Global positioning system (GPS) receivers, along with a user device with a camera, can be used to determine an elevation of a point of interest on or within a structure. The user device and a first GPS receiver can be located somewhere outside the structure from which the structure is clearly visible. A second GPS receiver can be located on, within, or near the structure. The user device receives location data from both GPS receivers and calculates a distance between the two. The user device then takes a digital photograph in which structure is visible and notes the photo capture angle. The user device then calculates the elevation of the point of interest trigonometrically using the calculated GPS distance and the photo angle. The user device can then automatically insert this information into associated documentation and transmit the same.

An automated machine learning approach and toolkit is developed for evaluating the causal impact of an event. This approach includes data generation, optimal model selection, model stability evaluation and model explanation. An example approach includes: generating predictive output data of physical geospatial objects is proposed whereby a first data set representative of geospatial event-based data and a second data set representative of the characteristics of the physical geospatial objects are spatially joined together and utilized to generate a causal graph data model that is then provided for at least one of a trained regression machine learning model, a trained causal machine learning model, and a trained similarity machine learning model to generate the predictive output data representative of event-adjusted characteristics of the physical geospatial objects.

Methods and systems for communicating between autonomous vehicles are described herein. Such communication may be performed for signaling, collision avoidance, path coordination, and/or autonomous control. A computing device may receive data for the same road segment from autonomous vehicles, including (i) an indication of a location within the road segment, and (ii) an indication of a condition of the road segment. The computing device may generate, from the data for the same road segment, an overall indication of the condition of the road segment, which may include a recommendation to vehicles approaching the road segment. Additionally, the computing device may receive a request from a computing device within a vehicle approaching the road segment to display vehicle data. The overall indication for the road segment may then be displayed on a user interface of the computing device.

A system for generating emergency egress advisement for a building having at least one first computing device that determines a floormap and generates initial emergency egress advisement for the building and at least one second computing device that improves generation of initial emergency egress advisement. The second computing device can receive the initial emergency egress advisement, iteratively train a model for the building by correlating the initial emergency egress advisement to corresponding information about intended egress outcomes for different emergency situations in the building across one or more model layers using one or more machine learning algorithms, predict, based on real-time information about the emergency and historic user presence information, presence and location information of users in the building, generate egress routes that can be used by the users, and update, based on a trained model and the generated egress routes, the initial emergency egress advisement for the building.

A method for predicting snowmelt flood is provided. The method includes: acquiring rain and snow fall distribution data in a target area in a preset time period, and extracting precipitation characteristic data according to the rain and snow fall distribution data; acquiring temperature distribution data in the target area, acquiring a target temperature and a corresponding target time according to the temperature distribution data, and determining temperature characteristic data according to the target temperature and the target time; and determining a snowmelt flood risk level in the target area according to the precipitation characteristic data and the temperature characteristic data.

A method for extracting a dam emergency event based on a dual attention mechanism is provided. The method includes: performing data preprocessing, building a dependency graph, building a dual attention network, and filling a document-level argument. The performing data preprocessing includes labeling a dam emergency corpus and encoding sentences. Building a dependency graph includes assisting a model to mine a syntactic relation based on a dependency. Building a dual attention network includes weighing and fusing an attention network based on a graph transformer network (GTN) and capturing key semantic information in the sentence. Filling a document-level argument includes filling a document-level argument by detecting a key sentence and ordering a semantic similarity. The method introduces a dependency and overcomes the long-range dependency problem based on the dual attention mechanism, thus achieving high identification accuracy and reducing a lot of labor costs.

The concepts and technologies disclosed herein are directed towards a predictive hydrological impact diagnosis system. According to one aspect disclosed herein, the system can obtain weather data associated with an area. The weather data can include an interval rainfall forecast and a total accumulated rainfall forecast for the area. The system can execute a flood index algorithm using the interval rainfall forecast and the total accumulated rainfall forecast. In response to executing the flood index algorithm, the system can obtain an output of the flood index algorithm. The output can include flood index data for the area. The system can plot the flood index data on a graph to show a forecasted rainfall intensity over a time. The system can determine hydrological potential energy data for the area. This data is representative of a cumulative area of the graph that is above a predetermined threshold value.

A three-level grid multi-scale finite element method for simulating groundwater flow in heterogeneous aquifers is proposed in present disclosure. The three-level grid refers to dividing the study region into coarse grid elements, then dividing each coarse grid element into medium grid elements, and finally dividing each medium grid element into fine grid elements, thereby improving the coarse-scale basis function construction method of the multi-scale finite element method. The new method of constructing a coarse-scale basis function by using the multi-scale finite element method itself instead of the finite element method is provided, constructing medium-scale basis functions on local medium grid elements, and using the medium-scale basis functions to construct a coarse-scale basis function in each coarse element, which can significantly improve the construction efficiency of the coarse-scale basis function.

Methods and systems for autonomous and semi-autonomous vehicle control, routing, and automatic feature adjustment are disclosed. Sensors associated with autonomous operation features may be utilized to search an area for missing persons, stolen vehicles, or similar persons or items of interest. Sensor data associated with the features may be automatically collected and analyzed to passively search for missing persons or vehicles without vehicle operator involvement. Search criteria may be determined by a remote server and communicated to a plurality of vehicles within a search area. In response to which, sensor data may be collected and analyzed by the vehicles. When sensor data generated by a vehicle matches the search criteria, the vehicle may communicate the information to the remote server.

Disclosed in the present invention is a method for forecasting runoff under influence of an upstream reservoir group by utilizing forecasting errors. The method comprises: collecting data; establishing a regulation and storage influence quantity estimation model by utilizing a known hydrological model and a KNN model according to the collected data; driving the hydrological model by combining the collected data to predict a future runoff volume; obtaining a forecast error in a previous time period; obtaining a future regulation and storage influence quantity estimated value according to the forecast error in the previous time period in combination with the regulation and storage influence quantity estimation model; and superposing the future runoff volume and the future regulation and storage influence quantity estimated value to obtain a runoff forecast value in a future time period.