Remote sensing for intelligent vegetation trim prediction

A system comprising:

• a non-transitory memory that stores machine readable instructions;
• and
• a processing unit that accesses the memory and executes the machine readable instructions, the machine readable instructions comprising:
• a remote sensing controller that includes machine executable instructions that cause a processor to execute operations including receiving a set of 3D data of an environment from a remote sensing device and generating a digital twin of the environment based on the set of 3D data, the digital twin being a 3D representation of the environment including a utility asset and vegetation, wherein the remote sensing controller applies a point cloud algorithm to identify particular utility assets and vegetation based on volumes of point clouds in the digital twin;
• and;
• a digital twin database that stores the digital twin and parameters corresponding to the utility asset and vegetation;
• and
• a biomass engine that includes machine executable instructions that cause the processor to execute operations including:
• classifying instances of vegetation characterized by the digital twin stored in the digital twin database as a particular type of vegetation, wherein each instance of the vegetation is a single plant, and the classifying is based on the volumes from the point clouds to identify particular species of vegetation;
• generating a growth curve for each instance of vegetation based on the digital twin for the corresponding instance of vegetation stored in the digital twin database and the particular type of vegetation, wherein the growth curve is generated by analyzing changes in volume and density of the instance of vegetation over time as captured through multiple scans stored in the digital twin database, and each species of vegetation has one of linear growth, logarithmic growth or exponential growth;
• and
• predicting future growth for each instance of vegetation based on the growth curve and predicts if and when each instance of vegetation will exceed an encroachment threshold associated with the utility asset, wherein the predicting includes determining a future distance between the instance of vegetation and the utility asset based on the growth curve and 3D spatial relationships stored in the digital twin database, and wherein a volume and density of each instance of the vegetation at a future time is predicted by the biomass engine based on the growth curve.

A method comprising:

• receiving, by a remote sensing controller executing on a computing platform comprising a non-transitory memory and a processor, a set of 3D data from a remote sensing device that characterizes an environment including utility assets and vegetation;
• generating, by the remote sensing controller, a digital twin of the environment using the set of 3D data, the digital twin being a 3D representation of the environment including the utility assets and vegetation, wherein the remote sensing controller applies a point cloud algorithm to identify particular utility assets and vegetation based on volumes of point clouds in the digital twin;
• and;
• storing, by the remote sensing controller, the set of 3D data and the digital twin in a digital twin database, digital twin database storing parameters corresponding to utility assets and vegetation of the environment;
• receiving, by the remote sensing controller, another set of 3D data from the remote sensing device that characterizes the environment;
• updating, by the remote sensing controller, the digital twin stored in the digital twin database using the another set of 3D data;
• classifying, by a biomass engine executing on the computing platform comprising the non-transitory memory and the processor, each instance of vegetation characterized by the digital twin stored in the digital twin database as a particular type of vegetation, wherein each instance of the vegetation is a single plant, and the classifying is based on the volumes from the point clouds to identify particular species of vegetation;
• determining, by the biomass engine, a distance to utility assets of each instance of vegetation based on the digital twin;
• storing, by the biomass engine, the classifications and distances to utility assets of each instance of vegetation as parameters corresponding to the instances of vegetation in the digital twin database;
• generating, by the biomass engine, a growth curve for each instance of vegetation based on the digital twin and parameters for the corresponding instance of vegetation stored in the digital twin database, wherein the growth curve is generated by analyzing changes in volume and density of the instance of vegetation over time as captured through multiple scans stored in the digital twin database, and each species of vegetation has one of linear growth, logarithmic growth or exponential growth;
• and
• predicting, by the biomass engine, if and when each instance of vegetation will exceed an encroachment threshold associated with the utility asset, wherein the predicting includes determining a future distance between the instance of vegetation and the utility asset based on the growth curve and 3D spatial relationships stored in the digital twin database, and a volume and density of each instance of the vegetation at a future time based on the growth curve.