Binary Logistic Regression applied to erosion susceptibility mapping in the Southern Amazon

IF 0.5 Q4 GEOGRAPHY, PHYSICAL

Revista Brasileira de Geomorfologia Pub Date : 2023-10-28 DOI:10.20502/rbgeomorfologia.v24i4.2314

Elaine Lima da Fonseca, Eliomar Pereira da Silva Filho

{"title":"Binary Logistic Regression applied to erosion susceptibility mapping in the Southern Amazon","authors":"Elaine Lima da Fonseca, Eliomar Pereira da Silva Filho","doi":"10.20502/rbgeomorfologia.v24i4.2314","DOIUrl":null,"url":null,"abstract":"Problems with soil erosion by water wind in the Brazilian Amazon are intensifying as the forest is replaced by agricultural production. Deforestation, burning, logging, and advancing the agricultural frontier have altered the soil-vegetation balance. In this context, the analysis of soil erosion susceptibility is one of the most significant challenges to developing long-term sustainability strategies and policies. Based on the above, the present study used the principles of Statistical Modeling - Logistic Regression - to develop and validate a model for analysis of susceptibility to soil erosion using 14 environmental factors. The study was carried out in a hydrographic sub-basin with 330 km2, located in the south of the State of Rondônia in the western Amazon, which combines characteristics of intense anthropic activity, loss of fertile soil, gullies, and silting of rivers. The study area has rainfall above 2000 mm year-1, they are transcurrent shear zones, predominant relief forms are flat to slightly convex tops, drainage networks are dendritic in an exorheic system, vegetation cover is composed of areas of forests and natural or regenerated forest fragments, agriculture is destined to annual crops. Livestock is extensive, with a predominance of small rural properties. The logistic regression model showed satisfactory results with an AUC of 0.888 and global accuracy was 0.77. The variables with the most significant effect on the equation were NDVI, erosivity, and TST. The mapping found that 57.71% of the study area is in places susceptible to soil loss due to water events.","PeriodicalId":44382,"journal":{"name":"Revista Brasileira de Geomorfologia","volume":"39 8","pages":"0"},"PeriodicalIF":0.5000,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Revista Brasileira de Geomorfologia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.20502/rbgeomorfologia.v24i4.2314","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"GEOGRAPHY, PHYSICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Problems with soil erosion by water wind in the Brazilian Amazon are intensifying as the forest is replaced by agricultural production. Deforestation, burning, logging, and advancing the agricultural frontier have altered the soil-vegetation balance. In this context, the analysis of soil erosion susceptibility is one of the most significant challenges to developing long-term sustainability strategies and policies. Based on the above, the present study used the principles of Statistical Modeling - Logistic Regression - to develop and validate a model for analysis of susceptibility to soil erosion using 14 environmental factors. The study was carried out in a hydrographic sub-basin with 330 km2, located in the south of the State of Rondônia in the western Amazon, which combines characteristics of intense anthropic activity, loss of fertile soil, gullies, and silting of rivers. The study area has rainfall above 2000 mm year-1, they are transcurrent shear zones, predominant relief forms are flat to slightly convex tops, drainage networks are dendritic in an exorheic system, vegetation cover is composed of areas of forests and natural or regenerated forest fragments, agriculture is destined to annual crops. Livestock is extensive, with a predominance of small rural properties. The logistic regression model showed satisfactory results with an AUC of 0.888 and global accuracy was 0.77. The variables with the most significant effect on the equation were NDVI, erosivity, and TST. The mapping found that 57.71% of the study area is in places susceptible to soil loss due to water events.

查看原文本刊更多论文

二元Logistic回归在南亚马逊侵蚀敏感性制图中的应用

随着森林被农业生产所取代，巴西亚马逊地区水风侵蚀土壤的问题正在加剧。森林砍伐、焚烧、伐木和推进农业前沿改变了土壤-植被平衡。在此背景下，分析土壤侵蚀易感性是制定长期可持续性战略和政策的最重大挑战之一。在此基础上，本研究运用统计建模-逻辑回归的原理，建立并验证了一个包含14个环境因子的土壤侵蚀敏感性分析模型。该研究是在亚马逊西部Rondônia州南部一个330平方公里的水文子流域进行的，该流域具有强烈的人类活动、肥沃土壤的丧失、沟渠和河流淤积的特点。研究区年降雨量在2000毫米以上，它们是横流剪切带，主要的地形形式是平坦到微凸的顶部，排水网络在一个大系统中是树突状的，植被覆盖由森林和自然或再生森林碎片组成，农业注定是一年生作物。畜牧业分布广泛，以小型农村财产为主。logistic回归模型的AUC为0.888，总体精度为0.77，结果令人满意。对方程影响最显著的变量是NDVI、侵蚀力和TST。测绘发现，57.71%的研究区处于易受水事件影响的水土流失地区。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Revista Brasileira de Geomorfologia GEOGRAPHY, PHYSICAL-

CiteScore

1.30

自引率

40.00%

发文量

审稿时长

16 weeks

期刊介绍： The Revista Brasileira de Geomorfologia are focused on research, analysis and application of knowledge for the development of models of large sets of relief; fluvial dynamics; the processes of aspects, such as erosion and mass movements and their impact; survey, assessment and recovery of degraded areas; surveys and assessments of natural resources; thematic mapping and integrated relief; environmental zoning; among other relevant aspects of the land relief on any scale. From a technical and instrumental basis for the development of these studies, studies that use instruments to the survey, the interpretation and generalization of data on various aspects of the Earth''s surface, including the forms of occupation and use (s) company (s) human (s). As well as the use and integration of methods and techniques that enable geo technical and instrumental character important in scientific production and the definition of public policies.