寻找区域范围内的最佳土壤属性地图

IF 2.6 4区 环境科学与生态学 Q3 ENVIRONMENTAL SCIENCES
Jesús Barrena-González, Francisco Lavado Contador, Blâz Repe, Manuel Pulido Fernández
{"title":"寻找区域范围内的最佳土壤属性地图","authors":"Jesús Barrena-González, Francisco Lavado Contador, Blâz Repe, Manuel Pulido Fernández","doi":"10.1007/s41742-024-00611-8","DOIUrl":null,"url":null,"abstract":"<p>Around 70% of surface in Extremadura, Spain, faces a critical risk of degradation processes, highlighting the necessity for regional-scale soil property mapping to monitor degradation trends. This study aimed to generate the most reliable soil property maps, employing the most accurate methods for each case. To achieve this, six different machine learning (ML) techniques were tested to map nine soil properties across three depth intervals (0–5, 5–10 and &gt; 10 cm). Additionally, 22 environmental covariates were utilized as inputs for model performance. Results revealed that the Random Forest (RF) model exhibited the highest precision, followed by Cubist, while Support Vector Machine showed effectiveness with limited data availability. Moreover, the study highlighted the influence of sample size on model performance. Concerning environmental covariates, vegetation indices along with selected topographic indices proved optimal for explaining the spatial distribution of soil physical properties, whereas climatic variables emerged as crucial for mapping the spatial distribution of chemical properties and key nutrients at a regional scale. Despite providing an initial insight into the regional soil property distribution using ML, future work is warranted to ensure a robust, up-to-date, and equitable database for accurate monitoring of soil degradation processes arising from various land uses.</p>","PeriodicalId":14121,"journal":{"name":"International Journal of Environmental Research","volume":null,"pages":null},"PeriodicalIF":2.6000,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Looking for Optimal Maps of Soil Properties at the Regional Scale\",\"authors\":\"Jesús Barrena-González, Francisco Lavado Contador, Blâz Repe, Manuel Pulido Fernández\",\"doi\":\"10.1007/s41742-024-00611-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Around 70% of surface in Extremadura, Spain, faces a critical risk of degradation processes, highlighting the necessity for regional-scale soil property mapping to monitor degradation trends. This study aimed to generate the most reliable soil property maps, employing the most accurate methods for each case. To achieve this, six different machine learning (ML) techniques were tested to map nine soil properties across three depth intervals (0–5, 5–10 and &gt; 10 cm). Additionally, 22 environmental covariates were utilized as inputs for model performance. Results revealed that the Random Forest (RF) model exhibited the highest precision, followed by Cubist, while Support Vector Machine showed effectiveness with limited data availability. Moreover, the study highlighted the influence of sample size on model performance. Concerning environmental covariates, vegetation indices along with selected topographic indices proved optimal for explaining the spatial distribution of soil physical properties, whereas climatic variables emerged as crucial for mapping the spatial distribution of chemical properties and key nutrients at a regional scale. Despite providing an initial insight into the regional soil property distribution using ML, future work is warranted to ensure a robust, up-to-date, and equitable database for accurate monitoring of soil degradation processes arising from various land uses.</p>\",\"PeriodicalId\":14121,\"journal\":{\"name\":\"International Journal of Environmental Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-05-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Environmental Research\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.1007/s41742-024-00611-8\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Environmental Research","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1007/s41742-024-00611-8","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

西班牙埃斯特雷马杜拉约 70% 的地表面临退化过程的严重风险,这凸显了绘制区域尺度土壤属性图以监测退化趋势的必要性。这项研究旨在生成最可靠的土壤属性图,针对每种情况采用最精确的方法。为此,对六种不同的机器学习(ML)技术进行了测试,以绘制三个深度区间(0-5、5-10 和 10 厘米)的九种土壤属性图。此外,还利用 22 个环境协变量作为模型性能的输入。结果显示,随机森林(RF)模型的精度最高,其次是 Cubist,而支持向量机在数据有限的情况下也显示出了有效性。此外,研究还强调了样本量对模型性能的影响。在环境协变量方面,植被指数和选定的地形指数被证明是解释土壤物理特性空间分布的最佳方法,而气候变量则是绘制区域范围内化学特性和主要养分空间分布图的关键。尽管利用 ML 对区域土壤特性分布有了初步了解,但仍需开展今后的工作,以确保建立一个强大、最新和公平的数据库,从而准确监测各种土地用途引起的土壤退化过程。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Looking for Optimal Maps of Soil Properties at the Regional Scale

Looking for Optimal Maps of Soil Properties at the Regional Scale

Around 70% of surface in Extremadura, Spain, faces a critical risk of degradation processes, highlighting the necessity for regional-scale soil property mapping to monitor degradation trends. This study aimed to generate the most reliable soil property maps, employing the most accurate methods for each case. To achieve this, six different machine learning (ML) techniques were tested to map nine soil properties across three depth intervals (0–5, 5–10 and > 10 cm). Additionally, 22 environmental covariates were utilized as inputs for model performance. Results revealed that the Random Forest (RF) model exhibited the highest precision, followed by Cubist, while Support Vector Machine showed effectiveness with limited data availability. Moreover, the study highlighted the influence of sample size on model performance. Concerning environmental covariates, vegetation indices along with selected topographic indices proved optimal for explaining the spatial distribution of soil physical properties, whereas climatic variables emerged as crucial for mapping the spatial distribution of chemical properties and key nutrients at a regional scale. Despite providing an initial insight into the regional soil property distribution using ML, future work is warranted to ensure a robust, up-to-date, and equitable database for accurate monitoring of soil degradation processes arising from various land uses.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.40
自引率
0.00%
发文量
104
审稿时长
1.7 months
期刊介绍: International Journal of Environmental Research is a multidisciplinary journal concerned with all aspects of environment. In pursuit of these, environmentalist disciplines are invited to contribute their knowledge and experience. International Journal of Environmental Research publishes original research papers, research notes and reviews across the broad field of environment. These include but are not limited to environmental science, environmental engineering, environmental management and planning and environmental design, urban and regional landscape design and natural disaster management. Thus high quality research papers or reviews dealing with any aspect of environment are welcomed. Papers may be theoretical, interpretative or experimental.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信