{"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.
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.