Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration

Soil respiration (Rs) represents the largest carbon flux from land to the atmosphere and is important for assessing the terrestrial carbon cycle and studying climate change. In this study, we propose an interpretable machine learning prediction of global Rs (IMPGRs) based on explainable artificial i...

Full description

Saved in:
Bibliographic Details
Main Authors: Junjie Jiang, Lingxia Feng, Junguo Hu, Chao Zhu
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Ecological Indicators
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1470160X25006806
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849425939766706176
author Junjie Jiang
Lingxia Feng
Junguo Hu
Chao Zhu
author_facet Junjie Jiang
Lingxia Feng
Junguo Hu
Chao Zhu
author_sort Junjie Jiang
collection DOAJ
description Soil respiration (Rs) represents the largest carbon flux from land to the atmosphere and is important for assessing the terrestrial carbon cycle and studying climate change. In this study, we propose an interpretable machine learning prediction of global Rs (IMPGRs) based on explainable artificial intelligence (XAI) technology to interpret tree-integrated global Rs prediction models, explore the factors driving global Rs responses, and predict their distribution patterns. The IMPGRs model showed superior performance in predicting Rs, capturing two meaningful non-linear (‘J’- and ‘U’-type) relationships between Rs and environmental variables. We found that a soil temperature of 20.9°C represented an important threshold for the ‘thermal adaptation’ of Rs. Moreover, this phenomenon varied significantly across climatic zones and ecosystems, and the threshold was positively correlated with precipitation. The response of global Rs to the leaf area index (LAI) was not a simple positive correlation, and contrasting results were observed both inside and outside the Tropic of Cancer. Global Rs values (688.43 g C m−2 year−1) and their distribution were predicted using IMPGRs, with forest soils releasing the most carbon dioxide (CO2; 42.84 Pg C year−1) and accounting for 45.7 % of the global Rs. Additionally, we found significant biases in the annual Rs calculated by area weighting based on climate and ecosystem classifications because these factors characterise spatial heterogeneity differently. Such dynamics should be considered when modelling global Rs and analysing the results because they can help improve the estimation accuracy of global Rs prediction models.
format Article
id doaj-art-ce5080726d714c9da9569b82fb133ebb
institution Kabale University
issn 1470-160X
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Ecological Indicators
spelling doaj-art-ce5080726d714c9da9569b82fb133ebb2025-08-20T03:29:35ZengElsevierEcological Indicators1470-160X2025-08-0117711375010.1016/j.ecolind.2025.113750Interpretable machine learning unveils threshold responses and spatial patterns of global soil respirationJunjie Jiang0Lingxia Feng1Junguo Hu2Chao Zhu3College of Chemistry and Materials Engineering, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; State Forestry Administration Key Laboratory of Forestry Sensing Technology and Intelligent Equipment, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology Research, Zhejiang A&F University, Hangzhou, Zhejiang 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; State Forestry Administration Key Laboratory of Forestry Sensing Technology and Intelligent Equipment, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology Research, Zhejiang A&F University, Hangzhou, Zhejiang 311300, ChinaCollege of Chemistry and Materials Engineering, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; State Forestry Administration Key Laboratory of Forestry Sensing Technology and Intelligent Equipment, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology Research, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, Zhejiang A&F University, Lin’an, Zhejiang 311300, China; Corresponding author at: College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China.College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; State Forestry Administration Key Laboratory of Forestry Sensing Technology and Intelligent Equipment, Zhejiang A&F University, Hangzhou, Zhejiang 311300, China; Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology Research, Zhejiang A&F University, Hangzhou, Zhejiang 311300, ChinaSoil respiration (Rs) represents the largest carbon flux from land to the atmosphere and is important for assessing the terrestrial carbon cycle and studying climate change. In this study, we propose an interpretable machine learning prediction of global Rs (IMPGRs) based on explainable artificial intelligence (XAI) technology to interpret tree-integrated global Rs prediction models, explore the factors driving global Rs responses, and predict their distribution patterns. The IMPGRs model showed superior performance in predicting Rs, capturing two meaningful non-linear (‘J’- and ‘U’-type) relationships between Rs and environmental variables. We found that a soil temperature of 20.9°C represented an important threshold for the ‘thermal adaptation’ of Rs. Moreover, this phenomenon varied significantly across climatic zones and ecosystems, and the threshold was positively correlated with precipitation. The response of global Rs to the leaf area index (LAI) was not a simple positive correlation, and contrasting results were observed both inside and outside the Tropic of Cancer. Global Rs values (688.43 g C m−2 year−1) and their distribution were predicted using IMPGRs, with forest soils releasing the most carbon dioxide (CO2; 42.84 Pg C year−1) and accounting for 45.7 % of the global Rs. Additionally, we found significant biases in the annual Rs calculated by area weighting based on climate and ecosystem classifications because these factors characterise spatial heterogeneity differently. Such dynamics should be considered when modelling global Rs and analysing the results because they can help improve the estimation accuracy of global Rs prediction models.http://www.sciencedirect.com/science/article/pii/S1470160X25006806Global soil respirationInterpretable prediction modelResponse mechanismDistribution patternNon-linear relationshipsEstimation bias
spellingShingle Junjie Jiang
Lingxia Feng
Junguo Hu
Chao Zhu
Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
Ecological Indicators
Global soil respiration
Interpretable prediction model
Response mechanism
Distribution pattern
Non-linear relationships
Estimation bias
title Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
title_full Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
title_fullStr Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
title_full_unstemmed Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
title_short Interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
title_sort interpretable machine learning unveils threshold responses and spatial patterns of global soil respiration
topic Global soil respiration
Interpretable prediction model
Response mechanism
Distribution pattern
Non-linear relationships
Estimation bias
url http://www.sciencedirect.com/science/article/pii/S1470160X25006806
work_keys_str_mv AT junjiejiang interpretablemachinelearningunveilsthresholdresponsesandspatialpatternsofglobalsoilrespiration
AT lingxiafeng interpretablemachinelearningunveilsthresholdresponsesandspatialpatternsofglobalsoilrespiration
AT junguohu interpretablemachinelearningunveilsthresholdresponsesandspatialpatternsofglobalsoilrespiration
AT chaozhu interpretablemachinelearningunveilsthresholdresponsesandspatialpatternsofglobalsoilrespiration