Derivative Data Products

Building Outlines

Advanced in-house tools and the latest orthoimagery and lidar data accurately map individual building footprints. A semi-automated process enables faster and more affordable results than traditional manual methods. Data is extracted from high-resolution imagery or classified lidar. The process begins with identifying sample areas representing diverse land cover and terrain, followed by custom classification algorithms and thorough statistical and visual reviews to drive accuracy.

Building Outlines

Advanced in-house tools and the latest orthoimagery and lidar data accurately map individual building footprints. A semi-automated process enables faster and more affordable results than traditional manual methods. Data is extracted from high-resolution imagery or classified lidar. The process begins with identifying sample areas representing diverse land cover and terrain, followed by custom classification algorithms and thorough statistical and visual reviews to drive accuracy.

Edge of Pavement

Detailed edge-of-pavement GIS layers help estimate repaving costs across jurisdictions. High-resolution imagery processed in an AI/ML environment enhances areas where imagery alone is unclear — resulting in more automated, accurate, and consistent pavement delineation.

Edge of Pavement

Detailed edge-of-pavement GIS layers help estimate repaving costs across jurisdictions. High-resolution imagery processed in an AI/ML environment enhances areas where imagery alone is unclear — resulting in more automated, accurate, and consistent pavement delineation.

Elevation-Derived Hydrography

The dynamic nature of water shapes our ever-changing physical landscape and shortens the shelf life of accurate geographic data and analytic products. EDH uses lidar data, human-built features and detailed landscape classifications to create true-to-life representations of water flow patterns. Woolpert’s dedicated EDH team supports the U.S. Geological Survey 3D Hydrography program, incorporating small and ephemeral streams to develop hydrography data up to four times denser than existing surface water data.

Elevation-Derived Hydrography

The dynamic nature of water shapes our ever-changing physical landscape and shortens the shelf life of accurate geographic data and analytic products. EDH uses lidar data, human-built features and detailed landscape classifications to create true-to-life representations of water flow patterns. Woolpert’s dedicated EDH team supports the U.S. Geological Survey 3D Hydrography program, incorporating small and ephemeral streams to develop hydrography data up to four times denser than existing surface water data.

Impervious Surface Mapping

Impervious areas — such as roads, rooftops, and parking lots — are identified and quantified using high-resolution multispectral imagery and ancillary datasets. Advanced AI and machine learning models detect features based on elevation, shape, texture, and spectral signatures. This enables precise mapping for stormwater billing, watershed analysis, flood modeling, and EPA compliance, with fast, scalable, and highly accurate results.

Impervious Surface Mapping

Impervious areas — such as roads, rooftops, and parking lots — are identified and quantified using high-resolution multispectral imagery and ancillary datasets. Advanced AI and machine learning models detect features based on elevation, shape, texture, and spectral signatures. This enables precise mapping for stormwater billing, watershed analysis, flood modeling, and EPA compliance, with fast, scalable, and highly accurate results.

Land Cover/Land Use Mapping

Automated, repeatable workflows generate reliable, cost-effective datasets across diverse landscapes. Lidar elevation data, high-resolution imagery, and ancillary datasets are combined to train machine learning algorithms that accurately classify land cover types. Proprietary pattern recognition and scene reconstruction techniques support change detection, resource management, and planning.

Land Cover/Land Use Mapping

Automated, repeatable workflows generate reliable, cost-effective datasets across diverse landscapes. Lidar elevation data, high-resolution imagery, and ancillary datasets are combined to train machine learning algorithms that accurately classify land cover types. Proprietary pattern recognition and scene reconstruction techniques support change detection, resource management, and planning.

Planimetric Features

Detailed planimetric features are extracted from high-resolution orthoimagery and lidar using advanced remote sensing and photogrammetry. Semi-automated workflows — built on both commercial and proprietary software — support accuracy and efficiency with integrated quality control. Mapped features include buildings, driveways, roads, sidewalks, swimming pools, patios, unpaved roads, vegetation groups, and waterbodies.

Planimetric Features

Detailed planimetric features are extracted from high-resolution orthoimagery and lidar using advanced remote sensing and photogrammetry. Semi-automated workflows — built on both commercial and proprietary software — support accuracy and efficiency with integrated quality control. Mapped features include buildings, driveways, roads, sidewalks, swimming pools, patios, unpaved roads, vegetation groups, and waterbodies.

Contours

In-house tools and routines are used to generate contours at any interval requested. They can be generated from lidar-derived surfaces or point clouds with varying levels of break line detail depending on project specific use and requirements. Automated quality control checks verify continuity and accuracy.

Contours

In-house tools and routines are used to generate contours at any interval requested. They can be generated from lidar-derived surfaces or point clouds with varying levels of break line detail depending on project specific use and requirements. Automated quality control checks verify continuity and accuracy.

Vegetation Classification

After identifying building features, we classify vegetation into height-based categories. Using supervised machine learning and ground truth validation, we achieve over 95% accuracy. This supports wildfire risk detection — including invasive species and deadfall — and enables consistent year-over-year monitoring.

Vegetation Classification

After identifying building features, we classify vegetation into height-based categories. Using supervised machine learning and ground truth validation, we achieve over 95% accuracy. This supports wildfire risk detection — including invasive species and deadfall — and enables consistent year-over-year monitoring.