.png){kind=icon}
返回
Mapping imbalanced soil classes using Markov chain random fields models treated with data resampling technique
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compag.2019.03.006.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Class imbalance is a problem in spatial predictive models; it occurs when classes with a large number of observations dominate the prediction and classes with much less number of observations are not predicted at all. It is a crucial topic as imbalanced distribution of soil classes occurs naturally. In this study, we address this problem using Markov chain random field modeling combined with a data resampling technique, i.e., random over sampling. The study area is about 12,000 ha with imbalanced distribution of eight soil great groups located in the northwest of Iran. Four algorithms were used to interpolate class observations, including fixed-path and random-path Markov chain random fields (FPth and RPth, respectively), indicator kriging simulation (IKS) and Markovian-type categorical simulation (MCS). All of the models provide prediction and simulation as outputs. The random oversampling technique was applied to the minority soil classes prior to modeling. Using original data that have imbalanced classes for mapping resulted in loss of the minority classes and relatively low Kappa agreement values for some models. Data oversampling increased overall accuracy and Kappa coefficient for FPth and RPth models. In addition, it led to the maintenance of one or two minority classes in the resulting maps. Overall, RPth model showed the highest overall accuracy and Kappa coefficient both in prediction (overall = 50%, K = 0.33) and simulation (overall = 52%, K = 0.36) outputs after data oversampling. Markov chain models combined with data oversampling technique can be used for mapping imbalanced soil classes.
Keyword:
Class imbalance problem
Data oversampling
Imbalanced datasets
Spatial simulation
Digital soil mapping
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
1.0W
被引数:
4.8W
机构
引用论文
Saline with benzyl alcohol as intradermal anesthesia for intravenous line placement in children
PREAI
分享收藏Arsenic removal from aqueous solutions by adsorption using novel MIL-53(Fe) as a highly efficient adsorbent使用新型MIL-53(Fe) 作为高效吸附剂通过吸附从水溶液中去除砷.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏
查看更多内容