The present disclosure belongs to the technical field of monitoring landslide mass geological disasters, and discloses a multi-state triggered system and method for remote automatic monitoring and early warning of a landslide mass. The multi-state triggered system for remote automatic monitoring and early warning of a landslide mass includes: a landslide mass monitoring module, a data preprocessing module, a communication module, a central control module, a displacement monitoring module, a stability evaluation module, an abnormality early warning module, a power supply module, a data storage module and a display update module. In the present disclosure, through the displacement monitoring module and the stability evaluation module, long-term automatic monitoring of the landslide mass can be realized, and the displacement change of the landslide mass can be grasped so as to evaluate the stability of the landslide mass.

The present disclosure belongs to the technical field of monitoring landslide mass geological disasters, and discloses a multi-state triggered system and method for remote automatic monitoring and early warning of a landslide mass. The multi-state triggered system for remote automatic monitoring and early warning of a landslide mass includes: a landslide mass monitoring module, a data preprocessing module, a communication module, a central control module, a displacement monitoring module, a stability evaluation module, an abnormality early warning module, a power supply module, a data storage module and a display update module. In the present disclosure, through the displacement monitoring module and the stability evaluation module, long-term automatic monitoring of the landslide mass can be realized, and the displacement change of the landslide mass can be grasped so as to evaluate the stability of the landslide mass.

Train a machine learning model, using an image-based knowledge graph of tropical cyclone data, for implementing a surface field modeling architecture that produces images of at least surface wind fields and surface rainfall fields from images of at least tropical cyclone tracks and pressure intensities. Generate model images of a modeled surface wind field and a modeled surface rainfall field by providing images of at least a user-generated tropical cyclone track and pressure intensity to the trained machine learning model.

Train a machine learning model, using an image-based knowledge graph of tropical cyclone data, for implementing a surface field modeling architecture that produces images of at least surface wind fields and surface rainfall fields from images of at least tropical cyclone tracks and pressure intensities. Generate model images of a modeled surface wind field and a modeled surface rainfall field by providing images of at least a user-generated tropical cyclone track and pressure intensity to the trained machine learning model.

To provide a precipitation particle classification apparatus for obtaining a proper classification result of precipitation particles based on information from a plurality of radar devices. The precipitation particle classification apparatus includes a data processing part, a fuzzy processing part, a coordinate conversion part, an interpolation part, and a classification part. The data processing part acquires polarization parameters obtained by reflection on the precipitation particles from each of the plurality of radar devices which are arranged at different positions and have a part of a scanning area overlapping with each other. The fuzzy processing part obtains a polar coordinate distribution evaluation value indicating the distribution in polar coordinates of an evaluation value indicating the degree of attribution to each type of precipitation particles from polarization parameters by using a fuzzy inference. The coordinate conversion part converts the polar coordinate distribution evaluation value into the Cartesian coordinate distribution evaluation value. The interpolation part integrates the Cartesian coordinate distribution evaluation values whose positions on the coordinates are substantially equal among the Cartesian coordinate distribution evaluation values obtained for each of the plurality of radar devices to obtain a composite evaluation value. The classification part classifies precipitation particle species based on the composite evaluation value.

To provide a precipitation particle classification apparatus for obtaining a proper classification result of precipitation particles based on information from a plurality of radar devices. The precipitation particle classification apparatus includes a data processing part, a fuzzy processing part, a coordinate conversion part, an interpolation part, and a classification part. The data processing part acquires polarization parameters obtained by reflection on the precipitation particles from each of the plurality of radar devices which are arranged at different positions and have a part of a scanning area overlapping with each other. The fuzzy processing part obtains a polar coordinate distribution evaluation value indicating the distribution in polar coordinates of an evaluation value indicating the degree of attribution to each type of precipitation particles from polarization parameters by using a fuzzy inference. The coordinate conversion part converts the polar coordinate distribution evaluation value into the Cartesian coordinate distribution evaluation value. The interpolation part integrates the Cartesian coordinate distribution evaluation values whose positions on the coordinates are substantially equal among the Cartesian coordinate distribution evaluation values obtained for each of the plurality of radar devices to obtain a composite evaluation value. The classification part classifies precipitation particle species based on the composite evaluation value.

A processing apparatus includes a data collection unit and a correlation degree derivation unit. The data collection unit is configured to collect operation mode data indicating an operation mode of a windshield wiper, acquired in one or more vehicles. The correlation degree derivation unit is configured to derive a degree of correlation between the operation mode data and precipitation amount data.

A processing apparatus includes a data collection unit and a correlation degree derivation unit. The data collection unit is configured to collect operation mode data indicating an operation mode of a windshield wiper, acquired in one or more vehicles. The correlation degree derivation unit is configured to derive a degree of correlation between the operation mode data and precipitation amount data.

A flood detection device includes a detection result acquisition section, a weather information acquisition section and an identification section. The detection result acquisition section acquires a detection result that, on the basis of a plurality of kinds of running state data relating to running of a vehicle, detects flooding of a road on which the vehicle is running. The weather information acquisition section acquires weather information including at least one of rainfall information representing a measured rainfall amount in a region in which the vehicle is running or rainfall estimation information representing an estimated rainfall amount. The identification section uses the respective acquisition results of the detection result acquisition section and the weather information acquisition section to identify flooding of the road.

A flood detection device includes a detection result acquisition section, a weather information acquisition section and an identification section. The detection result acquisition section acquires a detection result that, on the basis of a plurality of kinds of running state data relating to running of a vehicle, detects flooding of a road on which the vehicle is running. The weather information acquisition section acquires weather information including at least one of rainfall information representing a measured rainfall amount in a region in which the vehicle is running or rainfall estimation information representing an estimated rainfall amount. The identification section uses the respective acquisition results of the detection result acquisition section and the weather information acquisition section to identify flooding of the road.