Sugarcane Land Classification with Satellite Imagery using Logistic Regression Model

International Conference on Information Technology and Digital Applications

计算机科学

Henry, F.^1 ; Herwindiati, D.E.^2 ; Mulyono, S.^2 ; Hendryli, J.^2

Faculty of Information Technology, Tarumanagara University, Letjen S. Parman No. 1, Jakarta, Indonesia^1

Indonesian Agency for the Assessment and Application of Technology, Kawasan Puspitek, Serpong, Tangerang, Indonesia^2

关键词: Binary logistic regression;    Classification process;    Cohen's kappas;    Gradient descent algorithms;    Logistic Regression modeling;    Normalized difference vegetation index;    Regression model;    Time-series data;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/185/1/012024/pdf
DOI  :  10.1088/1757-899X/185/1/012024

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

This paper discusses the classification of sugarcane plantation area from Landsat-8 satellite imagery. The classification process uses binary logistic regression method with time series data of normalized difference vegetation index as input. The process is divided into two steps: training and classification. The purpose of training step is to identify the best parameter of the regression model using gradient descent algorithm. The best fit of the model can be utilized to classify sugarcane and non-sugarcane area. The experiment shows high accuracy and successfully maps the sugarcane plantation area which obtained best result of Cohen's Kappa value 0.7833 (strong) with 89.167% accuracy.