1 2 Mau forest Estate Tea Cloud & shadow South Nandi Forest Reserve

Slides:



Advertisements
Similar presentations
Page 1 of 50 Optimization of Artificial Neural Networks in Remote Sensing Data Analysis Tiegeng Ren Dept. of Natural Resource Science in URI (401)
Advertisements

A Land Cover Map of Eurasia’s Boreal Ecosystems S. BARTALEV, A. S. BELWARD Institute for Environment and Sustainability, EC Joint Research Centre, Italy.
NDVI Anomaly, Kenya, January 2009 Vegetation Indices Enhancing green vegetation using mathematical equations and transformations.
VEGETATION MAPPING FOR LANDFIRE National Implementation.
VIIRS Cloud Phase Validation. The VIIRS cloud phase algorithm was validated using a 24-hour period on November 10, Validation was performed using.
Vegetation and Population Density in Urban and Suburban Areas in the U.S.A. Francesca Pozzi Center for International Earth Science Information Network.
Land Use Change and Effects on Water Quality in the Lake Tahoe Basin: Applications of GIS Christian Raumann Research and Technology Team USGS Western Geographic.
Harvard University Graduate School of Design Exploring 30 Years of Land Use Change: Landsat Time Series Images and Simple Image Classification Techniques.
Lecture 13: Spectral Mixture Analysis Wednesday 16 February 2011 Reading Ch 7.7 – 7.12 Smith et al. Vegetation in deserts (class website)
Lecture 13: Spectral Mixture Analysis Tuesday 16 February 2010 Last lecture: framework for viewing image processing and details about some standard algorithms.
Use of Remote Sensing in Forestry Applications Murat Tunç Murat Tunç
Image Classification To automatically categorize all pixels in an image into land cover classes or themes.
More Remote Sensing Today- - announcements - Review of few concepts - Measurements from imagery - Satellites and Scanners.
Digital Imaging and Remote Sensing Laboratory Real-World Stepwise Spectral Unmixing Daniel Newland Dr. John Schott Digital Imaging and Remote Sensing Laboratory.
Remote Sensing Applications. Signatures – a unique identifier…
Module 2.1 Monitoring activity data for forests using remote sensing REDD+ training materials by GOFC-GOLD, Wageningen University, World Bank FCPF 1 Module.
Mobile Bay Water Quality Assessment Using NASA Spaceborne Data Products Jenny Q. Du Mississippi State University.
THE IMPACTS OF URBANIZATION ON SURFACE ALBEDO IN THE YANGTZE RIVER DELTA INTRODUCTION Mélanie Bourré 06/02/2011.
Chenghai Yang 1 John Goolsby 1 James Everitt 1 Qian Du 2 1 USDA-ARS, Weslaco, Texas 2 Mississippi State University Applying Spectral Unmixing and Support.
U.S. Department of the Interior U.S. Geological Survey Assessment of Conifer Health in Grand County, Colorado using Remotely Sensed Imagery Chris Cole.
Classification & Vegetation Indices
Introduction to Remote Sensing. Outline What is remote sensing? The electromagnetic spectrum (EMS) The four resolutions Image Classification Incorporation.
Digital Numbers The Remote Sensing world calls cell values are also called a digital number or DN. In most of the imagery we work with the DN represents.
Mapping lichen in a caribou habitat of Northern Quebec, Canada, using an enhancement-classification method and spectral mixture analysis J.Théau, D.R.
Chuvieco and Huete (2009): Fundamentals of Satellite Remote Sensing, Taylor and Francis Emilio Chuvieco and Alfredo Huete Fundamentals of Satellite Remote.
Image Classification Digital Image Processing Techniques Image Restoration Image Enhancement Image Classification Image Classification.
Fuzzy Entropy based feature selection for classification of hyperspectral data Mahesh Pal Department of Civil Engineering National Institute of Technology.
Karnieli: Introduction to Remote Sensing
Summer Session 09 August Tips for the Final Exam Make sure your answers clear, without convoluted language. Read questions carefully – are you answering.
Toward a Stable Real-Time Green Vegetation Fraction Le Jiang, Dan Tarpley, Felix Kogan, Wei Guo and Kenneth Mitchell JCSDA Science Workshop May 31 – June.
What is an image? What is an image and which image bands are “best” for visual interpretation?
Spectral classification of WorldView-2 multi-angle sequence Atlanta city-model derived from a WorldView-2 multi-sequence acquisition N. Longbotham, C.
Preliminary Results of Mapping Carbon at the Pixel Level in East Kalimantan GCF Kaltim Project Global Observatory for Ecosystem Services, Department of.
Cloud Mask: Results, Frequency, Bit Mapping, and Validation UW Cloud Mask Working Group.
CHAPTER 10 Principal Components BAND TRANSFORMATIONS A. Dermanis.
DEMs Download from Seamless Server Project Mosaic Calculate Slope Create a DEM (ArcGIS)
Test of forest classification over Bavaria (Germany) using a SPOT-VGT pixel mosaic Erwann FILLOL, Pamela KENNEDY, Sten FOLVING.
earthobs.nr.no Retraining maximum likelihood classifiers using a low-rank model Arnt-Børre Salberg Norwegian Computing Center Oslo, Norway IGARSS.
Canopy Forest Cover Change in Fanjingshan National Nature Reserve: “What measurable environmental changes have taken place after implementing payment for.
Satellite Band Combinations.. Bands 3, 2, 1 in red, green, blue. This is considered the natural colour composition. It is usually used primarily for display.
1 GOES-R AWG Product Validation Tool Development Snow Cover Team Thomas Painter UCAR Andrew Rost, Kelley Eicher, Chris Bovitz NOHRSC.
Satellite Derived Bathymetry GEBCO Cookbook
U.S. Department of the Interior U.S. Geological Survey Automatic Generation of Parameter Inputs and Visualization of Model Outputs for AGNPS using GIS.
GLC 2000 Workshop March 2003 Land cover map of southern hemisphere Africa using SPOT-4 VEGETATION data Ana Cabral 1, Maria J.P. de Vasconcelos 1,2,
1 GOES-R AWG Product Validation Tool Development Snow Cover Team Thomas Painter UCAR Andrew Rost, Kelley Eicher, Chris Bovitz NOHRSC.
Cropland mapping in South America
Cropland Extent Mapping in South America Global Food Security - Support Analysis m Chandra Giri, Ying Zhong January 19 th, 2016.
Landsat Satellite Data. 1 LSOS (1-ha) 9 Intensive Study Areas (1km x 1km) 3 Meso-cell Study Areas (25km x 25km) 1 Small Regional Study Area (1.5 o x 2.5.
By:Nick Severson Brian Trick Land Cover Change of Twin Cities Metro and Scott County ______________________________FR Fall 2013.
Date of download: 6/3/2016 Copyright © 2016 SPIE. All rights reserved. A framework for improved pedestrian detection performance through blind image distortion.
Kate E. Richardson 1 with Ramesh Sivanpillai 2 1.Department of Ecosystem Science and Management 2.Department of Botany University of Wyoming.
Using vegetation indices (NDVI) to study vegetation
Great Barrier Reef Report Card 2015 – Burdekin: Ground Cover
Factsheet # 12 Understanding multiscale dynamics of landscape change through the application of remote sensing & GIS Land use/land cover (LULC) from high-resolution.
Built-up Extraction from RISAT Data Using Segmentation Approach
Unsupervised Classification in Imagine
HIERARCHICAL CLASSIFICATION OF DIFFERENT CROPS USING
Image Classification FE423 - March 2, 2000.
Objectives Using a time series of data from radar sensors to detect and measure forest changes Combining different types of data, including: Multi polarisations.
Monitoring Surface Area Change in Iowa's Water Bodies
Evaluating Land-Use Classification Methodology Using Landsat Imagery
Digital Numbers The Remote Sensing world calls cell values are also called a digital number or DN. In most of the imagery we work with the DN represents.
Paulo Gonçalves1 Hugo Carrão2 André Pinheiro2 Mário Caetano2
Lecture 13: Spectral Mixture Analysis
An Image Classification of Khartoum, Sudan
Image Information Extraction
Igor Appel Alexander Kokhanovsky
Remote Sensing Landscape Changes Before and After King Fire 2014
Image Classification of the Upper South Fork Eel River Watershed
Calculating land use change in west linn from
Presentation transcript:

1 2 Mau forest Estate Tea Cloud & shadow South Nandi Forest Reserve Wetlands Lake Victoria Kisumu City Figure 1. Extent of forest cover in the Nyando River Basin ~ Nov. 1989. Top image shows Landsat 5 composite (Band 7 = red, Band 4 = green, Band 2= blue). Bottom image shows estimated forest cover fraction based on partial spectral unmixing and the Nyando Basin Boundary. Also shown are 2 proposed focal areas of the project (red). Methods: Forest cover has a very distinctive signature in the Landsat 5 Band 2,4,7 spectral range, and particularly “closed broadleaf evergreen” forest canopies are easily distinguished from non-forest cover types upon visual inspection (see examples top panel). Image pixel signatures from a wide range of visually identified forest and non-forest land cover types were extracted and posted to a database for analysis. The separability of different forest/non-forest types was tested statistically using linear discriminant analysis. Based on a 50% hold-out validation sample of 492 visually classified pixels, 98.7% were correctly classified as “forest”, and 97.5% were correctly classified as “non-forest”. Incorrectly classified pixels in the validation set were subsequently screened from further analyses. Using the screened validation dataset, signature files were then created in the ENVI® image processing system (see www.rsinc.com), and the “Matched-Filtering Algorithm” was used to estimate the fraction of forest cover in each 28.5 ´ 28.5 m pixel in the image (results shown in bottom panel). Tinderet Forest “Bare” soil 2 1