A framework based on mechanistic modelling and machine learning for soil moisture estimation

Abstract Soil moisture has many important applications in subsurface water movement. Methods for measuring soil moisture are either destructive or require prior calibration. The aim of this study was to provide a framework for estimating soil water content with limited data (rainfall and evaporation...

Full description

Saved in:
Bibliographic Details
Main Authors: Sabri Kanzari, Sana Ben Mariem, Samir Ghannem, Safouane Mouelhi, Hiba Ghazouani, Bechir Ben Nouna
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Soil
Subjects:
Online Access:https://doi.org/10.1007/s44378-025-00086-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238242628468736
author Sabri Kanzari
Sana Ben Mariem
Samir Ghannem
Safouane Mouelhi
Hiba Ghazouani
Bechir Ben Nouna
author_facet Sabri Kanzari
Sana Ben Mariem
Samir Ghannem
Safouane Mouelhi
Hiba Ghazouani
Bechir Ben Nouna
author_sort Sabri Kanzari
collection DOAJ
description Abstract Soil moisture has many important applications in subsurface water movement. Methods for measuring soil moisture are either destructive or require prior calibration. The aim of this study was to provide a framework for estimating soil water content with limited data (rainfall and evaporation). The hydraulic properties of four layers of soil from Tunisia were measured to a depth of 80 cm. These values were used as inputs to the Hydrus 1D model to generate soil water content profiles over a 27-year period. 109 profiles were calculated using machine learning algorithms (regression trees; random forest; support vector machine) to predict soil moisture content from daily values of rainfall and evaporation. The statistical performance indices of prediction, root mean square error and correlation coefficient indicate the superiority of regression trees over other methods for all soil layers and during both calibration and validation processes and reproducing the seasonal variation of soil moisture.
format Article
id doaj-art-a5e549e943aa4ea8a1eb7ece2dbd3975
institution Kabale University
issn 3005-1223
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Soil
spelling doaj-art-a5e549e943aa4ea8a1eb7ece2dbd39752025-08-20T04:01:42ZengSpringerDiscover Soil3005-12232025-07-012111810.1007/s44378-025-00086-9A framework based on mechanistic modelling and machine learning for soil moisture estimationSabri Kanzari0Sana Ben Mariem1Samir Ghannem2Safouane Mouelhi3Hiba Ghazouani4Bechir Ben Nouna5National research Institute of rural engineering, Water and Forests, University of CarthageNational research Institute of rural engineering, Water and Forests, University of CarthageFaculty of Sciences of Bizerte, University of CarthageNational research Institute of rural engineering, Water and Forests, University of CarthageRegional Field Crops Research Center of Beja, IRESANational research Institute of rural engineering, Water and Forests, University of CarthageAbstract Soil moisture has many important applications in subsurface water movement. Methods for measuring soil moisture are either destructive or require prior calibration. The aim of this study was to provide a framework for estimating soil water content with limited data (rainfall and evaporation). The hydraulic properties of four layers of soil from Tunisia were measured to a depth of 80 cm. These values were used as inputs to the Hydrus 1D model to generate soil water content profiles over a 27-year period. 109 profiles were calculated using machine learning algorithms (regression trees; random forest; support vector machine) to predict soil moisture content from daily values of rainfall and evaporation. The statistical performance indices of prediction, root mean square error and correlation coefficient indicate the superiority of regression trees over other methods for all soil layers and during both calibration and validation processes and reproducing the seasonal variation of soil moisture.https://doi.org/10.1007/s44378-025-00086-9Soil water contentHydrus-1DMachine learningModelling
spellingShingle Sabri Kanzari
Sana Ben Mariem
Samir Ghannem
Safouane Mouelhi
Hiba Ghazouani
Bechir Ben Nouna
A framework based on mechanistic modelling and machine learning for soil moisture estimation
Discover Soil
Soil water content
Hydrus-1D
Machine learning
Modelling
title A framework based on mechanistic modelling and machine learning for soil moisture estimation
title_full A framework based on mechanistic modelling and machine learning for soil moisture estimation
title_fullStr A framework based on mechanistic modelling and machine learning for soil moisture estimation
title_full_unstemmed A framework based on mechanistic modelling and machine learning for soil moisture estimation
title_short A framework based on mechanistic modelling and machine learning for soil moisture estimation
title_sort framework based on mechanistic modelling and machine learning for soil moisture estimation
topic Soil water content
Hydrus-1D
Machine learning
Modelling
url https://doi.org/10.1007/s44378-025-00086-9
work_keys_str_mv AT sabrikanzari aframeworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT sanabenmariem aframeworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT samirghannem aframeworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT safouanemouelhi aframeworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT hibaghazouani aframeworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT bechirbennouna aframeworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT sabrikanzari frameworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT sanabenmariem frameworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT samirghannem frameworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT safouanemouelhi frameworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT hibaghazouani frameworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation
AT bechirbennouna frameworkbasedonmechanisticmodellingandmachinelearningforsoilmoistureestimation