Predictive mapping of wetland soil types in the Canadian Prairie Pothole Region using high-resolution digital elevation model terrain derivatives

IF 1.5 4区 农林科学 Q4 SOIL SCIENCE Canadian Journal of Soil Science Pub Date : 2022-11-23 DOI:10.1139/cjss-2022-0034
J. Kiss, A. Bedard-Haughn, P. Sorenson
{"title":"Predictive mapping of wetland soil types in the Canadian Prairie Pothole Region using high-resolution digital elevation model terrain derivatives","authors":"J. Kiss, A. Bedard-Haughn, P. Sorenson","doi":"10.1139/cjss-2022-0034","DOIUrl":null,"url":null,"abstract":"Abstract Wetland soil types, which can be distinguished based on calcium carbonate content, vary in their effect on ecosystem functions like phosphorus retention, salinity contributions, and greenhouse gas forcing. These soil types may be predictively mapped with machine learning models that use terrain derivatives calculated from high-resolution digital elevation models. Soil profiles from three Saskatchewan study sites were classified into three functional categories—upland, calcareous wetland, or noncalcareous wetland—and used to train random forest models for predictive soil mapping. Multiple terrain derivatives were included as predictor variables to capture local- and landscape-scale morphometry and hydrology influences, including five derivatives developed for this study. Models were developed at three spatial resolutions: 2, 5, and 10 m, and tested via internal cross-validation and independent validation with datasets from previous studies. Predictive accuracies were highest when mapping at 2 m resolution (independent validation accuracy range = 64%–100%) but also successful when mapping at 5 and 10 m resolutions (independent validation accuracy range = 63%–100%); however, visual inspection determined that the maps generated at 10 m resolution were less detailed and occasionally featured questionable discontinuous soil distributions. Three of the five terrain derivatives developed for this study were among the most important predictor variables (first, second, and 10th most important). Models trained using only data from a specific site had slightly better performance than models trained using data from all sites, except in regions where training data were lacking.","PeriodicalId":9384,"journal":{"name":"Canadian Journal of Soil Science","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Canadian Journal of Soil Science","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1139/cjss-2022-0034","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"SOIL SCIENCE","Score":null,"Total":0}
引用次数: 1

Abstract

Abstract Wetland soil types, which can be distinguished based on calcium carbonate content, vary in their effect on ecosystem functions like phosphorus retention, salinity contributions, and greenhouse gas forcing. These soil types may be predictively mapped with machine learning models that use terrain derivatives calculated from high-resolution digital elevation models. Soil profiles from three Saskatchewan study sites were classified into three functional categories—upland, calcareous wetland, or noncalcareous wetland—and used to train random forest models for predictive soil mapping. Multiple terrain derivatives were included as predictor variables to capture local- and landscape-scale morphometry and hydrology influences, including five derivatives developed for this study. Models were developed at three spatial resolutions: 2, 5, and 10 m, and tested via internal cross-validation and independent validation with datasets from previous studies. Predictive accuracies were highest when mapping at 2 m resolution (independent validation accuracy range = 64%–100%) but also successful when mapping at 5 and 10 m resolutions (independent validation accuracy range = 63%–100%); however, visual inspection determined that the maps generated at 10 m resolution were less detailed and occasionally featured questionable discontinuous soil distributions. Three of the five terrain derivatives developed for this study were among the most important predictor variables (first, second, and 10th most important). Models trained using only data from a specific site had slightly better performance than models trained using data from all sites, except in regions where training data were lacking.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用高分辨率数字高程模型地形衍生物预测加拿大草原坑区湿地土壤类型
湿地土壤类型对磷保持、盐度贡献和温室气体强迫等生态系统功能的影响各不相同,可根据碳酸钙含量进行区分。这些土壤类型可以通过机器学习模型进行预测映射,该模型使用高分辨率数字高程模型计算的地形导数。萨斯喀彻温省三个研究地点的土壤剖面被划分为三个功能类别——高地、钙质湿地和非钙质湿地,并用于训练用于预测土壤制图的随机森林模型。多种地形衍生物被纳入预测变量,以捕获局部和景观尺度的形态计量学和水文影响,其中包括为本研究开发的五个衍生物。在3种空间分辨率下开发模型:2、5和10 m,并通过内部交叉验证和与先前研究数据集的独立验证进行测试。预测精度在2米分辨率下最高(独立验证精度范围= 64%-100%),但在5米和10米分辨率下也成功(独立验证精度范围= 63%-100%);然而,目视检查确定,以10米分辨率生成的地图不太详细,偶尔也有可疑的不连续土壤分布。为本研究开发的五个地形导数中有三个是最重要的预测变量(第一、第二和第十重要)。除了缺乏训练数据的地区外,仅使用来自特定地点的数据训练的模型比使用来自所有地点的数据训练的模型性能稍好。
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 去求助
来源期刊
Canadian Journal of Soil Science
Canadian Journal of Soil Science 农林科学-土壤科学
CiteScore
2.90
自引率
11.80%
发文量
73
审稿时长
6.0 months
期刊介绍: The Canadian Journal of Soil Science is an international peer-reviewed journal published in cooperation with the Canadian Society of Soil Science. The journal publishes original research on the use, management, structure and development of soils and draws from the disciplines of soil science, agrometeorology, ecology, agricultural engineering, environmental science, hydrology, forestry, geology, geography and climatology. Research is published in a number of topic sections including: agrometeorology; ecology, biological processes and plant interactions; composition and chemical processes; physical processes and interfaces; genesis, landscape processes and relationships; contamination and environmental stewardship; and management for agricultural, forestry and urban uses.
期刊最新文献
How Does No-till Affect Soil-Profile Distribution of Roots? miyo wîcêhtowin “good relations”: reckoning with the relationship between Indigenous Peoples and soil science in Canada Analytical and Experimental Evaluation of Two-Layered Unsaturated Sand Bearing Capacity Impacts of conservation agriculture on soil C and N stocks and organic matter fractions: comparing commercial producer fields with a long-term small-plot experiment in Brown Chernozems of Saskatchewan Soil surface greenhouse gas emissions and hydro-physical properties as impacted by prairie cordgrass intercropped with kura clover
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1