Model of Peatland Vegetation Species using HyMap Image and Machine Learning

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...

Full description

Saved in:
Bibliographic Details
Published in:IOP conference series. Earth and environmental science 2017-12, Vol.98 (1), p.12050
Main Authors: Dayuf Jusuf, Muhammad, Danoedoro, Projo, Muljo Sukojo, Bangun, Hartono
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Biodiversity
Climate change
Environmental restoration
Forecasting
Geographical distribution
HyMap image
Information systems
Learning algorithms
Learning theory
Machine learning
Natural resources
Neural networks
Peatland species
Peatlands
Position (location)
Shorea
Species
Training
Vegetation
WANN hybrid algorithm model
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1755-1307
1755-1315
DOI:10.1088/1755-1315/98/1/012050