Featured Apps

Algorithm Landcover in GEE

Algorithm of various landcover development.

Beirsdorf Smallholder Palm Oil Database

Comparison's Indicative HCS 2020 between WWF vs BC (v21Nov2021)

Comparison's Indicative HCS 2020 between WWF vs BC (v21Nov2021)

GEE V.2 Global Landcover WWF 08 May 2020 - ky

Various Landcover Detection Using Google Earth Engine The aim of this work is to develop an automatic land cover mapping classification scheme that covers the main commodities in WWF's scope of work including natural forests, rubber, palm oil and pulpwood. In the process of developing this land classification, WWF used a mapping classification scheme in taking samples which was also intended to build a satellite-based Landsat spectral value library that would be used in identifying various types of land cover. From several land cover sampling locations that have been verified by Landsat spectral value, then used to develop an algorithm that is run to produce pixel-based classification by decision tree method, the final result of the algorithm will be used to produce maps of various land cover globally based on a set of rules that have been developed. The sample regions to develop classification schemes cover 4 regions (Central Sumatra, East Kalimantan, Cambodia and Myanmar). Various land cover classes that have been mapped include: 1. Natural forest: Closed canopy natural forest ranging from high density to low density forest. 2. Mangrove forest: All type of mangrove (including Nypa) include in this class. 3. Palm oil plantation: All palm oil plantations both smallholders and large estate. 4. Pulpwood plantation: All pulpwood trees. 5. Rubber plantation: All rubber trees both smallholders and large estate. 6. Water: All types of water bodies. 7. Bare: Including urban, exposed-soil area, and sparse vegetation. 8. Other: All other remaining class will be classified into this class.

GEE WEKA version 4 (2 Dec 2020)

Comparation GEE WEKA Scripts V2 - V3 - V4 on Various Landcover Detection.

GEE WEKA version 5 (8 January 2021)

GEE WEKA version 5 (8 January 2021)

Hansen treecover loss vs Setiabudi 2020 forest cover map

Hansen 200-2020 TreeCover Loss compare with WWF Setiabudi Visual analyst 2020. https://k2yulianto.users.earthengine.app/view/hansen-treecover-loss-vs-setiabudi-2020-forest-cover-map

Algorithm of various landcover in GEE

Algorithm of various landcover development using Google Earth Engine.

Algorithm of various landcover in Google Earth Engine

KalSel 2020 Landcover

The automatic land cover mapping method uses the Landsat 8 remote sensing dataset available on the Google Earth Engine (Gorelick et al., 2017) with weka.classifiers.trees.J48 -C 0.25 -M 30 Algoritm.

Landcover BC & WWF algorithm 2020 comparison

Landcover BC & WWF algorithm 2020 comparison

March-Nov_2019_GEE_Algoritm_ky

Rubber GEE Algoritm Myanmar filter month March until Nov 2019

Risk's Map of Indicative HCV and HCS on Sumatera

Risk Maps of Indicative HCV and HCS on Sumatera

Rubber Distribution and Associated Deforestation with EUDR

Sumatera Indicative HCV HCS map

Indicative HCV area / HCS forest map for Sumatra

Sumatera Island Risk's Map of Indicative HCV and HCS v100621

Note to reviewers of indicative HCV-HCS mapping process WWF produced indicative HCV area / HCS forest maps for its upcoming Hamurni commodity supply chain assessment tool. We are compiling all the maps in an online GIS database as they become available. This document provide screenshots of some of them. We want to make sure that we followed the best possible procedure to make the maps based on the secondary data sets available to us. We would like to work with HCVRN and HCSA to check and if needed update our process. This document was extracted from our draft manual for the supply chain tool and provides some background on the intended purpose of the maps. It lists the origin of the secondary data and the process with which they were analyzed. Once verified, we would make maps available to companies and other potential users to assess supply chain risks. For further questions, please contact Kokok Yulianto <kyulianto@wwf.id>, Michael Stuewe <Michael.Stuewe@WWFUS.ORG>, and Yumiko Uryu <yumuryu@gmail.com>

Sumatera Island Risk's Map of Indicative HCV and HCS v210621

Map Version 210621 Note to reviewers of indicative HCV-HCS mapping process WWF produced indicative HCV area / HCS forest maps for its upcoming Hamurni commodity supply chain assessment tool. We are compiling all the maps in an online GIS database as they become available. This document provide screenshots of some of them. We want to make sure that we followed the best possible procedure to make the maps based on the secondary data sets available to us. We would like to work with HCVRN and HCSA to check and if needed update our process. This document was extracted from our draft manual for the supply chain tool and provides some background on the intended purpose of the maps. It lists the origin of the secondary data and the process with which they were analyzed. Once verified, we would make maps available to companies and other potential users to assess supply chain risks. For further questions, please contact Kokok Yulianto <kyulianto@wwf.id>, Michael Stuewe <Michael.Stuewe@WWFUS.ORG>, and Yumiko Uryu <yumuryu@gmail.com>

Sumatera Island Risk's Map of Indicative HCV and HCS v290621

Map Version 290621 Note to reviewers of indicative HCV-HCS mapping process WWF produced indicative HCV area / HCS forest maps for its upcoming Hamurni commodity supply chain assessment tool. We are compiling all the maps in an online GIS database as they become available. This document provide screenshots of some of them. We want to make sure that we followed the best possible procedure to make the maps based on the secondary data sets available to us. We would like to work with HCVRN and HCSA to check and if needed update our process. This document was extracted from our draft manual for the supply chain tool and provides some background on the intended purpose of the maps. It lists the origin of the secondary data and the process with which they were analyzed. Once verified, we would make maps available to companies and other potential users to assess supply chain risks. For further questions, please contact Kokok Yulianto <kyulianto@wwf.id>, Michael Stuewe <Michael.Stuewe@WWFUS.ORG>, and Yumiko Uryu <yumuryu@gmail.com>

TreeCover Loss in ABT RE since 2000-2021

Visual vs Machine Learning Algorithm

Comparable between Landcover generated using visual analyst vs automatic landcover detection using Machine Learning Algorithm Source imagery : Landsat 8 OLI free cloud composite range 2019-2020

WWF algorithm VS Global Palm Oil algorithm

WWF Forest week Draft final v1

WWF Forest Week 8 March 2022, Sumatera GIS

WWF Landcover Algoritm v5 jan 2021

Development of Landcover automatic detection Algorithm (version 5 Jan 2021).

WWF landcover machine learning Algoritms app march 2021

WWF landcover machine learning Algoritms app march 2021