distributed weather system includes a storage, a plurality of wireless weather stations, a server, and an interface. Each of the plurality of wireless weather stations is associated with a user and has a battery, a location sensor generating location information, an anemometer generating apparent wind speed, a transmitter transmitting the location information with the apparent wind speed to a network at periodic intervals, and a receiver receiving control commands that include a length of the periodic intervals. The server receives the location information with the apparent wind speed and stores them in the storage. The interface is accessible by a mobile computer, and receives the control commands from a user and sends them to the receiver of the wireless weather station associated with the user. The interface displays a true wind speed for each of the plurality of wireless weather stations, which is calculated using the apparent wind speed, the location information, and historical location information.

A distributed weather system includes a storage, a plurality of wireless weather stations, a server, and an interface. Each of the plurality of wireless weather stations is associated with a user and has a battery, a location sensor generating location information, an anemometer generating apparent wind speed, a transmitter transmitting the location information with the apparent wind speed to a network at periodic intervals, and a receiver receiving control commands that include a length of the periodic intervals. The server receives the location information with the apparent wind speed and stores them in the storage. The interface is accessible by a mobile computer, and receives the control commands from a user and sends them to the receiver of the wireless weather station associated with the user. The interface displays a true wind speed for each of the plurality of wireless weather stations, which is calculated using the apparent wind speed, the location information, and historical location information.

A method and system for determining cloud seeding potential comprises receiving a temperature and a liquid water content (LWC). A seeding index is calculated based on the temperature T, a temperature membership function ƒ(T), the LWC, and a liquid water content membership function ƒ(LWC) at the plurality of grid points to create a seeding index set. A target region potential flag is set based on the seeding index set.

A method and system for determining cloud seeding potential comprises receiving a temperature and a liquid water content (LWC). A seeding index is calculated based on the temperature T, a temperature membership function ƒ(T), the LWC, and a liquid water content membership function ƒ(LWC) at the plurality of grid points to create a seeding index set. A target region potential flag is set based on the seeding index set.

An information processing system is equipped with at least one vehicle and a server that can communicate with the at least one vehicle. The vehicle acquires an image obtained by imaging a landscape outside the vehicle, a humidity outside the vehicle, and an imaging position of the image. The vehicle or the server generates floating substance information on an atmospheric floating substance around the vehicle, based on the image and the humidity. The server stores at least one pair of the floating substance information and the imaging position corresponding thereto, and provides information to a client through the use of the at least one pair of the stored floating substance information and the stored imaging position corresponding thereto.