Impact Factor 2.749 | CiteScore 4.4
More on impact ›

Original Research ARTICLE

Front. Environ. Sci. | doi: 10.3389/fenvs.2021.628214

Quantifying Uncertainty in Land Use/Land Cover Classification Accuracy—a Stochastic Simulation Approach Provisionally accepted The final, formatted version of the article will be published soon. Notify me

 Ke-Seng Cheng1*, Jia-Yi Ling1,  Teng-Wei Lin1, Yin-Ting Liu1, You-Chen Shen1 and Yasuyuki Kono2
  • 1National Taiwan University, Taiwan
  • 2Kyoto University, Japan

In numerous applications of land use/land cover (LULC) classification, the classification rules are determined using a set of training data; thus, the results are inherently affected by uncertainty in the selection of those data. Few studies have assessed the accuracy of LULC classification with this consideration. In this paper, we provide a general expression of various measures of classification accuracy with regard to the sample dataset for classifier training and the sample dataset for the evaluation of the classification results. We conducted stochastic simulations for LULC classification of a two-feature two-class case and a three-feature four-class case to show the uncertainties in the training sample and reference sample confusion matrices. A bootstrap simulation approach for establishing the 95% confidence interval of the classifier global accuracy was proposed and validated through rigorous stochastic simulation. Moreover, theoretical relationships between the producer accuracy, user accuracy, and overall accuracy were derived. The results demonstrate that the sample size of class-specific training data and the a priori probabilities of individual LULC classes must be jointly considered to ensure the correct determination of LULC classification accuracy.

Keywords: Stochastic simulation, bootstrap resampling, confidence interval, confusion matrix, accuracy assessment, Land-Use/Land-Cover (LULC)

Received: 11 Nov 2020; Accepted: 02 Feb 2021.

Copyright: © 2021 Cheng, Ling, Lin, Liu, Shen and Kono. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Prof. Ke-Seng Cheng, National Taiwan University, Taipei, Taiwan, rslab@ntu.edu.tw