TY - JOUR
T1 - Model of Peatland Vegetation Species using HyMap Image and Machine Learning
AU - Dayuf Jusuf, Muhammad
AU - Danoedoro, Projo
AU - Muljo Sukojo, Bangun
AU - Hartono,
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
PY - 2017/12/20
Y1 - 2017/12/20
N2 - 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.
AB - 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.
KW - HyMap image
KW - Peatland species
KW - WANN hybrid algorithm model
UR - http://www.scopus.com/inward/record.url?scp=85039414557&partnerID=8YFLogxK
U2 - 10.1088/1755-1315/98/1/012050
DO - 10.1088/1755-1315/98/1/012050
M3 - Conference article
AN - SCOPUS:85039414557
SN - 1755-1307
VL - 98
JO - IOP Conference Series: Earth and Environmental Science
JF - IOP Conference Series: Earth and Environmental Science
IS - 1
M1 - 012050
T2 - 5th Geoinformation Science Symposium 2017, GSS 2017
Y2 - 27 September 2017 through 28 September 2017
ER -