Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture

Soil moisture is a key variable in the water, energy, and carbon cycles. Mapping sub-surface soil moisture with fine spatial resolution requires integrating downscaling approaches and process-based models. However, the effectiveness of hybrid methods, such as regression kriging (RK), in enhancing so...

Full description

Saved in:
Bibliographic Details
Main Authors: Mo Zhang, Yong Ge, Jianghao Wang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954124004175
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063490719416320
author Mo Zhang
Yong Ge
Jianghao Wang
author_facet Mo Zhang
Yong Ge
Jianghao Wang
author_sort Mo Zhang
collection DOAJ
description Soil moisture is a key variable in the water, energy, and carbon cycles. Mapping sub-surface soil moisture with fine spatial resolution requires integrating downscaling approaches and process-based models. However, the effectiveness of hybrid methods, such as regression kriging (RK), in enhancing soil moisture estimates through process-based parameter predictions remains inconclusive. This study aims to integrate infiltration processes into downscaling models to predict 1-km multi-layer soil moisture, while comparing performance of nonlinear and linear models, and evaluating RK improvements. Random forests (RF) and generalized linear model (GLM) were used to downscale surface soil moisture (0–5 cm) from 36-km Soil Moisture Active Passive satellite products to 1 km across the Qinghai-Tibet Plateau. Next, the soil moisture analytical relationship (SMAR) model was applied to simulate infiltration processes and obtain site-scale parameters. RK variants (RFRK and GLMRK) were applied to jointly predict the spatial distribution of multiple infiltration parameters, which were used in SMAR at 1-km grids to estimate sub-surface soil moisture (5–40 cm). The results showed that parameter calibration significantly enhanced sub-surface soil moisture simulation, reducing root mean square error (RMSE) by 61.2 % to 69.8 %, from 0.09 to 0.03. RF outperformed GLM across all depth intervals, providing higher prediction accuracy (average RMSE, RF: 0.07; GLM: 0.09). Moreover, RK enhanced the Nash-Sutcliffe efficiency coefficient (RFRK: 0.34; GLMRK: 0.28) and coefficient of determination (RFRK: 0.5; GLMRK: 0.38) by 7.7 %–13.3 % and 2.2 %–2.4 %. This study provides a reference for mapping multi-layer soil moisture through the integration of data-driven and knowledge-driven approaches in regional-scale study areas.
format Article
id doaj-art-8cbf4041b49640e9a9ab4e83a74230cb
institution DOAJ
issn 1574-9541
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-8cbf4041b49640e9a9ab4e83a74230cb2025-08-20T02:49:35ZengElsevierEcological Informatics1574-95412024-12-018410287510.1016/j.ecoinf.2024.102875Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moistureMo Zhang0Yong Ge1Jianghao Wang2State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China; College of Resources and Environment, University of Chinese Academy of Sciences, Beijing, China; Corresponding authors at: Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences. 11A, Datun Road, Chaoyang District, Beijing 100101, China.State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China; College of Resources and Environment, University of Chinese Academy of Sciences, Beijing, China; Key Laboratory of Poyang Lake Wetland and Watershed Research Ministry of Education, Jiangxi Normal University, Nanchang, China; Key Laboratory of Intelligent Monitoring and Comprehensive Management of Watershed Ecology, Jiangxi Province, Nanchang, China; Corresponding authors at: Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences. 11A, Datun Road, Chaoyang District, Beijing 100101, China.State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China; College of Resources and Environment, University of Chinese Academy of Sciences, Beijing, ChinaSoil moisture is a key variable in the water, energy, and carbon cycles. Mapping sub-surface soil moisture with fine spatial resolution requires integrating downscaling approaches and process-based models. However, the effectiveness of hybrid methods, such as regression kriging (RK), in enhancing soil moisture estimates through process-based parameter predictions remains inconclusive. This study aims to integrate infiltration processes into downscaling models to predict 1-km multi-layer soil moisture, while comparing performance of nonlinear and linear models, and evaluating RK improvements. Random forests (RF) and generalized linear model (GLM) were used to downscale surface soil moisture (0–5 cm) from 36-km Soil Moisture Active Passive satellite products to 1 km across the Qinghai-Tibet Plateau. Next, the soil moisture analytical relationship (SMAR) model was applied to simulate infiltration processes and obtain site-scale parameters. RK variants (RFRK and GLMRK) were applied to jointly predict the spatial distribution of multiple infiltration parameters, which were used in SMAR at 1-km grids to estimate sub-surface soil moisture (5–40 cm). The results showed that parameter calibration significantly enhanced sub-surface soil moisture simulation, reducing root mean square error (RMSE) by 61.2 % to 69.8 %, from 0.09 to 0.03. RF outperformed GLM across all depth intervals, providing higher prediction accuracy (average RMSE, RF: 0.07; GLM: 0.09). Moreover, RK enhanced the Nash-Sutcliffe efficiency coefficient (RFRK: 0.34; GLMRK: 0.28) and coefficient of determination (RFRK: 0.5; GLMRK: 0.38) by 7.7 %–13.3 % and 2.2 %–2.4 %. This study provides a reference for mapping multi-layer soil moisture through the integration of data-driven and knowledge-driven approaches in regional-scale study areas.http://www.sciencedirect.com/science/article/pii/S1574954124004175Dual-drive methodGenetic algorithmMachine learningSoil moisture analytical relationship modelSoil moisture downscaling
spellingShingle Mo Zhang
Yong Ge
Jianghao Wang
Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture
Ecological Informatics
Dual-drive method
Genetic algorithm
Machine learning
Soil moisture analytical relationship model
Soil moisture downscaling
title Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture
title_full Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture
title_fullStr Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture
title_full_unstemmed Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture
title_short Integrating infiltration processes in hybrid downscaling methods to estimate sub-surface soil moisture
title_sort integrating infiltration processes in hybrid downscaling methods to estimate sub surface soil moisture
topic Dual-drive method
Genetic algorithm
Machine learning
Soil moisture analytical relationship model
Soil moisture downscaling
url http://www.sciencedirect.com/science/article/pii/S1574954124004175
work_keys_str_mv AT mozhang integratinginfiltrationprocessesinhybriddownscalingmethodstoestimatesubsurfacesoilmoisture
AT yongge integratinginfiltrationprocessesinhybriddownscalingmethodstoestimatesubsurfacesoilmoisture
AT jianghaowang integratinginfiltrationprocessesinhybriddownscalingmethodstoestimatesubsurfacesoilmoisture