Accuracy of Land Cover Products Why is it important and what does it all mean Note: The figures and tables in this presentation were derived from work.

Slides:



Advertisements
Similar presentations
Lecture 7 Forestry 3218 Forest Mensuration II Lecture 7 Forest Inventories Avery and Burkhart Chapter 9.
Advertisements

Major Operations of Digital Image Processing (DIP) Image Quality Assessment Radiometric Correction Geometric Correction Image Classification Introduction.
PRESENTATION ON “ Processing Of Satellite Image Using Dip ” by B a n d a s r e e n i v a s Assistant Professor Department of Electronics & Communication.
Accuracy Assessment of Thematic Maps
USGS-NPS Vegetation Mapping Program Wind Cave National Park, South Dakota Dan Cogan ACS Government Solutions Group Hollis Marriott Wyoming Natural Heritage.
VALIDATION OF REMOTE SENSING CLASSIFICATIONS: a case of Balans classification Markus Törmä.
SEReGAP Land Cover Mapping Summary and Results Southwest Regional GAP Project Arizona, Colorado, Nevada, New Mexico, Utah US-IALE 2004, Las Vegas, Nevada:
Geog 458: Map Sources and Errors Uncertainty January 23, 2006.
Accuracy Assessment Chapter 14. Significance Accuracy of information is surprisingly difficult to address We may define accuracy, in a working sense,
Lecture 14: Classification Thursday 18 February 2010 Reading: Ch – 7.19 Last lecture: Spectral Mixture Analysis.
PROBABILITY AND SAMPLES: THE DISTRIBUTION OF SAMPLE MEANS.
AA_Vis_1. Using the software “MultiSpec,” students follow protocols to prepare a “clustered” image of their GLOBE Study Site.
ML ALGORITHMS. Algorithm Types Classification (supervised) Given -> A set of classified examples “instances” Produce -> A way of classifying new examples.
Statistical Treatment of Data Significant Figures : number of digits know with certainty + the first in doubt. Rounding off: use the same number of significant.
Lineage February 13, 2006 Geog 458: Map Sources and Errors.
February 15, 2006 Geog 458: Map Sources and Errors
Global Land Cover: Approaches to Validation Alan Strahler GLC2000 Meeting JRC Ispra 3/02.
Validation of the GLC2000 products Philippe Mayaux.
POPULATION: Population is an aggregate of objaects enimate or inenimate understudy. The population may be finite or infinite. SAMPLE: A finite subset.
EG1106: GI: a primer Field & Survey data collection 19 th November 2004.
Accuracy Assessment. 2 Because it is not practical to test every pixel in the classification image, a representative sample of reference points in the.
Chapter 9 Accuracy assessment in remotely sensed categorical information 遥感类别信息精度评估 Jingxiong ZHANG 张景雄 Chapter 9 Accuracy assessment in remotely sensed.
Methods of Validating Maps of Deforestation and Selective Logging Carlos Souza Jr. Instituto do Homem e Meio Ambiente da Amazônia—Imazon.
Image Classification and its Applications
Centre for Geo-information Fieldwork: the role of validation in geo- information science RS&GIS Integration Course (GRS ) Lammert Kooistra Contact:
Co-authors: Maryam Altaf & Intikhab Ulfat
earthobs.nr.no Land cover classification of cloud- and snow-contaminated multi-temporal high-resolution satellite images Arnt-Børre Salberg and.
Classification & Vegetation Indices
Chapter Nine Copyright © 2006 McGraw-Hill/Irwin Sampling: Theory, Designs and Issues in Marketing Research.
GIS Data Quality.
Mapping “what?” Instead of “where?”. Two types of geographic data: Horizontal location Vertical location Vegetation types Soil types Land cover Number.
Orthorectification using
Lecture 3 Forestry 3218 Avery and Burkhart, Chapter 3 Shiver and Borders, Chapter 2 Forest Mensuration II Lecture 3 Elementary Sampling Methods: Selective,
Data Sources Sources, integration, quality, error, uncertainty.
Image Classification Digital Image Processing Techniques Image Restoration Image Enhancement Image Classification Image Classification.
Image Classification 영상분류
Use of Aerial Videography in Habitat Survey and Computers as Observers Leonard Pearlstine University of Florida.
Accuracy Assessment Having produced a map with classification is only 50% of the work, we need to quantify how good the map is. This step is called the.
A Forest Cover Change Study Gone Bad Lessons Learned(?) Measuring Changes in Forest Cover in Madagascar Ned Horning Center for Biodiversity and Conservation.
OPENING QUESTIONS 1.What key concepts and symbols are pertinent to sampling? 2.How are the sampling distribution, statistical inference, and standard.
1 Joint Research Centre (JRC) Using remote sensing for crop and land cover area estimation
Wetlands Investigation Utilizing GIS and Remote Sensing Technology for Lucas County, Ohio: a hybrid analysis. Nathan Torbick Spring 2003 Update on current.
Digital Image Processing
Chuvieco and Huete (2009): Fundamentals of Satellite Remote Sensing, Taylor and Francis Emilio Chuvieco and Alfredo Huete Fundamentals of Satellite Remote.
Remote Sensing Classification Accuracy
Error & Uncertainty: II CE / ENVE 424/524. Handling Error Methods for measuring and visualizing error and uncertainty vary for nominal/ordinal and interval/ratio.

BOT / GEOG / GEOL 4111 / Field data collection Visiting and characterizing representative sites Used for classification (training data), information.
Citation: Moskal., L. M. and D. M. Styers, Land use/land cover (LULC) from high-resolution near infrared aerial imagery: costs and applications.
Environmental Modeling Validating GIS Models. 1. A Habitat Model Issues: ► Mapping Florida Scrub Jay habitat in the Kennedy Space Center in the Kennedy.
Reference data & Accuracy Assessment Dr. Russ Congalton Kamini Yadav.
Housekeeping –5 sets of aerial photo stereo pairs on reserve at SLC under FOR 420/520 –June 1993 photography.
Accuracy Assessment Accuracy Assessment Error Matrix Sampling Method
Accuracy Assessment of Thematic Maps THEMATIC ACCURACY.
Effect of Sun Incidence Angle on Classifying Water Bodies in Landsat Images Ina R. Goodman, Dr. Ramesh Sivanpillai Department of Botany WyomingView.
26. Classification Accuracy Assessment
Distortions in imagery:
ERT247 GEOMATICS ENGINEERING
26. Classification Accuracy Assessment
GEOGRAPHICAL INFORMATION SYSTEM
Accuracy Assessment of Thematic Maps
Incorporating Ancillary Data for Classification
Evaluating Land-Use Classification Methodology Using Landsat Imagery
Statistical surfaces: DEM’s
The GISCO task force “Remote Sensing for Statistics”
Outline Announcement Texture modeling - continued Some remarks
REMOTE SENSING Multispectral Image Classification
REMOTE SENSING Multispectral Image Classification
Housekeeping 5 sets of aerial photo stereo pairs on reserve at SLC under FOR 420/520 June 1993 photography.
network of simple neuron-like computing elements
Presentation transcript:

Accuracy of Land Cover Products Why is it important and what does it all mean Note: The figures and tables in this presentation were derived from work originally prepared by Ross Nelson – Laboratory of Terrestrial Physics, NASA Goddard Space Flight Center

Overview Classified maps are not a perfect representation of reality Classified maps are not a perfect representation of reality Accuracy statistics provide objective information about the quality of the land cover classification Accuracy statistics provide objective information about the quality of the land cover classification Accuracy statistics address overall quality and per-class quality Accuracy statistics address overall quality and per-class quality Accuracy assessment can be costly Accuracy assessment can be costly Accuracy assessment is often dropped from a project because of cost or time limitations Accuracy assessment is often dropped from a project because of cost or time limitations

Types of errors Position error Position error Often due to misregistration between the base information and the area being mapped Often due to misregistration between the base information and the area being mapped Can be difficult to notice unless compared to accurate base data Can be difficult to notice unless compared to accurate base data Thematic error Thematic error Due to misidentification of individual features Due to misidentification of individual features Usually the focus of accuracy statistics Usually the focus of accuracy statistics Accuracy assessment sampling often skewed toward detecting thematic error Accuracy assessment sampling often skewed toward detecting thematic error Accuracy assessment sampling design usually allows for “reasonable” position errors by assuring sample points are not close to a class edge Accuracy assessment sampling design usually allows for “reasonable” position errors by assuring sample points are not close to a class edge

Steps for assessing accuracy Sample design Sample design Collection of validation data Collection of validation data Compiling validation data Compiling validation data Analysis Analysis

Sample design Sampling design attempts to minimize bias Sampling design attempts to minimize bias The following decisions must be made: The following decisions must be made: Number of samples Number of samples How will the samples be distributed How will the samples be distributed How will a sample area be defined (point, area) How will a sample area be defined (point, area) How will sampling take place (field, aerial photos) How will sampling take place (field, aerial photos) In many cases adjustments to the “pure” sampling design must be made to accommodate practical realities such as access to sampling points. In many cases adjustments to the “pure” sampling design must be made to accommodate practical realities such as access to sampling points. Sample data must be independent of training data Sample data must be independent of training data Many sampling designs are influenced by the amount of money available and not “pure” statistical theory Many sampling designs are influenced by the amount of money available and not “pure” statistical theory

Collection of validation data Accurate locality (i.e., latitude/longitude, UTM coordinates) data should be associated with each sampling point Accurate locality (i.e., latitude/longitude, UTM coordinates) data should be associated with each sampling point Often useful if geo-coded photographs are acquired in the field Often useful if geo-coded photographs are acquired in the field Information should be collected that is relevant to the map being assessed Information should be collected that is relevant to the map being assessed Ancillary data such as aerial photography can be used in place of data collected in the field if the mapped classes can be accurately identified Ancillary data such as aerial photography can be used in place of data collected in the field if the mapped classes can be accurately identified

Compiling validation data If photos are used to record land cover type they must be acquired in the same time frame as the image used to create a map If photos are used to record land cover type they must be acquired in the same time frame as the image used to create a map For each sampling point the classification value (i.e., land cover type) as determined in the field must be recorded For each sampling point the classification value (i.e., land cover type) as determined in the field must be recorded The classification values from the validation data (reference data) and the classified map should be tallied in a contingency table to facilitate analysis The classification values from the validation data (reference data) and the classified map should be tallied in a contingency table to facilitate analysis

Analysis Analysis is used to determine the accuracy of the map Analysis is used to determine the accuracy of the map Using simple formulas the data in a contingency table can be analyzed to determine a range of accuracy figures Using simple formulas the data in a contingency table can be analyzed to determine a range of accuracy figures Accuracy figures are often presented from the users perspective Accuracy figures are often presented from the users perspective If I select any water pixel on the classified map, what is the probability that I'll be standing in water when I visit that pixel location in the field? and from the producers perspective If I know that a particular area is water, what is the probability that the digital map will correctly identify that pixel as water?

Example of an error matrix showing pixel counts From Canada Centre for Remote Sensing, Natural Resources Canada, 11/21/2005 User's Accuracy: A map-based accuracy. User's accuracy (water) = (# of pixels correctly classified as water) / (total # of pixels classified as water) = 367/400 = 91.75% Producers accuracy: A reference-based accuracy. Producer accuracy (water) = (# of pixels correctly classified as water) / (# ground reference pixels in water) = 367/382 = 96%

Overall accuracy = (# pixels correctly classified) / (total # of pixels) = (90) / 100 = 90% Overall accuracy = (# pixels correctly classified) / (total # of pixels) = (90) / 100 = 90% Omission Error: Excluding a pixel that should have been included in the class (i.e., omission error = 1 - producers accuracy) Omission Error: Excluding a pixel that should have been included in the class (i.e., omission error = 1 - producers accuracy) Commission Error: Including a pixel in a class when it should have been excluded (i.e., commission error = 1 - user's accuracy. Commission Error: Including a pixel in a class when it should have been excluded (i.e., commission error = 1 - user's accuracy. Kappa coefficient: Measures the improvement of the classified map over a random class assignment Kappa coefficient: Measures the improvement of the classified map over a random class assignment Other accuracy terms

Another example

Typical land cover accuracy figures Forest/nonforest, water/no water, soil/vegetated: accuracies in the high 90% Forest/nonforest, water/no water, soil/vegetated: accuracies in the high 90% Conifer/hardwood: 80-90% Conifer/hardwood: 80-90% Genus: 60-70% Genus: 60-70% Species: 40-60% Species: 40-60% Bottom line: The greater the detail (precision) the lower the per class accuracy Bottom line: The greater the detail (precision) the lower the per class accuracy Note: If including a Digital Elevation Model (DEM) in the classification, add 10% Note: If including a Digital Elevation Model (DEM) in the classification, add 10%