Model of Peatland Vegetation Species using HyMap Image and Machine Learning

5th Geoinformation Science Symposium 2017

地球科学;计算机科学

Dayuf Jusuf, Muhammad^1 ; Danoedoro, Projo^2 ; Muljo Sukojo, Bangun^3 ; Hartono^2

PhD Stud. Remote Sensing, Fakultas Geografi, Universitas Gadjah Mada, Yogyakarta, Indonesia^1

Fakultas Geografi, Universitas Gadjah Mada, Yogyakarta, Indonesia^2

Fakultas Teknik Geomatika, Institut Teknologi Sepuluh Nopember, ITS, Surabaya, Indonesia^3

关键词: Analysis of alternatives;    Climate change projections;    Ecosystem restoration;    Geo-spatial information systems;    Hybrid algorithms;    HyMap image;    Peatland;    Reference collections;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/98/1/012050/pdf
DOI  :  10.1088/1755-1315/98/1/012050

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

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.