Jinming Zhang , Jianli Ding , Zihan Zhang , Jinjie Wang , Xu Zeng , Xiangyu Ge
{"title":"干旱区典型绿洲多深度土壤盐渍化反演及时空变化机制研究——以维库绿洲为例","authors":"Jinming Zhang , Jianli Ding , Zihan Zhang , Jinjie Wang , Xu Zeng , Xiangyu Ge","doi":"10.1016/j.agwat.2025.109542","DOIUrl":null,"url":null,"abstract":"<div><div>Soil salinization is a widespread issue in arid and semi-arid regions, severely threatening agricultural productivity and environmental sustainability. However, accurately modeling and predicting soil salinity at multiple depths over time remains a challenge due to complex interactions among environmental factors and limited ground observations. Understanding the spatiotemporal characteristics of soil salinity and its driving factors is essential for formulating more scientific and rational irrigation strategies and remediation methods. Taking the Wei-Ku Oasis, a typical arid region oasis, as an example, this study uses Landsat remote sensing imagery as the data source, incorporating soil salinity field measurements over a decade, employing the Bootstrap Soft Shrinkage(BOSS) algorithm to select feature variables, and building soil salinity inversion models at various depths through a Convolutional Neural Networks and Long Short-Term Memory networks (CNN-LSTM) framework. The spatiotemporal variation of soil salinity in the Wei-Ku Oasis is analyzed, and the driving mechanisms of soil salinity change in the study area are explored using the optimal geographic detector. Results indicate that: (1) The multi-depth soil salinity inversion models built with the CNN-LSTM framework exhibit superior predictive performance, with the 0–10 cm soil salinity prediction model achieving the highest accuracy, attaining an R² of 0.7 in the test set. The R² values for the test set of soil salinity prediction models at 10–20 cm, 20–40 cm, 40–60 cm, 60–80 cm, and 80–100 cm depths are 0.5, 0.57, 0.53, 0.5, and 0.52, respectively. (2) Based on soil salinity classification, the area of non-salinized soil at all depths shows an increasing trend, whereas non-salinized soil within the oasis exhibits salinity accumulation. (3) Soil salinity in the Wei-Ku Oasis is influenced by multiple types of driving factors, with the interaction of any two factors enhancing the explanatory power for salinity changes. Future research could also focus on more refined soil salinity mapping across seasons, obtaining more comprehensive driving data with higher temporal and spatial resolutions, analyzing the transfer mechanisms of soil salinity between different soil depths, and providing a theoretical basis for the scientific management of salinization.</div></div>","PeriodicalId":7634,"journal":{"name":"Agricultural Water Management","volume":"315 ","pages":"Article 109542"},"PeriodicalIF":5.9000,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Study on the inversion and spatiotemporal variation mechanism of soil salinization at multiple depths in typical oases in arid areas: A case study of Wei-Ku Oasis\",\"authors\":\"Jinming Zhang , Jianli Ding , Zihan Zhang , Jinjie Wang , Xu Zeng , Xiangyu Ge\",\"doi\":\"10.1016/j.agwat.2025.109542\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Soil salinization is a widespread issue in arid and semi-arid regions, severely threatening agricultural productivity and environmental sustainability. However, accurately modeling and predicting soil salinity at multiple depths over time remains a challenge due to complex interactions among environmental factors and limited ground observations. Understanding the spatiotemporal characteristics of soil salinity and its driving factors is essential for formulating more scientific and rational irrigation strategies and remediation methods. Taking the Wei-Ku Oasis, a typical arid region oasis, as an example, this study uses Landsat remote sensing imagery as the data source, incorporating soil salinity field measurements over a decade, employing the Bootstrap Soft Shrinkage(BOSS) algorithm to select feature variables, and building soil salinity inversion models at various depths through a Convolutional Neural Networks and Long Short-Term Memory networks (CNN-LSTM) framework. The spatiotemporal variation of soil salinity in the Wei-Ku Oasis is analyzed, and the driving mechanisms of soil salinity change in the study area are explored using the optimal geographic detector. Results indicate that: (1) The multi-depth soil salinity inversion models built with the CNN-LSTM framework exhibit superior predictive performance, with the 0–10 cm soil salinity prediction model achieving the highest accuracy, attaining an R² of 0.7 in the test set. The R² values for the test set of soil salinity prediction models at 10–20 cm, 20–40 cm, 40–60 cm, 60–80 cm, and 80–100 cm depths are 0.5, 0.57, 0.53, 0.5, and 0.52, respectively. (2) Based on soil salinity classification, the area of non-salinized soil at all depths shows an increasing trend, whereas non-salinized soil within the oasis exhibits salinity accumulation. (3) Soil salinity in the Wei-Ku Oasis is influenced by multiple types of driving factors, with the interaction of any two factors enhancing the explanatory power for salinity changes. Future research could also focus on more refined soil salinity mapping across seasons, obtaining more comprehensive driving data with higher temporal and spatial resolutions, analyzing the transfer mechanisms of soil salinity between different soil depths, and providing a theoretical basis for the scientific management of salinization.</div></div>\",\"PeriodicalId\":7634,\"journal\":{\"name\":\"Agricultural Water Management\",\"volume\":\"315 \",\"pages\":\"Article 109542\"},\"PeriodicalIF\":5.9000,\"publicationDate\":\"2025-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Agricultural Water Management\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0378377425002562\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRONOMY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agricultural Water Management","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378377425002562","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
Study on the inversion and spatiotemporal variation mechanism of soil salinization at multiple depths in typical oases in arid areas: A case study of Wei-Ku Oasis
Soil salinization is a widespread issue in arid and semi-arid regions, severely threatening agricultural productivity and environmental sustainability. However, accurately modeling and predicting soil salinity at multiple depths over time remains a challenge due to complex interactions among environmental factors and limited ground observations. Understanding the spatiotemporal characteristics of soil salinity and its driving factors is essential for formulating more scientific and rational irrigation strategies and remediation methods. Taking the Wei-Ku Oasis, a typical arid region oasis, as an example, this study uses Landsat remote sensing imagery as the data source, incorporating soil salinity field measurements over a decade, employing the Bootstrap Soft Shrinkage(BOSS) algorithm to select feature variables, and building soil salinity inversion models at various depths through a Convolutional Neural Networks and Long Short-Term Memory networks (CNN-LSTM) framework. The spatiotemporal variation of soil salinity in the Wei-Ku Oasis is analyzed, and the driving mechanisms of soil salinity change in the study area are explored using the optimal geographic detector. Results indicate that: (1) The multi-depth soil salinity inversion models built with the CNN-LSTM framework exhibit superior predictive performance, with the 0–10 cm soil salinity prediction model achieving the highest accuracy, attaining an R² of 0.7 in the test set. The R² values for the test set of soil salinity prediction models at 10–20 cm, 20–40 cm, 40–60 cm, 60–80 cm, and 80–100 cm depths are 0.5, 0.57, 0.53, 0.5, and 0.52, respectively. (2) Based on soil salinity classification, the area of non-salinized soil at all depths shows an increasing trend, whereas non-salinized soil within the oasis exhibits salinity accumulation. (3) Soil salinity in the Wei-Ku Oasis is influenced by multiple types of driving factors, with the interaction of any two factors enhancing the explanatory power for salinity changes. Future research could also focus on more refined soil salinity mapping across seasons, obtaining more comprehensive driving data with higher temporal and spatial resolutions, analyzing the transfer mechanisms of soil salinity between different soil depths, and providing a theoretical basis for the scientific management of salinization.
期刊介绍:
Agricultural Water Management publishes papers of international significance relating to the science, economics, and policy of agricultural water management. In all cases, manuscripts must address implications and provide insight regarding agricultural water management.