Abstract: The present disclosure provides a meteorological big data fusion method based on deep learning, including the following steps: constructing multi-source meteorological data samples; according to an original resolution of different climate variables, selecting a corresponding super-resolution multiple to obtain an optimized super-resolution module under the constraint of maximizing information retention efficiency; constructing a spatial-temporal attention module using a focused attention mechanism, and selecting a corresponding time stride according to periodic characteristics of different climate variables; constructing a meteorological data fusion model in combination with the optimized super-resolution model and the spatial-temporal attention module; taking a minimum resolution of climate variables as a loss function, and training the meteorological data fusion model with the multi-source meteorological data samples; and importing the acquired real-time meteorological data from multiple data sources into t

Abstract: The present disclosure provides a meteorological big data fusion method based on deep learning, including the following steps: constructing multi-source meteorological data samples; according to an original resolution of different climate variables, selecting a corresponding super-resolution multiple to obtain an optimized super-resolution module under the constraint of maximizing information retention efficiency; constructing a spatial-temporal attention module using a focused attention mechanism, and selecting a corresponding time stride according to periodic characteristics of different climate variables; constructing a meteorological data fusion model in combination with the optimized super-resolution model and the spatial-temporal attention module; taking a minimum resolution of climate variables as a loss function, and training the meteorological data fusion model with the multi-source meteorological data samples; and importing the acquired real-time meteorological data from multiple data sources into t

Abstract: A method for flood disaster monitoring and disaster analysis based on vision transformer is provided. It includes: step (1), constructing a bi-temporal image change detection model based on vision transformer; step (2), selecting bi-temporal remote sensing images to make flood disaster labels; and step (3), performing flood monitoring and disaster analysis according to the bi-temporal image change detection model constructed in the step (1). In combination with the bi-temporal image change detection model based on an advanced vision transformer in deep learning and radar data which is not affected by time and weather and has strong penetration ability, data when floods occur can be obtained and recognition accuracy is improved.

Abstract: A deep-sea submarine gas hydrate collecting method and a production house for the first time, the collecting method comprises the steps of: determining an active methane leakage zone near a landward limit of a submarine gas hydrate stability zone, acquiring submarine methane leakage in-situ observation data, determining a methane leakage rate and evaluating its economy; mounting a production house on the seabed, opening a monitoring system after the mounting, monitoring the submarine methane leakage condition and hydrate generation progress in real time, evaluating a hydrate generation amount, and performing hydrate acquisition work; and rapidly processing the gas hydrate in the house by a gas hydrate collecting system of an offshore platform, and continuously monitoring the methane leakage condition. A large amount of methane leaked can be collected, thereof, the method has dual meanings of resources and environment.

Abstract: A deep-sea submarine gas hydrate collecting method and a production house for the first time, the collecting method comprises the steps of: determining an active methane leakage zone near a landward limit of a submarine gas hydrate stability zone, acquiring submarine methane leakage in-situ observation data, determining a methane leakage rate and evaluating its economy; mounting a production house on the seabed, opening a monitoring system after the mounting, monitoring the submarine methane leakage condition and hydrate generation progress in real time, evaluating a hydrate generation amount, and performing hydrate acquisition work; and rapidly processing the gas hydrate in the house by a gas hydrate collecting system of an offshore platform, and continuously monitoring the methane leakage condition. A large amount of methane leaked can be collected, thereof, the method has dual meanings of resources and environment.

Abstract: In some embodiments, a method receives a plurality of inputs for a video for a plurality of times at a prediction network that includes a plurality of cells. The prediction network generates a plurality of predictions of watch behavior of the video for the plurality of inputs at the plurality of cells. The plurality of predictions predicts a performance of the video on a video delivery service for the plurality of times. Actual performance data generated from users viewing the video on the video delivery service is received before a time. A time series residual for at least a portion of the plurality of predictions is generated from the actual performance data and prior predictions. The portion of the predictions after the time using values in the time series residual is adjusted. The adjusted predictions of watch behavior are output for the video.

Abstract: A system for wireless power transmission may include one or more charging panels and one or more powered devices. The charging panel may include a pilot analysis circuitry, processor and power transmitter. The pilot analysis circuitry may be configured to analyze the magnitude and phase of a pilot signal from the powered device, based on which the processor may be configured to determine a complex conjugate of the pilot signal. And the power transmitter may be configured to cause radiation of a focused wireless power beam to the powered device in accordance with the complex conjugate of the pilot signal and via one or more antenna elements. The charging panel may be one of a plurality of spatially-distributed charging panels each of which includes respective antenna elements that may form an array of antenna elements configured to collaboratively radiate wireless power as a distributed, retro-reflective beamformer.

Abstract: A system for wireless power transmission may include one or more charging panels and one or more powered devices. The charging panel may include a pilot analysis circuitry, processor and power transmitter. The pilot analysis circuitry may be configured to analyze the magnitude and phase of a pilot signal from the powered device, based on which the processor may be configured to determine a complex conjugate of the pilot signal. And the power transmitter may be configured to cause radiation of a focused wireless power beam to the powered device in accordance with the complex conjugate of the pilot signal and via one or more antenna elements. The charging panel may be one of a plurality of spatially-distributed charging panels each of which includes respective antenna elements that may form an array of antenna elements configured to collaboratively radiate wireless power as a distributed, retro-reflective beamformer.