Mapping soil thickness by accounting for right-censored data with survival probabilities and machine learning

IF 4 2区 农林科学 Q2 SOIL SCIENCE
Stephan van der Westhuizen, Gerard B. M. Heuvelink, David P. Hofmeyr, Laura Poggio, Madlene Nussbaum, Colby Brungard
{"title":"Mapping soil thickness by accounting for right-censored data with survival probabilities and machine learning","authors":"Stephan van der Westhuizen,&nbsp;Gerard B. M. Heuvelink,&nbsp;David P. Hofmeyr,&nbsp;Laura Poggio,&nbsp;Madlene Nussbaum,&nbsp;Colby Brungard","doi":"10.1111/ejss.13589","DOIUrl":null,"url":null,"abstract":"<p>In digital soil mapping, modelling soil thickness poses a challenge due to the prevalent issue of right-censored data. This means that the true soil thickness exceeds the depth of sampling, and neglecting to account for the censored nature of the data can lead to poor model performance and underestimation of the true soil thickness. Survival analysis is a well-established domain of statistical modelling that can deal with censored data. The random survival forest is a notable example of a survival-related machine learning approach used to address right-censored soil property data in digital soil mapping. Previous studies that employed this model either focused on mapping the probability of soil thickness exceeding certain depths, and thereby not mapping soil thickness itself, or dismissed it due to perceived poor performance. In this study, we propose an alternative survival model to map soil thickness that is based on the inverse probability of censoring weighting. In this approach, calibration data are weighted by the inverse of the probability that soil thickness exceeds a certain depth, that is, a survival probability. These weights can then be used with most machine learning models. We used the weights with a regular random forest, and compared it with a random survival forest, and other strategies for handling right-censored data, through a comprehensive synthetic simulation study and two real-world case studies. The results suggest that the weighted random forest model produces competitive predictions, establishing it as a viable option for mapping right-censored soil property data.</p>","PeriodicalId":12043,"journal":{"name":"European Journal of Soil Science","volume":null,"pages":null},"PeriodicalIF":4.0000,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ejss.13589","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Soil Science","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/ejss.13589","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SOIL SCIENCE","Score":null,"Total":0}
引用次数: 0

Abstract

In digital soil mapping, modelling soil thickness poses a challenge due to the prevalent issue of right-censored data. This means that the true soil thickness exceeds the depth of sampling, and neglecting to account for the censored nature of the data can lead to poor model performance and underestimation of the true soil thickness. Survival analysis is a well-established domain of statistical modelling that can deal with censored data. The random survival forest is a notable example of a survival-related machine learning approach used to address right-censored soil property data in digital soil mapping. Previous studies that employed this model either focused on mapping the probability of soil thickness exceeding certain depths, and thereby not mapping soil thickness itself, or dismissed it due to perceived poor performance. In this study, we propose an alternative survival model to map soil thickness that is based on the inverse probability of censoring weighting. In this approach, calibration data are weighted by the inverse of the probability that soil thickness exceeds a certain depth, that is, a survival probability. These weights can then be used with most machine learning models. We used the weights with a regular random forest, and compared it with a random survival forest, and other strategies for handling right-censored data, through a comprehensive synthetic simulation study and two real-world case studies. The results suggest that the weighted random forest model produces competitive predictions, establishing it as a viable option for mapping right-censored soil property data.

Abstract Image

利用生存概率和机器学习计算右删失数据,绘制土壤厚度图
在数字土壤测绘中,由于普遍存在右删失数据问题,土壤厚度建模是一项挑战。这意味着真实的土壤厚度超过了采样深度,如果忽略数据的删减特性,就会导致模型性能不佳,低估真实的土壤厚度。生存分析是统计建模的一个成熟领域,可以处理有删减的数据。随机生存林就是一个与生存相关的机器学习方法的典型例子,用于处理数字土壤制图中的右删失土壤属性数据。以往采用该模型的研究要么侧重于绘制土壤厚度超过特定深度的概率图,从而不绘制土壤厚度图本身,要么因认为该模型性能不佳而将其排除在外。在本研究中,我们提出了另一种绘制土壤厚度的生存模型,该模型基于普查加权的逆概率。在这种方法中,校准数据根据土壤厚度超过一定深度的概率的倒数(即生存概率)进行加权。这些权重可用于大多数机器学习模型。我们将权重用于常规随机森林,并通过全面的合成模拟研究和两个实际案例研究,将其与随机生存森林和其他处理右删失数据的策略进行了比较。结果表明,加权随机森林模型能做出有竞争力的预测,是绘制右删失土壤属性数据的可行选择。
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
European Journal of Soil Science
European Journal of Soil Science 农林科学-土壤科学
CiteScore
8.20
自引率
4.80%
发文量
117
审稿时长
5 months
期刊介绍: The EJSS is an international journal that publishes outstanding papers in soil science that advance the theoretical and mechanistic understanding of physical, chemical and biological processes and their interactions in soils acting from molecular to continental scales in natural and managed environments.
×
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