Abstract: Methods, non-transitory computer readable media, and roof analysis systems are disclosed that preprocess overhead images in imagery data obtained based on a request comprising a geographic location. The overhead images depict a building at different historical points in time identified in the imagery data. A neural network is applied to input data structures into which the overhead images are converted. The neural network is trained to extract relationships between features from the input data structures indicating changes in a roof of the building and generate an output data structure representing the changes. Patterns in the output data structure are analyzed to determine instances of change of the roof. A roof age is then output via a user interface in response to the request. The roof age is generated based on a likelihood of the instances of change or a time interval between the overhead images and a current time.

Abstract: Methods, non-transitory computer-readable media, and property analysis systems are disclosed that extract vegetation location information from overhead and LIDAR images associated with a geographic location. The images are aligned based on the extracted vegetation information. Models are applied to the aligned images based on vegetation height information extracted from the LIDAR images. A graph is then generated based on a result of the application of the models. The graph represents a relationship between vegetation, one or more buildings, and one or more fire pathways associated with the geographic location. A wildfire risk score generated based on the graph is then output for the buildings via a GUI. Thus, the disclosed technology applies wildfire spread models and graphs to vegetation and buildings identified in aligned overhead and LIDAR imagery to provide relatively accurate wildfire risk assessment to insurers and homeowners and thereby facilitate informed decision-making and preventative measures.

Abstract: Methods, non-transitory computer-readable media, and property analysis systems are disclosed that extract vegetation location information from overhead and LIDAR images associated with a geographic location. The images are aligned based on the extracted vegetation information. Models are applied to the aligned images based on vegetation height information extracted from the LIDAR images. A graph is then generated based on a result of the application of the models. The graph represents a relationship between vegetation, one or more buildings, and one or more fire pathways associated with the geographic location. A wildfire risk score generated based on the graph is then output for the buildings via a GUI. Thus, the disclosed technology applies wildfire spread models and graphs to vegetation and buildings identified in aligned overhead and LIDAR imagery to provide relatively accurate wildfire risk assessment to insurers and homeowners and thereby facilitate informed decision-making and preventative measures.

Abstract: Methods, non-transitory computer readable media, and roof analysis systems are disclosed that preprocess overhead images in imagery data obtained based on a request comprising a geographic location. The overhead images depict a building at different historical points in time identified in the imagery data. A neural network is applied to input data structures into which the overhead images are converted. The neural network is trained to extract relationships between features from the input data structures indicating changes in a roof of the building and generate an output data structure representing the changes. Patterns in the output data structure are analyzed to determine instances of change of the roof. A roof age is then output via a user interface in response to the request. The roof age is generated based on a likelihood of the instances of change or a time interval between the overhead images and a current time.

Abstract: Methods, non-transitory computer readable media, and building analysis systems are disclosed that analyze an overhead image to generate a building outline for a building associated with a property represented by the overhead image. The overhead image is included in imagery data obtained from an overhead imagery server based on a received request comprising a geographic location for the property. The building outline is then shifted or rotated. Segment(s) of the building outline are slid to match identified wall(s) of the building. The building outline is then modified based on property feature(s) detected based on an application of one or more trained machine learning classifiers to the overhead image. At least a portion of the overhead image is output with a graphical overlay comprising the building outline via a user interface in response to the received request.

Abstract: Methods, non-transitory computer-readable media, and property analysis systems are disclosed that extract vegetation location information from overhead and LIDAR images associated with a geographic location. The images are aligned based on the extracted vegetation information. Models are applied to the aligned images based on vegetation height information extracted from the LIDAR images. A graph is then generated based on a result of the application of the models. The graph represents a relationship between vegetation, one or more buildings, and one or more fire pathways associated with the geographic location. A wildfire risk score generated based on the graph is then output for the buildings via a GUI. Thus, the disclosed technology applies wildfire spread models and graphs to vegetation and buildings identified in aligned overhead and LIDAR imagery to provide relatively accurate wildfire risk assessment to insurers and homeowners and thereby facilitate informed decision-making and preventative measures.

Abstract: Methods, non-transitory computer readable media, and roof analysis systems are disclosed that preprocess overhead images in imagery data obtained based on a request comprising a geographic location. The overhead images depict a building at different historical points in time identified in the imagery data. A neural network is applied to input data structures into which the overhead images are converted. The neural network is trained to extract relationships between features from the input data structures indicating changes in a roof of the building and generate an output data structure representing the changes. Patterns in the output data structure are analyzed to determine instances of change of the roof. A roof age is then output via a user interface in response to the request. The roof age is generated based on a likelihood of the instances of change or a time interval between the overhead images and a current time.

Abstract: Methods, non-transitory computer readable media, and roof analysis systems are disclosed that preprocess overhead images in imagery data obtained based on a request comprising a geographic location. The overhead images depict a building at different historical points in time identified in the imagery data. A neural network is applied to input data structures into which the overhead images are converted. The neural network is trained to extract relationships between features from the input data structures indicating changes in a roof of the building and generate an output data structure representing the changes. Patterns in the output data structure are analyzed to determine instances of change of the roof. A roof age is then output via a user interface in response to the request. The roof age is generated based on a likelihood of the instances of change or a time interval between the overhead images and a current time.