{"title":"Mapping the Petrogypsic Horizon Occurrence Probability in the Sahara Desert Using Predictive Models","authors":"T. Assami, H. Chenchouni, S. Hadj-Miloud","doi":"10.1134/s1064229323601920","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The presence of the petrogypsic horizon is an impediment to developing agriculture in the Sahara. It hinders the soil’s ability to store water and root development of crops. The petrogypsic horizon is commonly difficult to map due to its location either on the surface or at depth. This study used logistic regression-kriging and logistic regression models to map the petrogypsic horizon occurrence probability using 466 observations over an area of 22 573 ha in the Sahara Desert of Algeria. The models included remote sensing indices and topographic variables as environmental covariates. The accuracy of models was verified by the area under the curve (AUC). A binary map was produced by applying a threshold of 0.7 on the most performant probability map. Our results showed that logistic regression-kriging performed the best (AUC = 0.88), due to the consideration of residual spatial correlation in the model. The grain size index covariate was the most relevant compared to topographic variables, which showed the usefulness of spectral indices. Based on the binary map, the risk associated with the presence of the petrogypsic horizon was limited, representing 26% of the study area. In the Sahara Desert, though the petrogypsic horizon was weakly correlated with the tested environmental covariates, the use of satellite images and residual autocorrelation in a predictive modelling approach improved the mapping and thus risk assessment of the petrogypsic horizon.</p>","PeriodicalId":11892,"journal":{"name":"Eurasian Soil Science","volume":"4 1","pages":""},"PeriodicalIF":1.4000,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Eurasian Soil Science","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1134/s1064229323601920","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: 0
Abstract
The presence of the petrogypsic horizon is an impediment to developing agriculture in the Sahara. It hinders the soil’s ability to store water and root development of crops. The petrogypsic horizon is commonly difficult to map due to its location either on the surface or at depth. This study used logistic regression-kriging and logistic regression models to map the petrogypsic horizon occurrence probability using 466 observations over an area of 22 573 ha in the Sahara Desert of Algeria. The models included remote sensing indices and topographic variables as environmental covariates. The accuracy of models was verified by the area under the curve (AUC). A binary map was produced by applying a threshold of 0.7 on the most performant probability map. Our results showed that logistic regression-kriging performed the best (AUC = 0.88), due to the consideration of residual spatial correlation in the model. The grain size index covariate was the most relevant compared to topographic variables, which showed the usefulness of spectral indices. Based on the binary map, the risk associated with the presence of the petrogypsic horizon was limited, representing 26% of the study area. In the Sahara Desert, though the petrogypsic horizon was weakly correlated with the tested environmental covariates, the use of satellite images and residual autocorrelation in a predictive modelling approach improved the mapping and thus risk assessment of the petrogypsic horizon.
期刊介绍：
Eurasian Soil Science publishes original research papers on global and regional studies discussing both theoretical and experimental problems of genesis, geography, physics, chemistry, biology, fertility, management, conservation, and remediation of soils. Special sections are devoted to current news in the life of the International and Russian soil science societies and to the history of soil sciences.
Since 2000, the journal Agricultural Chemistry, the English version of the journal of the Russian Academy of Sciences Agrokhimiya, has been merged into the journal Eurasian Soil Science and is no longer published as a separate title.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
