Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data

The accurate prediction of the spatial variability for soil water content (SWC) in farmland is essential for water resource management and sustainable agricultural development. However, natural factors introduce uncertainty and result in poor alignment when predicting farmland SWC, leading to low ac...

Full description

Saved in:
Bibliographic Details
Main Authors: Weihao Yang, Ruofan Zhen, Fanyue Meng, Xiaohang Yang, Miao Lu, Yingqiang Song
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/14/12/3039
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850239884664504320
author Weihao Yang
Ruofan Zhen
Fanyue Meng
Xiaohang Yang
Miao Lu
Yingqiang Song
author_facet Weihao Yang
Ruofan Zhen
Fanyue Meng
Xiaohang Yang
Miao Lu
Yingqiang Song
author_sort Weihao Yang
collection DOAJ
description The accurate prediction of the spatial variability for soil water content (SWC) in farmland is essential for water resource management and sustainable agricultural development. However, natural factors introduce uncertainty and result in poor alignment when predicting farmland SWC, leading to low accuracy. To address this, this study introduced a novel indicator: landscape indices. These indices include the largest patch index (LPI), edge density (ED), aggregation index (AI), patch cohesion index (COH), contagion index (CON), landscape division index (DIV), percentage of like adjacencies (PLA), Shannon evenness index (SHEI), and Shannon diversity index (SHDI). A Bayesian optimization–deep forest (BO–DF) model was developed to leverage these indices for predicting the spatial variability of SWC. Statistical analysis revealed that landscape indices exhibited skewed distributions and weak linear correlations with SWC (r < 0.2). Despite this, incorporating landscape index variables into the BO–DF model significantly improved prediction accuracy, with R<sup>2</sup> increasing by 35.85%. This model demonstrated a robust nonlinear fitting capability for the spatial variability of SWC. Spatial mapping of SWC using the BO–DF model indicated that high-value areas were predominantly located in the eastern and southern regions of the Yellow River Delta in China. Furthermore, the SHapley additive explanation (SHAP) analysis highlighted that landscape indices were key drivers in predicting SWC. These findings underscore the potential of landscape indices as valuable variables for spatial SWC prediction, supporting regional strategies for sustainable agricultural development.
format Article
id doaj-art-d6262cbe826c439e99a31c8285d464bf
institution OA Journals
issn 2073-4395
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-d6262cbe826c439e99a31c8285d464bf2025-08-20T02:01:01ZengMDPI AGAgronomy2073-43952024-12-011412303910.3390/agronomy14123039Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture DataWeihao Yang0Ruofan Zhen1Fanyue Meng2Xiaohang Yang3Miao Lu4Yingqiang Song5School of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaState Key Laboratory of Efficient Utilization of Arid and Semi-Arid Arable Land in Northern China/Key Laboratory of Agricultural Remote Sensing, Ministry of Agriculture and Rural Affairs/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaThe accurate prediction of the spatial variability for soil water content (SWC) in farmland is essential for water resource management and sustainable agricultural development. However, natural factors introduce uncertainty and result in poor alignment when predicting farmland SWC, leading to low accuracy. To address this, this study introduced a novel indicator: landscape indices. These indices include the largest patch index (LPI), edge density (ED), aggregation index (AI), patch cohesion index (COH), contagion index (CON), landscape division index (DIV), percentage of like adjacencies (PLA), Shannon evenness index (SHEI), and Shannon diversity index (SHDI). A Bayesian optimization–deep forest (BO–DF) model was developed to leverage these indices for predicting the spatial variability of SWC. Statistical analysis revealed that landscape indices exhibited skewed distributions and weak linear correlations with SWC (r < 0.2). Despite this, incorporating landscape index variables into the BO–DF model significantly improved prediction accuracy, with R<sup>2</sup> increasing by 35.85%. This model demonstrated a robust nonlinear fitting capability for the spatial variability of SWC. Spatial mapping of SWC using the BO–DF model indicated that high-value areas were predominantly located in the eastern and southern regions of the Yellow River Delta in China. Furthermore, the SHapley additive explanation (SHAP) analysis highlighted that landscape indices were key drivers in predicting SWC. These findings underscore the potential of landscape indices as valuable variables for spatial SWC prediction, supporting regional strategies for sustainable agricultural development.https://www.mdpi.com/2073-4395/14/12/3039landscape indexmachine learningsoil water contentfarmland
spellingShingle Weihao Yang
Ruofan Zhen
Fanyue Meng
Xiaohang Yang
Miao Lu
Yingqiang Song
Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data
Agronomy
landscape index
machine learning
soil water content
farmland
title Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data
title_full Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data
title_fullStr Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data
title_full_unstemmed Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data
title_short Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data
title_sort spatial prediction of soil water content by bayesian optimization deep forest model with landscape index and soil texture data
topic landscape index
machine learning
soil water content
farmland
url https://www.mdpi.com/2073-4395/14/12/3039
work_keys_str_mv AT weihaoyang spatialpredictionofsoilwatercontentbybayesianoptimizationdeepforestmodelwithlandscapeindexandsoiltexturedata
AT ruofanzhen spatialpredictionofsoilwatercontentbybayesianoptimizationdeepforestmodelwithlandscapeindexandsoiltexturedata
AT fanyuemeng spatialpredictionofsoilwatercontentbybayesianoptimizationdeepforestmodelwithlandscapeindexandsoiltexturedata
AT xiaohangyang spatialpredictionofsoilwatercontentbybayesianoptimizationdeepforestmodelwithlandscapeindexandsoiltexturedata
AT miaolu spatialpredictionofsoilwatercontentbybayesianoptimizationdeepforestmodelwithlandscapeindexandsoiltexturedata
AT yingqiangsong spatialpredictionofsoilwatercontentbybayesianoptimizationdeepforestmodelwithlandscapeindexandsoiltexturedata