ArcGIS REST Services Directory
JSON

Layer: San Mateo SOD Veg Clipped to 3000 (ID:7)

View In:   Map Viewer

Name: San Mateo SOD Veg Clipped to 3000

Display Field: MAP_CLASS_18

Type: Feature Layer

Geometry Type: esriGeometryPolygon

Description: For the final project report that includes detailed methods and an accuracy assessment, go to this link: https://vegmap.press/san_mateo_finescale_final_report The San Mateo County fine scale vegetation map is a 106-class vegetation map of San Mateo County with 97,580 polygons. The map also includes select federal lands (NPS/Presidio Trust) in San Francisco city/county. The fine scale vegetation map represents the state of the landscape in 2018 and adheres to the National Vegetation Classification System (NVC). The map was designed to be used at scales of 1:5,000 and smaller. Table 1 shows the options for downloading the fine scale vegetation map. Table 1. Options for downloading the San Mateo fine scale vegetation map Description Location File GDB Feature Class https://vegmap.press/San_Mateo_vegmapLayer Symbology https://vegmap.press/San_Mateo_vegmap_layer_file Layer Package https://vegmap.press/San_Mateo_vegmap_layer_package Feature Service https://vegmap.press/San_Mateo_vegmap_feature_service Web Map https://vegmap.press/San_Mateo_vegmap_webmap Map class definitions, as well as a dichotomous key for the map classes, can be found in the San Mateo Fine Scale Vegetation Map Key (https://vegmap.press/sm_mapping_key). A key to map class abbreviations is also available (https://vegmap.press/sm_vegmap_abbrevs). The next section provides an overview of methods. The methods overview is followed by tables that show the minimum mapping unit for the project and the list of attributes contained in the fine scale map’s attribute table. Fine Scale Vegetation Methods Overview:The fine scale vegetation map was created using semi-automated methods that include field work, computer-based machine learning, and manual aerial photo interpretation. The vegetation map was developed by first creating an enhanced lifeform map, a 25-class map that served as a foundation for the fine-scale map. The lifeform map was created using “expert systems” rulesets in Trimble Ecognition. These rulesets combine automated image segmentation (stand delineation) with object-based image classification techniques. In contrast with machine learning approaches, expert systems rulesets are developed heuristically based on the knowledge of experienced image analysts. Key data sets used in the expert systems rulesets for enhanced lifeform included: 6-inch, 4-band orthophotography (2018), the 2019 LiDAR derived Canopy Height Model (CHM), and other LiDAR derived landscape metrics. After it was produced using Ecognition, the preliminary enhanced lifeform map product was manually edited by photo interpreters. Manual editing corrected errors where the automated methods produced incorrect results. Edits were made to correct two types of errors: 1) unsatisfactory polygon (stand) delineations and 2) incorrect polygon labels.The mapping team used the enhanced lifeform map as the foundation for the finer scale and more floristically detailed fine scale vegetation map. For example, a single polygon mapped in the enhanced lifeform map as ‘evergreen hardwood’ might be divided into four polygons in the in the fine scale map including tanoak, California live oak, California bay forest, and madrone. The enhanced lifeform map was refined into the fine scale vegetation map using a semi-automated approach. The approach combines Ecognition segmentation, extensive field data collection, machine learning, manual editing, and expert review. Ecognition segmentation results in refinement and subdivision of the larger lifeform polygons. Field data collection results in a large number of training polygons labeled with their field-validated map class. Machine learning relies on the field collected data as training data and a stack of GIS datasets as predictor variables. The resulting model is used to create automated fine-scale labels countywide. Machine learning algorithms for this project included both Random Forests and Support Vector Machines (SVMs). Machine learning is followed by extensive manual editing, which is used to 1) edit segment (polygon) labels when they are incorrect and 2) edit segment (polygon) shape when necessary.The map classes in the fine scale vegetation map generally correspond to the alliance level of the National Vegetation Classification, but some map classes - especially herbaceous types - correspond to higher levels of the hierarchy (such as group or macrogroup). Minimum Mapping Units:Table 2 shows the minimum mapping units (MMUs) for the fine scale vegetation map.Minimum Mapping Units by Feature TypeFeature TypeMinimum Mapping UnitAgricultural Classes1/4 AcreWoody Upland Classes1/2 acre for contrasting lifeforms (e.g., ‘forest fragments’ surrounded by non-forest); 1 acre for different alliances in the same lifeformWoody Riparian Classes1/4 Acre for contrasting lifeforms, 1 acre for different alliances in the same lifeformUpland Herbaceous Classes1/2 Acre for contrasting lifeforms, 1 acre for different alliances in the same lifeformWetland Herbaceous Classes1/4 acre for contrasting lifeforms; 1 acre for different alliances in the same lifeformBare Land1/2 AcreDeveloped 1/5 AcreWater400 square feetFine Scale Vegetation Map Attributes:Table 3 shows the attributes (fields) in the fine scale vegetation map.Fine Scale Map Attributes (Name/Alias)DescriptionOID_COPY/ OID_COPYIndex for internal useMAP_CLASS_18/Fine Scale Map Class in ‘18National Vegetation Classification (NVCS) map class label for all stands. ABBRV/Fine Scale Map Class AbbreviationMap class abbreviations for use in cartography and visualization. A key to abbreviations is available here: https://vegmap.press/San Mateo_vegmap_abbrevsLIFEFORM_18/Lifeform in ‘1815-class lifeform label for all stands. Labels are floristically more general than the fine scale map class and forest lifeform. ENHANCED_LIFEFORM_18/Enhanced Lifeform in ‘1820-class lifeform label for all stands. Labels are floristically more general than the fine scale map class. ABS_COVER_17/% Veg Returns Over 15 ft. in ‘17Absolute cover of trees greater than 15 feet in height. Derived from 2019 lidar data.REL_CON_COV_18/Relative % Conifer Cover in ‘18Relative conifer cover, estimating the percent of tree canopy >= 15 ft. is conifer. Derived from manual image interpretation of ‘18 imagery.REL_HDW_COV_18/Relative % Hardwood Cover in ‘18Relative hardwood cover, estimating the percent of tree canopy >= 15 ft. is hardwood. Derived from manual image interpretation of ‘18 imagery.HDW_COVER_18/Absolute % Hardwood Cover in ‘18Absolute hardwood cover, derived as: ((relative % hardwood cover/100) x (absolute % hardwood/100)) * 100CON_COVER_18/Absolute % Conifer Cover in ‘18Absolute conifer cover, derived as: ((relative % conifer cover/100) x (absolute % cover/100)) * 100SHB_COVER_18/Absolute % Shrub Cover in ‘18Absolute shrub cover for herbaceous and shrub stands. Derived from manual image interpretation of ‘18 imagery.STAND_HT_MN_17/Mean LiDAR Stand Height in ‘17 (ft.)Mean stand height from LiDAR-derived canopy height model (CHM).STAND_HT_MN_17/Median LiDAR Stand Height in ‘17 (ft.)Median stand height from LiDAR-derived canopy height model (CHM).STAND_HT_MX_17/Maximum LiDAR Stand Height in ‘17 (ft.)Maximum stand height from LiDAR-derived canopy height model (CHM).STAND_HT_SD_17/Standard Deviation LiDAR Stand Height in ‘17 (ft.)Standard deviation stand height from LiDAR-derived canopy height model (CHM).STANDING_DEAD_19/% Standing Dead 2018Estimate of percent standing dead vegetation in forested stands. Estimates the percent of the woody canopy > 7 feet tall that did not have a living crown in 2018.SD_PRESENCE/Standing Dead Presence in 2018Indicates the presence of standing dead vegetation at under .5% of the stand’s cover above 7 ft. (trace amount of standing dead).LADDER_FUELS_17/Mean Ladder Fuels 1-4 Meters (0-1)Mean lidar derived ‘ladder fuels’ for forested stands. Represents density of lidar returns between 1-4 meters above ground. Integrated from the 2017 lidar derived ladder fuels raster using the zonal statistics function. The ladder fuel metric is a 0-1 metric; 0 is lowest, 1 is highest.SLOPE_MEAN/Mean Slope DegreesMean slope degrees, derived from the 2017 lidar data.SLOPE_STD/Standard Deviation Slope DegreesStandard deviation slope degrees, derived from the 2017 lidar data.SLOPE_MAX/Maximum Slope DegreesMaximum slope degrees, derived from the 2017 lidar data.PERVIOUS_18/% Pervious in ‘18Percent of stand that was pervious in 2018. Integrated from the San Mateo County impervious surface map.IMPERVIOUS_18/% Impervious in ‘18Percent of stand that was impervious in 2018. Integrated from the San Mateo County impervious surface map.PAVED_RD_18/% Paved Road in ‘18Percent of stand that was paved road in 2018. Integrated from the San Mateo County impervious surface map.DIRT_RD_18/% Dirt and Gravel Road in ‘18Percent of stand that was dirt or gravel road in 2018. Integrated from the San Mateo County impervious surface map.OTHER_IMPERVIOUS_18/% Other Impervious in ‘18Percent of stand that was a paved or unpaved, non-road surface (such as a paved or unpaved parking lot) in 2018. Integrated from the San Mateo County impervious surface map.BUILDING_18/% Buildings in ‘18Percent of stand that was a building in 2018. Integrated from the San Mateo County impervious surface map.ACRES/ AcresAcres of land encompassed by the stand.SOURCE/SourceIndicates whether stand’s fine scale map class was validated during field work, or if the map label was assigned based on remote sensing methods.URBAN_WINDOW/Urban Window FlagA flag that indicates if the stand was in a core urban area (the ‘urban window’).COUNTY/CountyIndicates whether the stand was in San Francisco or San Mateo County.Related Datasets and Resources:Enhanced Lifeform – The enhanced lifeform map is derived from this Fine-Scale Vegetation map. It is a simplification of the vegetation map, with a fraction of the total map classes. Impervious Surfaces Map – The impervious surfaces map is a fine scale map of built features including dirt gravel roads, paved roads, buildings, and other impervious surfaces.CNPS Report – Vegetation Classification of Alliances and Associations in San Mateo County, California. This report provides very detailed information about San Mateo County’s vegetation communities. This work includes a classification report and floristic key (more detailed than the mapping key), as well as detailed descriptions for each map class.

Copyright Text: Golden Gate National Parks Conservancy, Tukman Geospatial LLC, Aerial Information Systems, National Park Service, Midpeninsula Regional Open Space District, County of San Mateo, San Francisco Public Utilities Commission, Peninsula Open Space Trust, San Mateo City/County Association of Governments

Min. Scale: 0

Max. Scale: 0

Default Visibility: false

Max Record Count: 2000

Supported query Formats: JSON, geoJSON, PBF

Use Standardized Queries: True

Extent:

Drawing Info:

HasZ: true

HasM: false

Has Attachments: false

Has Geometry Properties: true

HTML Popup Type: esriServerHTMLPopupTypeAsHTMLText

Object ID Field: OBJECTID

Unique ID Field:

Global ID Field:

Type ID Field: MAP_CLASS_18

Fields:
Types:

Is Data Versioned: false

Has Contingent Values: false

Supports Rollback On Failure Parameter: true

Last Edit Date: 5/18/2026 11:09:05 PM

Schema Last Edit Date: 5/18/2026 11:09:05 PM

Data Last Edit Date: 5/18/2026 11:09:05 PM

Supported Operations:   Query   Query Pivot   Query Top Features   Query Analytic   Query Bins   Generate Renderer   Validate SQL   Get Estimates   ConvertFormat