Gradient Nearest Neighbor (GNN) Method for Local-Scale Basal Area Mapping: FIA 2005 Symposium Interpolation Contest Kenneth B. Pierce Jr., Matthew J. Gregory*

Slides:



Advertisements
Similar presentations
Spatial point patterns and Geostatistics an introduction
Advertisements

Tables, Figures, and Equations
Sensitivity of wildlife habitat capability models to spatial resolution of underlying mapped vegetation data Matthew J. Gregory 1 Janet L. Ohmann 2 Brenda.
An Introduction to Multivariate Analysis
The Nationwide Forest Imputation Study (NaFIS): Challenges, results and recommendations from the western United States Matt Gregory 1, Emilie Grossmann.
Mapping Current Vegetation in the Pacific Coast States with GNN, CART, and Other Tricks Landscape Ecology, Modeling, Mapping, and Analysis (LEMMA) team.
The West Cascades Park City The West Cascades NaFISNationwide Forest Imputation Study.
Spatial monitoring of older forest for the Northwest Forest Plan Janet Ohmann 1, Matt Gregory 2, Heather Roberts 2, Robert Kennedy 2, Warren Cohen 1, Zhiqiang.
Spatial monitoring of late-successional forest habitat over large regions with nearest-neighbor imputation Janet Ohmann 1, Matt Gregory 2, Heather Roberts.
Maximum Covariance Analysis Canonical Correlation Analysis.
Mapping change in live and dead forest biomass with Landsat time-series, remeasured plots, and nearest-neighbor imputation Janet Ohmann 1, Matt Gregory.
Basic geostatistics Austin Troy.
Gradients or hierarchies? Which assumptions make a better map? Emilie B. Grossmann Janet L. Ohmann Matthew J. Gregory Heather K. May.
Spatial Statistics in Ecology: Case Studies Lecture Five.
All for one or One for All? Mapping many species individually vs. simultaneously with random forest. Emilie Henderson, Janet Ohmann, Matthew Gregory, Heather.
Estimating forest structure in wetlands using multitemporal SAR by Philip A. Townsend Neal Simpson ES 5053 Final Project.
Introducing the Forest Planner a project of Ecotrust Free web-based decision support for landowners in Oregon and Washington Growth Model Users Group.
1 Multivariate Statistics ESM 206, 5/17/05. 2 WHAT IS MULTIVARIATE STATISTICS? A collection of techniques to help us understand patterns in and make predictions.
Correlation and Autocorrelation
Princeton University Global Evaluation of a MODIS based Evapotranspiration Product Eric Wood Hongbo Su Matthew McCabe.
Spatial Interpolation
Department of Geography, University of California, Santa Barbara
Deterministic Solutions Geostatistical Solutions
Why Geography is important.
Analysis of Individual Variables Descriptive – –Measures of Central Tendency Mean – Average score of distribution (1 st moment) Median – Middle score (50.
Applications in GIS (Kriging Interpolation)
Method of Soil Analysis 1. 5 Geostatistics Introduction 1. 5
Why Worry? Predictive models of vegetation-environment relationships are an important first step in mapping vegetation classes at regional scales. There.
These early results were obtained using one year’s set of FIA field data, DISTANCE: EUCLIDEAN WEIGHTING FUNCTION: NO WEIGHTS. NUMBER OF PLOTS: 696 NUMBER.
Gradient Nearest Neighbor Imputation Maps for Landscape Analysis in the Pacific Northwest Janet L. Ohmann Pacific Northwest Research Station USDA Forest.
Methods in Medical Image Analysis Statistics of Pattern Recognition: Classification and Clustering Some content provided by Milos Hauskrecht, University.
Analysis of Conflict between Potential Resource Use and Wildlife Conservation in The Muskuwa-Kechika Management Area Nobuya (Nobi) Suzuki, Natural Resources.
Quantitative Estimates of Biomass and Forest Structure in Coastal Temperate Rainforests Derived from Multi-return Airborne Lidar Marc G. Kramer 1 and Michael.
Getting Ready for the Future Woody Turner Earth Science Division NASA Headquarters May 7, 2014 Biodiversity and Ecological Forecasting Team Meeting Sheraton.
Why Is It There? Getting Started with Geographic Information Systems Chapter 6.
Validating Wykoff's Model, Take 2: Equivalence tests and spatial analysis in a design- unbiased analytical framework Robert Froese, Ph.D., R.P.F. School.
STRATIFICATION PLOT PLACEMENT CONTROLS Strategy for Monitoring Post-fire Rehabilitation Treatments Troy Wirth and David Pyke USGS – Biological Resources.
The Semivariogram in Remote Sensing: An Introduction P. J. Curran, Remote Sensing of Environment 24: (1988). Presented by Dahl Winters Geog 577,
Spatial Analysis of Large Tree Distribution of FIA Plots on the Lassen National Forest Tom Gaman, East-West Forestry Associates, Inc Kevin Casey, USDA-FS.
Vegetation Mapping An Interagency Approach The California Department of Forestry and Fire Protection and the USDA Forest Service Mark Rosenberg: Research.
Applications of Spatial Statistics in Ecology Introduction.
Extent and Mask Extent of original data Extent of analysis area Mask – areas of interest Remember all rasters are rectangles.
Remotely sensed land cover heterogeneity
Spatial Analysis & Geostatistics Methods of Interpolation Linear interpolation using an equation to compute z at any point on a triangle.
Principle Component Analysis (PCA)
Northern Michigan Forest Productivity Across a Complex Landscape David S. Ellsworth and Kathleen M. Bergen.
Lecture 12 Factor Analysis.
Grid-based Map Analysis Techniques and Modeling Workshop
Goal: to understand carbon dynamics in montane forest regions by developing new methods for estimating carbon exchange at local to regional scales. Activities:
Imputating snag data to forest inventory for wildlife habitat modeling Kevin Ceder College of Forest Resources University of Washington GMUG – 11 February.
L15 – Spatial Interpolation – Part 1 Chapter 12. INTERPOLATION Procedure to predict values of attributes at unsampled points Why? Can’t measure all locations:
Lecture 6: Point Interpolation
 Chapter 3! 1. UNIT 7 VOCABULARY – CHAPTERS 3 & 14 2.
Multivariate Analysis and Data Reduction. Multivariate Analysis Multivariate analysis tries to find patterns and relationships among multiple dependent.
Variance of Similar Neighbors compared to Random Imputation Nearest Neighbor Conference August 28-30, 2006 Kenneth B. Pierce Jr and Janet L. Ohmann Forestry.
Prediction models perform better when including transition zones Sophie Vermeersch Plant Science and Nature Plant Science and Nature Management, Department.
INTEGRATING SATELLITE AND MONITORING DATA TO RETROSPECTIVELY ESTIMATE MONTHLY PM 2.5 CONCENTRATIONS IN THE EASTERN U.S. Christopher J. Paciorek 1 and Yang.
Stochastic Hydrology Random Field Simulation Professor Ke-Sheng Cheng Department of Bioenvironmental Systems Engineering National Taiwan University.
A Framework and Methods for Characterizing Uncertainty in Geologic Maps Donald A. Keefer Illinois State Geological Survey.
Methods of multivariate analysis Ing. Jozef Palkovič, PhD.
Forest ecological applications of ALS ALS provide 3D information where each point has height (and intensity) value Even with low pulse density data, say,
PADMA ALEKHYA V V L, SURAJ REDDY R, RAJASHEKAR G & JHA C S
JMP Discovery Summit 2016 Janet Alvarado
Coweeta Terrain and Station Locations
Quantifying Scale and Pattern Lecture 7 February 15, 2005
Incorporating Ancillary Data for Classification
Review- vector analyses
Tabulations and Statistics
Stochastic Hydrology Random Field Simulation
Interpolation & Contour Maps
Presentation transcript:

Gradient Nearest Neighbor (GNN) Method for Local-Scale Basal Area Mapping: FIA 2005 Symposium Interpolation Contest Kenneth B. Pierce Jr., Matthew J. Gregory* and Janet L. Ohmann Forestry Science Lab, 3200 SW Jefferson Way, Corvallis OR 97331

Why map? Why GNN? (Pacific Northwest perspective) Primary objective: supply missing data for analysis and modeling of forest ecosystems at the regional level Problem: basic information on current vegetation is needed to address a wide array of issues in forest management and policy. Increasingly, this information needs to be: –spatially complete (spatial pattern, small geographic areas) –consistent across large, multi-ownership regions –rich in floristic and structural detail –suitable for input to stand and landscape simulation models –flexible in meeting a variety of analytical needs Differs from other objectives which are concerned primarily with estimation

GNN Mapping in West Coast States Future GNN mapping: Wall-to-wall OR, CA, WA –Start Oct. ’05 in eastern OR –5-year mapping cycle –Coordinated with Region 6, Oregon Department of Forestry and other collaborators –Funded by FIA and the Western Wildlands Environmental Threat and Analysis Center ‘Ecological Systems’ for Gap Analysis Program (MZs 8 & 9) Includes non-forest mapping COLA CLAMS GNNFire Current GNN efforts

The Gradient Nearest Neighbor (GNN) Method for Vegetation Mapping A tool for: –Spatially explicit (wall-to-wall) vegetation data based on ‘interpolation’ of FIA plot data using an ecological (gradient) model –Inference of plot data to smaller geographic areas (e.g., 6 th -field HUCs) Imputation approach (as are kNN, MSN) provides: –Data that are regional in extent, yet rich in detail –Analytical flexibility for users

Components of GNN Imputation Statistical model = canonical correspondence analysis (CCA) (flexibility for redundancy analysis (RDA) and other methods): –Multivariate –Results in a weight for each of many spatial variables, based on its relationship with the multiple response variables –Any multivariate method can be specified (eg. PCA, CCorA) Distance measure (between map pixel and potential NN plots): –Euclidean distance for first n axes (usually 8, specified by user) –Axes weighted by their explanatory power (eigenvalues) Imputation method: –Single nearest neighbor (k=1, MSN-like) –Summary statistic of multiple neighbors (kNN-like) –Measures of variation based on multiple imputation (k>1)

Environmental and Disturbance Gradients (Explanatory Variables) Landsat TM (1996) Bands, transformations, texture ClimateMeans, seasonal variability Topography Elevation, slope, aspect, solar Disturbance Past fires, harvest, insects and disease LocationX, Y Ownership FS, BLM, forest industry, other private

Gradient Nearest Neighbor Method Plot data Climate Geology Topography Ownership Remote sensing PredictionSpatial data Plot locations Direct gradient analysis Plot assigned to each pixel Statistical model Imputation Pixel PSME (m 2 /ha) CanCov (%) Snags >50 cm (trees/ha) Old-growth index Etc

(2) calculate axis scores of pixel from mapped data layers (3) find nearest- neighbor plot in gradient space Axis 2 (climate) gradient spacegeographic space Axis 1 (Landsat) (1) conduct gradient analysis of plot data field plots study area (4) impute nearest neighbor’s ground data to mapped pixel The imputation component of GNN

Accuracy assessment (‘obsessive transparency’) Local-scale accuracy (at plot locations) via cross-validation: –Confusion matrices –Kappa statistics –Correlation statistics Regional-scale accuracy: –distribution of forest conditions in map vs. plot sample –range of variation in map vs. plot sample Spatial depictions: –Variation among k nearest neighbors –Distance to nearest neighbor(s) (sampling sufficiency) Findings re. GNN map accuracy: –Excellent for regional patterns and amounts, imperfect for local sites –Mid-scales??? –Appropriate for regional planning and policy analysis

Bartlett Interpolation Contest Comparison between ‘control’ methods and GNN methods Effect of footprint size

Interpolation Contestants Kriging –best with intensive sampling and autocorrelated data Linear Model –perhaps best local predictions when a strong gradient / remote sensing link exists for the response Single neighbor GNN Imputation –best for multivariate responses and regional data, recaptures variation and attribute covariance Mean of 5 nearest GNN neighbors

ObservedKrigedLinearGNN1GNN5 Distributions Average Maximum Variance Models RMSE Slope Y-intercept Corr. coeff R-square Model Comparisons

Plot scale accuracy assessment Predicted basal area (m 2 /ha) Observed basal area (m 2 /ha) ab cd a)Kriging b)Linear Model c)GNN1 d)GNN5

Quantile distributions Overprediction at lower basal areas / underprediction at higher basal areas Accentuated for linear model

Bartlett Study Area TM Leaf On 4|5|3

Bartlett Study Area TM Leaf On 4|5|3

Kriged Spatial Prediction – – – – – – – 70.0 > 70.0 Basal area m 2 /ha 0.0 – – – – 60.0 > 60.0

Linear Model Spatial Prediction – – – – – – – 70.0 > 70.0 Basal area m 2 /ha 0.0 – – – – 60.0 > 60.0

GNN 1 st Neighbor Spatial Prediction – – – – – – – 70.0 > 70.0 Basal area m 2 /ha 0.0 – – – – 60.0 > 60.0

GNN 5-Neighbor Mean Spatial Prediction – – – – – – – 70.0 > 70.0 Basal area m 2 /ha 0.0 – – – – 60.0 > 60.0

Effect of plot footprint size Studied to account for possible misregistration between plots and TM imagery Used two footprints at 30m cell resolution –1x1 and 2x2 (plot spacing is ~65m – 3x3 windows overlap) –Used for both extraction of spatial data and for mean basal area prediction at the cross-validation plots Imputation is still at a per-pixel level

ObservedGNN 1x1GNN 2x2 Distributions Average Maximum Variance Models RMSE Slope Y-intercept Corr. coeff GNN 1x1 Window GNN 2x2 Window

Summary – Bartlett Interpolation Inverse relationship between better model fits and maintaining sample variance between methods While kriging gives the highest degree of local scale agreement, it suffers from lack of spatial pattern Linear model and GNN imputation methods seem to maintain spatial pattern Plot footprint size made larger difference than anticipated

Strengths and limitations of GNN imputation Advantages: Recaptures most of variation in plot data Maintains multi-attribute covariance at a location Analytical flexibility: detailed vegetation data for post- mapping classification, analysis, and modeling Ability to map variability and assess sampling sufficiency Where strong gradients exist, can use other spatial environmental data to describe pattern Limitations: Map values are constrained to those at sampled locations Natural variability reduces local-scale prediction accuracy