Model of Peatland Vegetation Species using HyMap Image and Machine Learning

Muhammad Dayuf Jusuf*, Projo Danoedoro, Bangun Muljo Sukojo, Hartono

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)

Abstract

Species Tumih / Parepat (Combretocarpus-rotundatus Mig. Dancer) family Anisophylleaceae and Meranti (Shorea Belangerang, Shorea Teysmanniana Dyer ex Brandis) family Dipterocarpaceae is a group of vegetation species distribution model. Species pioneer is predicted as an indicator of the succession of ecosystem restoration of tropical peatland characteristics and extremely fragile (unique) in the endemic hot spot of Sundaland. Climate change projections and conservation planning are hot topics of current discussion, analysis of alternative approaches and the development of combinations of species projection modelling algorithms through geospatial information systems technology. Approach model to find out the research problem of vegetation level based on the machine learning hybrid method, wavelet and artificial neural networks. Field data are used as a reference collection of natural resource field sample objects and biodiversity assessment. The testing and training ANN data set iterations times 28, achieve a performance value of 0.0867 MSE value is smaller than the ANN training data, above 50%, and spectral accuracy 82.1 %. Identify the location of the sample point position of the Tumih / Parepat vegetation species using HyMap Image is good enough, at least the modelling, design of the species distribution can reach the target in this study. The computation validation rate above 90% proves the calculation can be considered.

Original languageEnglish
Article number012050
JournalIOP Conference Series: Earth and Environmental Science
Volume98
Issue number1
DOIs
Publication statusPublished - 20 Dec 2017
Event5th Geoinformation Science Symposium 2017, GSS 2017 - Yogyakarta, Indonesia
Duration: 27 Sept 201728 Sept 2017

Keywords

  • HyMap image
  • Peatland species
  • WANN hybrid algorithm model

Fingerprint

Dive into the research topics of 'Model of Peatland Vegetation Species using HyMap Image and Machine Learning'. Together they form a unique fingerprint.

Cite this