Non-Linear Models for Assessing Soil Moisture Estimation

Accurately estimating soil moisture (SM) without direct measurements poses significant challenges due to nonlinear interactions in meteorological variables and the lagged response of SM to precipitation. This study evaluates two approaches: the auto-regressive integrated moving average (ARIMA) model...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Li, Susu Wang, Han Wu, Hao Dong, Dezhi Kong, Hanxue Li, Dorothy S. Zhang, Haitao Chen
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Horticulturae
Subjects:
Online Access:https://www.mdpi.com/2311-7524/11/5/492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327011424632832
author Rui Li
Susu Wang
Han Wu
Hao Dong
Dezhi Kong
Hanxue Li
Dorothy S. Zhang
Haitao Chen
author_facet Rui Li
Susu Wang
Han Wu
Hao Dong
Dezhi Kong
Hanxue Li
Dorothy S. Zhang
Haitao Chen
author_sort Rui Li
collection DOAJ
description Accurately estimating soil moisture (SM) without direct measurements poses significant challenges due to nonlinear interactions in meteorological variables and the lagged response of SM to precipitation. This study evaluates two approaches: the auto-regressive integrated moving average (ARIMA) model for one-day-ahead SM forecasting and a K-means clustering-based multilayer perceptron (K-MLP) for real-time SM estimation at depths of 5 cm, 20 cm, and 50 cm in Changbai Mountain region. Although the K-MLP model outperformed the MLP model, achieving a maximum R<sup>2</sup> of 0.728, its estimation accuracy remains suboptimal. By contrast, the ARIMA model effectively leveraged SM persistence, achieving high accuracy in one-day-ahead forecasting. Specifically, the ARIMA (0, 1, 6), ARIMA (1, 1, 2), and ARIMA (2, 1, 1) models yield R<sup>2</sup> values of 0.9677, 0.9853, and 0.9684 and RMSE values of 0.02 m<sup>3</sup>·m<sup>3</sup>, 0.015 m<sup>3</sup>·m<sup>3</sup>, and 0.006 m<sup>3</sup>·m<sup>3</sup> at depths of 5 cm, 20 cm, and 50 cm, respectively. This study explores ARIMA’s robustness in short-term SM forecasting and its adaptability to dynamic meteorological conditions, offering potential applications in agricultural water management and ecological monitoring.
format Article
id doaj-art-8f6ed6a317da4ee4ac55e21aac5f36f8
institution Kabale University
issn 2311-7524
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Horticulturae
spelling doaj-art-8f6ed6a317da4ee4ac55e21aac5f36f82025-08-20T03:47:59ZengMDPI AGHorticulturae2311-75242025-04-0111549210.3390/horticulturae11050492Non-Linear Models for Assessing Soil Moisture EstimationRui Li0Susu Wang1Han Wu2Hao Dong3Dezhi Kong4Hanxue Li5Dorothy S. Zhang6Haitao Chen7College of Engineering, Northeast Agricultural University, Harbin 150030, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaSchool of Computer and Internet of Things Engineering, Chongqing Institute of Engineering, Chongqing 400900, ChinaSchool of Public Administration, Dongbei University of Finance and Economics, Dalian 116025, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaCollege of Mechanical and Electrical Information, Shangqiu University, Shangqiu 476000, ChinaComputing Technology and Information Systems Department, Guilford College, Greensboro, NC 27410, USACollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaAccurately estimating soil moisture (SM) without direct measurements poses significant challenges due to nonlinear interactions in meteorological variables and the lagged response of SM to precipitation. This study evaluates two approaches: the auto-regressive integrated moving average (ARIMA) model for one-day-ahead SM forecasting and a K-means clustering-based multilayer perceptron (K-MLP) for real-time SM estimation at depths of 5 cm, 20 cm, and 50 cm in Changbai Mountain region. Although the K-MLP model outperformed the MLP model, achieving a maximum R<sup>2</sup> of 0.728, its estimation accuracy remains suboptimal. By contrast, the ARIMA model effectively leveraged SM persistence, achieving high accuracy in one-day-ahead forecasting. Specifically, the ARIMA (0, 1, 6), ARIMA (1, 1, 2), and ARIMA (2, 1, 1) models yield R<sup>2</sup> values of 0.9677, 0.9853, and 0.9684 and RMSE values of 0.02 m<sup>3</sup>·m<sup>3</sup>, 0.015 m<sup>3</sup>·m<sup>3</sup>, and 0.006 m<sup>3</sup>·m<sup>3</sup> at depths of 5 cm, 20 cm, and 50 cm, respectively. This study explores ARIMA’s robustness in short-term SM forecasting and its adaptability to dynamic meteorological conditions, offering potential applications in agricultural water management and ecological monitoring.https://www.mdpi.com/2311-7524/11/5/492soil moisture estimationauto-regressive integrated moving averagemultilayer perceptronK-means clustering
spellingShingle Rui Li
Susu Wang
Han Wu
Hao Dong
Dezhi Kong
Hanxue Li
Dorothy S. Zhang
Haitao Chen
Non-Linear Models for Assessing Soil Moisture Estimation
Horticulturae
soil moisture estimation
auto-regressive integrated moving average
multilayer perceptron
K-means clustering
title Non-Linear Models for Assessing Soil Moisture Estimation
title_full Non-Linear Models for Assessing Soil Moisture Estimation
title_fullStr Non-Linear Models for Assessing Soil Moisture Estimation
title_full_unstemmed Non-Linear Models for Assessing Soil Moisture Estimation
title_short Non-Linear Models for Assessing Soil Moisture Estimation
title_sort non linear models for assessing soil moisture estimation
topic soil moisture estimation
auto-regressive integrated moving average
multilayer perceptron
K-means clustering
url https://www.mdpi.com/2311-7524/11/5/492
work_keys_str_mv AT ruili nonlinearmodelsforassessingsoilmoistureestimation
AT susuwang nonlinearmodelsforassessingsoilmoistureestimation
AT hanwu nonlinearmodelsforassessingsoilmoistureestimation
AT haodong nonlinearmodelsforassessingsoilmoistureestimation
AT dezhikong nonlinearmodelsforassessingsoilmoistureestimation
AT hanxueli nonlinearmodelsforassessingsoilmoistureestimation
AT dorothyszhang nonlinearmodelsforassessingsoilmoistureestimation
AT haitaochen nonlinearmodelsforassessingsoilmoistureestimation