Modeling and digital mapping of shallow water table depth using satellite-based spectral and thermal data: Introducing a framework for digital shallow water table mapping
{"title":"Modeling and digital mapping of shallow water table depth using satellite-based spectral and thermal data: Introducing a framework for digital shallow water table mapping","authors":"Mehrdad Jeihouni , Khalil Valizadeh Kamran , Lutfiye Kusak","doi":"10.1016/j.still.2024.106317","DOIUrl":null,"url":null,"abstract":"<div><div>Shallow groundwater is a key variable of the hydrological cycle and has significant impacts on the components of energy, carbon, and water balances. Moreover, shallow saline groundwater plays a critical role in secondary soil salinization. Therefore, comprehensive information on spatial distribution of shallow water table depth is fundamental for effective land management and sustainable development. But determining it by conventional methods is time-consuming and financially costly in large areas. Shallow groundwater naturally has signatures at the land surface, and it can be parameterized by properties inferred from satellite-based surface data. Against this background, this study is to introduce a novel approach and framework for Digital Shallow Water Table Mapping (DSWTM). The efficiency and performance of the proposed DSWTM was assessed by different covariate sets and employing different predictive models. In the DSWTM framework, remote sensing spectral/thermal indices, geographic and trend data were used as covariates and the PLSR, M5, Cubist, and RF algorithms were employed as predictive models under four scenarios. For two high-performance models in each scenario, the water table depth maps were generated, and associated uncertainties were quantified using the bootstrapping technique at a spatial resolution of 30 m. The results revealed that the prediction accuracies of each predictive model were constantly increasing from the first to the fourth scenario. Moreover, the Cubist and RF models had higher performance than PLSR and M5 in all scenarios. The uncertainties’ of prediction maps generated by Cubist and RF models were decreased from the first to the fourth scenarios. The RF generated maps in all scenarios had the lowest uncertainty and provided accurate prediction maps compared to Cubist. The RF as a predictive model showed the highest ability and is recommended to use in DSWTM studies. The presented DSWTM framework opened a new research window for accurate shallow water table mapping.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"245 ","pages":"Article 106317"},"PeriodicalIF":6.1000,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Soil & Tillage Research","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167198724003180","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SOIL SCIENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Shallow groundwater is a key variable of the hydrological cycle and has significant impacts on the components of energy, carbon, and water balances. Moreover, shallow saline groundwater plays a critical role in secondary soil salinization. Therefore, comprehensive information on spatial distribution of shallow water table depth is fundamental for effective land management and sustainable development. But determining it by conventional methods is time-consuming and financially costly in large areas. Shallow groundwater naturally has signatures at the land surface, and it can be parameterized by properties inferred from satellite-based surface data. Against this background, this study is to introduce a novel approach and framework for Digital Shallow Water Table Mapping (DSWTM). The efficiency and performance of the proposed DSWTM was assessed by different covariate sets and employing different predictive models. In the DSWTM framework, remote sensing spectral/thermal indices, geographic and trend data were used as covariates and the PLSR, M5, Cubist, and RF algorithms were employed as predictive models under four scenarios. For two high-performance models in each scenario, the water table depth maps were generated, and associated uncertainties were quantified using the bootstrapping technique at a spatial resolution of 30 m. The results revealed that the prediction accuracies of each predictive model were constantly increasing from the first to the fourth scenario. Moreover, the Cubist and RF models had higher performance than PLSR and M5 in all scenarios. The uncertainties’ of prediction maps generated by Cubist and RF models were decreased from the first to the fourth scenarios. The RF generated maps in all scenarios had the lowest uncertainty and provided accurate prediction maps compared to Cubist. The RF as a predictive model showed the highest ability and is recommended to use in DSWTM studies. The presented DSWTM framework opened a new research window for accurate shallow water table mapping.
期刊介绍:
Soil & Tillage Research examines the physical, chemical and biological changes in the soil caused by tillage and field traffic. Manuscripts will be considered on aspects of soil science, physics, technology, mechanization and applied engineering for a sustainable balance among productivity, environmental quality and profitability. The following are examples of suitable topics within the scope of the journal of Soil and Tillage Research:
The agricultural and biosystems engineering associated with tillage (including no-tillage, reduced-tillage and direct drilling), irrigation and drainage, crops and crop rotations, fertilization, rehabilitation of mine spoils and processes used to modify soils. Soil change effects on establishment and yield of crops, growth of plants and roots, structure and erosion of soil, cycling of carbon and nutrients, greenhouse gas emissions, leaching, runoff and other processes that affect environmental quality. Characterization or modeling of tillage and field traffic responses, soil, climate, or topographic effects, soil deformation processes, tillage tools, traction devices, energy requirements, economics, surface and subsurface water quality effects, tillage effects on weed, pest and disease control, and their interactions.