Gully erosion susceptibility maps and influence factor analysis in the Lhasa River Basin on the Tibetan Plateau, based on machine learning algorithms

冲沟侵蚀 腐蚀 高原(数学) 仰角(弹道) 水文学(农业) 流域 植被(病理学) 构造盆地 逻辑回归 环境科学 自然地理学 地质学 地貌学 地理 地图学 统计 岩土工程 几何学 数学分析 病理 医学 数学
作者
Jianjun Li,Yulan Chen,Juying Jiao,Yixian Chen,Tongde Chen,Chao Zhao,Li Wang,Tian‐Cui Shang,Qian Xu,Haolin Wang,Leichao Bai
出处
期刊:Catena [Elsevier]
卷期号:235: 107695-107695 被引量:1
标识
DOI:10.1016/j.catena.2023.107695
摘要

The environment of the Tibetan Plateau is under stress due to the warming climate and increased human activity, which also increases the risk of soil erosion. Gully erosion is one of the main environmental problems in the Tibetan Plateau. Taking Lhasa River Basin as a representative, investigating the spatial variation and influencing factors in this area will help to understand the current status and mechanism of gully erosion. However, gully erosion factor analysis has not been carried out at the regional scale. Therefore, three machine learning algorithms, including Random Forest (RF), Support Vector Machine, and Logistic Regression, were used to analyze 2224 samples and 18 influencing factors and detect the gully erosion susceptibility in the Lhasa River Basin. Seventy percent of the samples were used to train the model and rank the influencing factors by importance, and 30% were used to assess the prediction ability of the model. Approximately 15%–20% of the study area has a high or very high gully erosion susceptibility. The slopes of the lower Lhasa River and the Nyenchen Tanglha valleys were identified as areas with a high gully erosion susceptibility. The RF model exhibits the best performance, with area under the curve (AUC) values of 0.969 and 0.894 for the training and testing datasets, respectively. The main factors affecting the occurrence of gully erosion were determined to be the elevation, normalized difference vegetation index, relief, human footprint, mean annual temperature, and distance to the residential area. Elevation has the greatest effect on gully erosion, which can be explained as elevation indirectly controls gully erosion by affecting human activities and rainfall. The findings of this study provide insights into the effects of human activities, climate and permafrost on soil erosion and can serve as a basis for regional land use planning and gully erosion prevention and control in the Tibetan Plateau.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
CNS发布了新的文献求助100
刚刚
三岁半完成签到 ,获得积分10
刚刚
刚刚
Mo_Hog完成签到,获得积分10
2秒前
Handsome__oov2完成签到 ,获得积分10
2秒前
深情妙菡发布了新的文献求助30
2秒前
英俊的铭应助qfk采纳,获得10
2秒前
lala完成签到,获得积分10
2秒前
3秒前
现代代桃发布了新的文献求助10
3秒前
4秒前
6秒前
完美的jia发布了新的文献求助10
6秒前
6秒前
量子星尘发布了新的文献求助10
7秒前
7秒前
戈多来了发布了新的文献求助10
8秒前
量子星尘发布了新的文献求助10
8秒前
Akazugi完成签到,获得积分10
9秒前
9秒前
甜美的芷完成签到,获得积分10
9秒前
9秒前
10秒前
Lucas应助俊逸的翅膀采纳,获得10
10秒前
10秒前
朝闻道发布了新的文献求助10
11秒前
大个应助刘浩采纳,获得10
12秒前
BowieHuang应助甜美的芷采纳,获得10
13秒前
einspringen发布了新的文献求助10
14秒前
安详岱周发布了新的文献求助10
14秒前
简一发布了新的文献求助10
14秒前
桐桐应助完美的jia采纳,获得10
14秒前
jmy1995发布了新的文献求助10
14秒前
黄萧雨完成签到,获得积分10
15秒前
鸣谦发布了新的文献求助20
15秒前
轻松凡英完成签到,获得积分10
16秒前
传奇3应助sfliufighting采纳,获得10
17秒前
尘迹完成签到,获得积分10
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Clinical Microbiology Procedures Handbook, Multi-Volume, 5th Edition 2000
The Cambridge History of China: Volume 4, Sui and T'ang China, 589–906 AD, Part Two 1000
The Composition and Relative Chronology of Dynasties 16 and 17 in Egypt 1000
Russian Foreign Policy: Change and Continuity 800
Real World Research, 5th Edition 800
Qualitative Data Analysis with NVivo By Jenine Beekhuyzen, Pat Bazeley · 2024 800
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 计算机科学 有机化学 物理 生物化学 纳米技术 复合材料 内科学 化学工程 人工智能 催化作用 遗传学 数学 基因 量子力学 物理化学
热门帖子
关注 科研通微信公众号,转发送积分 5713487
求助须知:如何正确求助?哪些是违规求助? 5215699
关于积分的说明 15270963
捐赠科研通 4865238
什么是DOI,文献DOI怎么找? 2611937
邀请新用户注册赠送积分活动 1562134
关于科研通互助平台的介绍 1519378