1 / 39

Random Forests and Nearest Neighbors: Methods for mapping the West Cascades of Oregon

Random Forests and Nearest Neighbors: Methods for mapping the West Cascades of Oregon. Emilie Grossmann, Oregon State University Janet Ohmann, U. S. Forest Service James Kagan, Oregon State University Kenneth Pierce, U.S. Forest Service Heather May, Oregon State University

lyle
Télécharger la présentation

Random Forests and Nearest Neighbors: Methods for mapping the West Cascades of Oregon

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Random Forests and Nearest Neighbors: Methods for mapping the West Cascades of Oregon Emilie Grossmann, Oregon State University Janet Ohmann, U. S. Forest Service James Kagan, Oregon State University Kenneth Pierce, U.S. Forest Service Heather May, Oregon State University Matthew Gregory, Oregon State University

  2. The West Cascades Madison The West Cascades

  3. USGS Pacific Northwest ReGAP • GAP project needs broad-scale, but also detailed vegetation base-maps. • Consistent classification system: NatureServe’s Ecological Systems

  4. North Pacific Mesic-Wet Douglas-fir Western Hemlock Forest • This ecological system is a significant component of the lowland and low montane forests of western Washington, northwestern Oregon, and southwestern British Columbia. • ... In Oregon, it occurs on the western slopes of the Cascades, around the margins of the Willamette Valley, and on the west side of the Coast Ranges, and is reduced to locally small patches in southwestern Oregon. ... continued

  5. North Pacific Mesic-Wet Douglas-fir Western Hemlock Forest ... • They differ from North Pacific Maritime Dry-Mesic Douglas-fir-Western Hemlock Forest primarily in having more hydrophilic undergrowth species ... • In many rather drier climatic areas, it occurs as small to large patches within a matrix of North Pacific Maritime Dry-Mesic Douglas-fir-Western Hemlock Forest; in dry areas, it can occur adjacent to or in a mosaic with North Pacific Dry Douglas-fir Forest and Woodland, and at higher elevations it intermingles with either North Pacific Dry-Mesic Silver Fir-Western Hemlock-Douglas-fir Forest or North Pacific Mesic Western Hemlock-Silver Fir Forest.

  6. Can you see the problem? • We need more information than LANDSAT • This is why we need statistics for building the GAP maps. What type of model to use?

  7. Objective • Compare Random Forest (RF) and Gradient Nearest Neighbor (GNN) modeling techniques with respect to: • classification accuracy • class area representation • spatial patterns • explanatory variables used

  8. Methods • GNN and RF models built from • 4222 records from our plot database • and mapped explanatory variables, selected from 115 possible layers

  9. Methods: Random Forest • One Classification Tree. Elevation < 1244 August Maximum < 2560 Temp August Maximum < 2324 Temp Summer Mean < 1279 Temp Aug. to Dec. Temperature < 1279 Differential LANDSAT Band 7 < 24 Elevation < 1625 4215 4267 4224 4224 4272 4228 4224 4215 North Pacific Dry-Mesic Silver Fir-Western Hemlock-Douglas-fir Forest

  10. Methods: Random Forest • A “Forest” of classification trees. • Each tree is built from a random subset of plots and variables. • When the model is applied to a pixel, each tree ‘votes’ for an Ecological System.

  11. Methods: Adjusting The Random Forest Map • The Random Forest model tends to over-map some systems, and under-map others. • We can map the votes for the under-mapped systems, creating single-system maps. • ...which can be used to expand their area in the final map.

  12. Methods: Adjusting The Random Forest Map Single System Map of: North Pacific Mesic Western Hemlock-Silver Fir Forest

  13. (2) calculate axis scores of pixel from mapped data layers study area (4) impute nearest neighbor’s value to pixel (3) find nearest-neighbor plot in gradient space Methods: Gradient Nearest Neighbor Imputation gradient space geographic space CCA Axis 2 (e.g., Climate) (1) conduct gradient analysis of plot data CCA Axis 1 (e.g., elevation, Y)

  14. Without Landsat TM RF RF_ADJ GNN With Landsat TM RF_TM RF_ADJ_TM GNN_TM The Maps

  15. Results

  16. RF_ADJ_TM: 0.38 0.70 GNN: 0.30 0.63 RF_TM: 0.38 0.73 RF: 0.34 0.68 GNN_TM: 0.29 0.60 RF_ADJ: 0.34 0.70 Top #: Kappa, Bottom #: Fuzzy Kappa

  17. Best Maps: Class By Class (assigned by Kappa)

  18. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest Actual Area (est. from Inventory Plots)

  19. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest Random Forest No Imagery

  20. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest Random Forest With Imagery

  21. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest Random Forest Adjusted No Imagery

  22. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest Random Forest Adjusted With Imagery

  23. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest GNN No Imagery

  24. 80,000 60,000 Hectares 40,000 20,000 0 North Pacific North Pacific Dry North Pacific Mesic North Pacific Maritime Mountain Hemlock Forest Mesic Subalpine Parkland Mediterranean California Mesic North Pacific Maritime Dry-Mesic North Pacific Dry-Mesic Silver Fir- Douglas-fir Forest and Woodland North Pacific Maritime Mesic-Wet Mediterranean California Dry-Mesic Western Hemlock-Silver Fir Forest Mixed Conifer Forest and Woodland Mixed Conifer Forest and Woodland Douglas-fir-Western Hemlock Forest Douglas-fir-Western Hemlock Forest Western Hemlock-Douglas-fir Forest GNN with Imagery

  25. Random Forest UnadjustedNo Imagery

  26. Random ForestAdjustedNo Imagery

  27. Random ForestUnadjustedWith Imagery

  28. Random ForestAdjustedWith Imagery

  29. GNNNo Imagery

  30. GNNWith Imagery

  31. Top 5 Variables

  32. X X X X X RF Accuracy OK Area lousy Coarse-grained RF_ADJ Accuracy OK Area OK RF_TM Best Accuracy Area lousy RF_ADJ_TM Accuracy Good Area OK Incorporates Imagery GNN Accuracy OK Area Good No Imagery GNN_TM Least accurate Area good Fine-grained

  33. Conclusions • Buyer Beware. • The patterns in a map are at least partly a function of model choice. • The most appropriate map depends upon intended application. • Importance of area estimations vs. incorporation of imagery • For some applications, the GNN base-map may be better. • We chose RF_Adj_TM, because it balanced a variety of concerns well.

  34. Landscape Ecology Modeling Mapping & Analysis Acknowledgements: • USGS GAP analysis program • LEMMA research group at Oregon State University • Jimmy Kagan – reality-check and systems identification • Brendan Ward – programming help

More Related