Evaluation of Three Different Machine Learning Methods for Object-Based Artificial Terrace Mapping - A Case Study of the Loess Plateau, China
Evaluation of Three Different Machine Learning Methods for Object-Based Artificial Terrace Mapping - A Case Study of the Loess Plateau, China
复制标题
基于对象的人工梯田制图三种不同机器学习方法的评估——以中国黄土高原为例
DOI：
10.3390/rs13051021
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Fayuan Li
中科院分区：
文献类型：
--
作者：
Hu Ding;Jiaming Na;Shangjing Jiang;Jie Zhu;Kai Liu;Yingchun Fu;Fayuan Li
人工梯田对农业生产和水土保持具有重要意义。人工梯田的自动高精度测绘是监测和相关研究的基础。以往的研究基于高分辨率数字高程模型(DEM)或影像实现了人工梯田制图。由于上下文信息对梯田制图的重要性，基于对象的图像分析(OBIA)和机器学习(ML)技术得到了广泛的应用。然而，选择合适的分类器对于梯田制图任务至关重要。在这项研究中，测试了使用OBIA和ML进行梯田制图的集成框架的性能。以位于黄土高原的纸坊沟流域中国为研究区域。首先，对图像进行优化分割。然后，从DEM和影像中提取特征，并分析特征之间的相关性并进行分类排序。最后，将三种不同的最大似然分类器，即极端梯度Boost分类器(XGBoost)、随机森林分类器(RF)和k近邻分类器(KNN)用于梯田映射。与地面实地调查结果的对比表明，随机森林的总体准确率为95.60%，其次是XGBoost和KNN，分别为94.16%和92.33%。讨论了类不平衡和特征选择的影响。这项工作为绘制人工梯田图提供了一个可信的框架。
Artificial terraces are of great importance for agricultural production and soil and water conservation. Automatic high-accuracy mapping of artificial terraces is the basis of monitoring and related studies. Previous research achieved artificial terrace mapping based on high-resolution digital elevation models (DEMs) or imagery. As a result of the importance of the contextual information for terrace mapping, object-based image analysis (OBIA) combined with machine learning (ML) technologies are widely used. However, the selection of an appropriate classifier is of great importance for the terrace mapping task. In this study, the performance of an integrated framework using OBIA and ML for terrace mapping was tested. A catchment, Zhifanggou, in the Loess Plateau, China, was used as the study area. First, optimized image segmentation was conducted. Then, features from the DEMs and imagery were extracted, and the correlations between the features were analyzed and ranked for classification. Finally, three different commonly-used ML classifiers, namely, extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor (KNN), were used for terrace mapping. The comparison with the ground truth, as delineated by field survey, indicated that random forest performed best, with a 95.60% overall accuracy (followed by 94.16% and 92.33% for XGBoost and KNN, respectively). The influence of class imbalance and feature selection is discussed. This work provides a credible framework for mapping artificial terraces.
登录
查看更多内容
用于从开源图像和数字高程模型导出梯田山脊的等高线方向检测
影响因子：
3.9
作者：
Dai Wen;Hu Guanghui;Huang Nan;Zhang Peng;Yang Xin;Tang Guoan
通讯作者：
Tang Guoan
西河地区坡耕地等级分类识别
影响因子：
3.4
作者：
Li, Y.1, 2;Gong, Jianhua1, 2;Wang, Dongchuan3;An, Leping4;Li, Rong1
通讯作者：
Li, Rong1
影响因子：
1.7
作者：
G. Rota
通讯作者：
G. Rota
超高分辨率无人机图像的基于地理对象的图像分析中的训练集大小、规模和特征
DOI：
10.1016/j.isprsjprs.2014.12.026
发表时间：
2015-04
影响因子：
12.7
作者：
Ma Lei;Cheng Liang;Li Manchun;Liu Yongxue;Ma Xiaoxue
通讯作者：
Ma Xiaoxue
DOI：
10.3390/molecules21080983
发表时间：
2016-07-28
期刊：
Molecules (Basel, Switzerland)
影响因子：
--
作者：
Babajide Mustapha I;Saeed F
通讯作者：
Saeed F