Comparing the Performance of Machine Learning Models for Identifying Gully Landforms-A Case Study of a Typical Watershed on the Chinese Loess Plateau

FAN Tiancheng; WANG Zhenliang; LI Yunfei; JIA Yunfei; YUAN Ke; ZHAO Jianlin

doi:10.13870/j.cnki.stbcxb.2023.04.026

您当前的位置：

首页 >

文章列表页 >

Comparing the Performance of Machine Learning Models for Identifying Gully Landforms-A Case Study of a Typical Watershed on the Chinese Loess Plateau

更新时间：2025-03-12

- Comparing the Performance of Machine Learning Models for Identifying Gully Landforms-A Case Study of a Typical Watershed on the Chinese Loess Plateau
- Vol. 37, Issue 4, Pages: 205-213(2023)
- 作者机构：
  
  长安大学地质工程与测绘学院,西安,710054
- 作者简介：
- 基金信息：
- DOI：10.13870/j.cnki.stbcxb.2023.04.026
  CLC： P208
- Published：2023
- 稿件说明：
移动端阅览
FAN Tiancheng, WANG Zhenliang, LI Yunfei, et al. Comparing the Performance of Machine Learning Models for Identifying Gully Landforms-A Case Study of a Typical Watershed on the Chinese Loess Plateau[J]. 2023, 37(4): 205-213.
DOI：

FAN Tiancheng, WANG Zhenliang, LI Yunfei, et al. Comparing the Performance of Machine Learning Models for Identifying Gully Landforms-A Case Study of a Typical Watershed on the Chinese Loess Plateau[J]. 2023, 37(4): 205-213. DOI： 10.13870/j.cnki.stbcxb.2023.04.026.

摘要

探索沟谷地貌空间分布与环境控制特征之间的联系并构建沟谷地貌准确提取模型

对大尺度范围沟谷提取具有重要意义。基于人工提取黄土高原典型流域沟谷地貌样本

结合不同时期的Landsat8 OLI影像数据和DEM数据

建立随机森林模型确定黄土高原沟谷地貌提取最佳影像时期和最佳组合特征

基于最优模型参数

对比其与支持向量机和人工神经网络沟谷提取模型效果

验证模型泛化能力。结果表明:(1)黄土高原沟谷提取的最佳影像时期为12月

最佳组合特征集为Red、Blue、H、SWIR1、PNT、Coastal、GLCM4和NIR;(2)3种方法提取测试区域的沟谷空间分布一致

从定性和定量角度进行比较

随机森林模型提取效果最好

验证样区平均总体精度为80.48％

相较于支持向量机模型和人工神经网络模型分别提高4.00和8.63个百分比;(3)测试区域中

沟谷地貌面积约占总面积的56.91％

且呈现西北至东南方向逐渐集中的特点。研究表明随机森林模型在黄土高原地区高精度沟谷地貌识别研究中综合表现最佳

可大范围推广。

Abstract

Exploring the relationship between spatial distribution and environmental control characters of gully landforms and building accurate extraction model are of great significance for gully landforms extraction in large scale. Based on the artificial extraction of gully landform samples combing with Landsat8 OLI image data with different periods of and DEM data of a typical watershed on the Chinese loess plateau

the random forest model was established to determine the best period for gully landforms extraction and the best combination of gullying features. Then

combined with the optimal model parameters

results of random forest were compared with support vector machine and artificial neural network model to validate the model generalization ability. Our results showed that: (1) The best image period for gully extraction was in December

and the best combination feature set was Red

Blue

elevation (H)

SWIR1

positive and negative terrain (PNT)

Coastal

texture (GLCM4) and NIR; (2) The distribution of gully landforms in the testing area extracted by three methods had consistently spatial pattern. Based on qualitatively and quantitatively modelling performance

the random forest model presented the best extracting performance

with the average overall accuracy of 80.48%

which was higher by 4.00 percentage and 8.63 percentage compared with the support vector machine model and the artificial neural network model

respectively; (3) The gully landforms accounted for 56.91% of the total testing area and the distribution of gullies in testing area was gradually concentrated from northwest to southeast. The results show that the random forest model has the best comprehensive performance in the study of high-precision gully landforms identification on the Chinese Loess Plateau

and can be widely extended.

关键词

Keywords

references

Zhao J L, Vanmaercke M, Chen L Q, et al. Vegetation cover and topography rather than human disturbance control gully density and sediment production on the Chinese Loess Plateau[J].Geomorphology,2016,274(1):92-105.

Zabihi M, Mirchooli F, Motevalli A, et al. Spatial modelling of gully erosion in Mazandaran Province,northern Iran[J].Catena,2018,161:1-13.

Yang X, Li M, Na J M, et al. Gully boundary extraction based on multidirectional hill-shading from high-resolution DEMs[J].Transactions in GIS,2017,21(6):1204-1216.

王轲,王琤,张青峰,等.地形开度和差值图像阈值分割原理相结合的黄土高原沟沿线提取法[J].测绘学报,2015,44(1):67-75.

柳潇,吕新彪,吴春明,等.面向高空间分辨率遥感影像的山区地形校正方法[J].地球科学,2020,45(2):645-662.

Dai W, Hu G H, Yang X, et al. Identifying ephemeral gullies from high-resolution images and DEMs using flow-directional detection[J].Journal of Mountain Science,2020,17(12):3024-3038.

Yang X, Dai W, Tang G A, et al. Deriving ephemeral gullies from VHR image in Loess Hilly Areas through directional edge detection[J].ISPRS International Journal of Geo-Information,2017,6(11):e371.

陈靖涛,史明昌,罗志东,等.基于双向地形阴影法的黄土侵蚀沟自动提取技术[J].农业工程学报,2022,38(7):127-135.

李乐,马巍,勾蒙蒙,等.三峡库区典型流域硝态氮输出特征及归因分析[J].水土保持学报,2022,36(4):74-84.

王少丽,臧敏,王亚娟,等.年径流系数变化特征及预测模型研究[J].水土保持学报,2020,34(5):56-60,67.

李柳阳,朱青,刘亚,等.基于气象因子的长三角地区农田站点土壤水分时间序列预测[J].水土保持学报,2021,35(2):131-137.

Vanmaercke M, Chen Y X, Haregeweyn N, et al. Predicting gully densities at sub-continental scales: A case study for the Horn of Africa[J].Earth Surface Processes and Landforms,2020,45(15):3763-3779.

Yang A N, Wang C M, Pang G W, et al. Gully Erosion susceptibility mapping in highly complex terrain using machine learning models[J].ISPRS International Journal of Geo-Information,2021,10(10):e680.

Ding H, Liu K, Chen X Z, et al. Optimized segmentation based on the weighted aggregation method for loess bank gully mapping[J].Remote Sensing,2020,12(5):e793.

Liu K, Ding H, Tang G A, et al. Large-scale mapping of gully-affected areas: An approach integrating Google Earth images and terrain skeleton information[J].Geomorphology,2018,314:13-26.

贾云飞,李云飞,范天程,等.基于长时间序列NDVI的黄土高原延河流域及其沟壑区植被覆盖变化分析[J].水土保持研究,2022,29(4):240-247.

呼媛,鲁克新,李鹏,等.延河流域骨干坝拦沙量反推与未来可拦沙年限预测[J].水土保持学报,2021,35(3):38-45.

范天程,贾云飞,李云飞,等.基于遥感影像与逻辑回归模型的延河流域沟壑分布概率预测[J].水土保持研究,2022,29(4):316-321.

夏子书,白一茹,王幼奇,等.基于GIS和随机森林算法的宁东土壤饱和导水率分布与预测[J].水土保持学报,2021,35(1):285-293.

王飞,杨胜天,丁建丽,等.环境敏感变量优选及机器学习算法预测绿洲土壤盐分[J].农业工程学报,2018,34(22):102-110.

陈黔,李晓松,修晓敏,等.基于Google Earth Engine与机器学习的大尺度30 m分辨率沙地灌木覆盖度估算[J].生态学报,2019,39(11):4056-4069.

杨剑锋,乔佩蕊,李永梅,等.机器学习分类问题及算法研究综述[J].统计与决策,2019,35(6):36-40.

陈强.机器学习及R应用[M].北京:高等教育出版社,2020:314-315.

张鹏,马庆勋,吕杰,等.机器学习算法在森林地上生物量估算中的应用[J].测绘通报,2021(12):28-32.

杨丽萍,侯成磊,苏志强,等.基于机器学习和全极化雷达数据的干旱区土壤湿度反演[J].农业工程学报,2021,37(13):74-82.

李辉东,关德新,袁凤辉,等.BP人工神经网络模拟杨树林冠蒸腾[J].生态学报,2015,35(12):4137-4145.

侯蒙京,殷建鹏,葛静,等.基于随机森林的高寒湿地地区土地覆盖遥感分类方法[J].农业机械学报,2020,51(7):220-227.

Chen Y X, Jiao J Y, Wei Y H, et al. Accuracy assessment of the planar morphology of valley bank gullies extracted with high resolution remote sensing imagery on the Loess Plateau, China[J].International Journal of Environmental Research and Public Health,2019,16(3):e369.

李斌兵,黄磊.基于面向对象技术的黄土丘陵沟壑区切沟遥感提取方法研究[J].水土保持研究,2013,20(3):115-119,124.

Zhou Y, Tang G A, Yang X, et al. Positive and negative terrains on northern Shaanxi Loess Plateau[J].Journal of Geographical Sciences,2010,20(1):64-76.

Views

1086

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Inversion of Black Soil Layer Thickness Based on Multi-Temporal High-Resolution Remote Sensing Data and Machine Learning

Estimation of Soil Wind Erodibility in Farmland of Bashang Region in Hebei Based on Sentinel-2A Data

Correction of Satellite Precipitation Product Based on Machine Learning Models in Tarim River Basin

Construction of Seasonal Soil Salinity Inversion Models in Yellow River Irrigation Area of Ningxia Based on Multi-Source Remote Sensing

Related Author

LI Huapeng

ZHAO Tongtong

AN Chenyu

WANG Rende

CHANG Chunping

GUO Zhongling

LI Huiru

XUE Aoya

Related Institution

School of Geomatics and Prospecting Engineering， Jilin Jianzhu University

Northeast Institute of Geography and Agroecology， Chinese Academy of Sciences

School of Geographical Sciences， Hebei Normal University

Hebei Technology Innovation Center for Remote Sensing Identification of Environmental Change

Hebei Key Laboratory of Environmental Change and Ecological Construction

⁰