International Business Machines Corporation

Lingyun Wang

Ke Xu Zou

Junmei Qu

Chao Zhang

Xin Xin Bai

Ming Xie

Gang Zhou

Junsong Wang

Jin Yan Shao

Xin Jie Lv

Xi Xia

Qing Fa Wang

Shi Lei Zhang

Wei Xu

Xiao Guang Rui

Yu Tao Ba

Wenchen Cheng

Liang Liu

Tao Wang

Wei Zhao

Wen Jun Yin

Wei Zhuang

Yutao Ba

A method, a device and a computer program product for abnormal air pollution emission prediction are proposed. In the method, a first set of features characterizing air condition in a zone is obtained. Whether the zone is subject to abnormal air pollution emission in a future first time period is determined based on the first set of features and using a first prediction classifier. In response to determining that the zone is subject to abnormal air pollution emission in the first time period, a second set of features characterizing air condition in the zone is obtained. A future second time period in which the zone is subject to abnormal air pollution emission is determined based on the second set of features and using a second prediction classifier. The second time period is included in the first time period. In this way, the abnormal air pollution emission in the zone can be accurately and efficiently predicted.

Abnormal air pollution emission prediction

Techniques for monitoring particulate matter (PM) mass concentration using relatively low cost devices are described. A computer-implemented method comprises determining, by a device operatively coupled to a processor, relationships between: first PM mass data determined by a monitor station device for a first atmospheric area over a period of time; first PM count data determined by a reference PM count device for the first atmospheric area over the period of time; and first conditional information comprising first values for defined conditional parameters, wherein the first values are associated with the first atmospheric area over the period of time. The method further includes generating an initial conversion model based on the relationships, wherein the conversion model converts a PM count to a PM mass based on one or more conditional parameters of the defined conditional parameters and features for updating the conversion model.

Particulate matter monitoring

Embodiments of the invention are directed to a computer-implemented method that includes using a reinforcement learning (RL) system to generate a first set of displayed region candidates based on inputs received from online users while watching video. A recommendation system is used to rank the first set of displayed region candidates based on inputs received from a local user watching video. The recommendation system is further used to select a first highest ranked one of the first set of displayed region candidates. Based on the first highest ranked one of the first set of displayed region candidates, a first section of a first raw video frame is fetched that matches the first highest ranked one of the first set of displayed candidate regions, wherein the first section of the first raw video frame includes a first predicted display region of the video frame.

Using reinforcement learning and personalized recommendations to generate a video stream having a predicted, personalized, and enhance-quality field-of-view

A method can include obtaining, from a video having a first resolution, a set of frames having a second resolution. The first resolution can be higher than the second resolution. The set of frames can include a first frame and a second frame. The method can include generating a difference feature map. The method can include obtaining a third frame having the first resolution. The method can include detecting, based on the difference feature map, a first location of a first object in the third frame. The method can include cropping, from the third frame, a first cropped area. The first cropped area can be smaller than a third frame area. The method can include generating, based on a feature map and the difference feature map, a spatial attention layer. The method can include detecting, by the spatial attention layer, the first object in the first cropped area.

Difference-guided video analysis

At least one target area is identified based on a pollution concentration field of a geographic area. At least one candidate site is selected from a plurality of sites within the geographic area based on a relationship between the plurality of sites and pollution sources, where the plurality of sites are potential positions for deploying sensors for monitoring pollution. A target site is determined from the at least one candidate site based on the at least one target area.

Sensor deployment

An abnormal area is detected using an initial spatial weights matrix between pairs of air quality sensors in a plurality of air quality sensors distributed across a geographical area and air quality data for each air quality sensor. The spatial weights matrix utilizes a distance between pairs of air quality sensors and wind direction through the geographical area. The initial spatial weights matrix and air quality data are used to calculate a plurality of local moran's indexes, one for each air quality sensor. The plurality of local moran's indexes are used to divide the plurality of air quality sensors into four groups. The groups are classified as proper or improper, and the proper groups are identified as abnormal areas.

Detection of area of abnormal air quality within a geographical area

Correction management techniques are provided. In one embodiment, the techniques involve determining, via a first machine learning model, a first and second data based on a respective first and second raw data obtained from a plurality of sensors, determining, based on a deviation between the first data and the second data, an inaccuracy of the first data, identifying an ambient situation corresponding to the first raw data and the second raw data, selecting, from historical raw data of the plurality of sensors, a group of raw data corresponding to the ambient situation, and correcting, via a second machine learning model, the first data based on the selected group of raw data.

Error correction

A computer implemented method, computer system, and computer program product are provided for air-pollution emission source monitoring. To determine the air-pollution emission of a monitored area, location data and air pollution data are taken from sensor stations positioned along a boundary of the monitored area. The macroscale atmospheric data of a region, where the monitored area is located, is also received. A boundary pollutant distribution can be estimated based on the location data and the air pollution data. Horizontal diffusion and vertical diffusion of the monitored area can be estimated based on the boundary pollutant distribution and the macroscale atmospheric data. To determine an accurate amount of pollution contribution caused by a monitored area, a calculation based on the boundary pollutant distribution, the horizontal diffusion, and the vertical diffusion can be used.

Air-pollution emission source monitoring

A method, system, and computer program product, include recording high-frequency wave data of local arid adjacent fault curves of a power grid to compare the high-frequency wave data with historical fault data to detect an actual fault region in the power grid, the power grid having a plurality of sensors distributed in the power grid, each sensor being upstream of one adjacent sensor and downstream of an other adjacent sensor.

System, method and computer program product for fault detection and location in power grid

A processor-implemented method receives a plurality of pollution measurement data, a plurality of geodetic data, and a plurality of meteorological data associated with a geographical area. The processor-implemented method generates a grid of the geographical area, whereby the generated grid virtually divides the geographical area into a plurality of cells. The processor-implemented method associates the received plurality of measurement data, the received plurality of geodetic data, and the received plurality of meteorological data with a cell in the generated grid. The processor-implemented method determines a pollutant contribution value of the cell based on the pollution measurement data associated with the cell and a physical contribution of a plurality of pollutants. The processor-implemented method identifies the pollution source based on a paired comparison of the plurality of cells and displays the location on the geographical area associated with the identified pollution source.

Air pollution source recognition based on dynamic pairing and comparison

A method, system, and computer program product, include obtaining a dataset related to a power grid collected by a plurality of sensors distributed in the power grid, identifying a region as a candidate fault region based on first data in the dataset, the first data being collected by a first sensor from among the plurality of sensors that is located in the region, and verifying the candidate fault region based on second data in the dataset, the second data being collected by a second sensor from among the plurality of sensors that is adjacent to the first sensor.

A method, system, and computer program product, include determining a first region based on a first point, a second point and a third point associated with temperature indication information that represents association relationship between temperature and pressure, the first and second points being associated with a same temperature value and different pressure values, a temperature inversion ending at the first point, and the temperature inversion starting from the third point, determining, within the first region, a second region associated with the temperature inversion, and predicting atmospheric condition based on the first and second regions.

Growing community of inventors

Beijing, China

Lingyun Wang