Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation

Abstract Global warming is one of the most pressing and critical problems facing the world today. It is mainly caused by the increase in greenhouse gases in the atmosphere, such as carbon dioxide (CO2). Understanding how soils respond to rising temperatures is critical for predicting carbon release...

Full description

Saved in:
Bibliographic Details
Main Authors: Pierfrancesco Novielli, Michele Magarelli, Donato Romano, Pierpaolo Di Bitonto, Anna Maria Stellacci, Alfonso Monaco, Nicola Amoroso, Roberto Bellotti, Sabina Tangaro
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96216-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849737790330241024
author Pierfrancesco Novielli
Michele Magarelli
Donato Romano
Pierpaolo Di Bitonto
Anna Maria Stellacci
Alfonso Monaco
Nicola Amoroso
Roberto Bellotti
Sabina Tangaro
author_facet Pierfrancesco Novielli
Michele Magarelli
Donato Romano
Pierpaolo Di Bitonto
Anna Maria Stellacci
Alfonso Monaco
Nicola Amoroso
Roberto Bellotti
Sabina Tangaro
author_sort Pierfrancesco Novielli
collection DOAJ
description Abstract Global warming is one of the most pressing and critical problems facing the world today. It is mainly caused by the increase in greenhouse gases in the atmosphere, such as carbon dioxide (CO2). Understanding how soils respond to rising temperatures is critical for predicting carbon release and informing climate mitigation strategies. Q10, a measure of soil microbial respiration, quantifies the increase in CO2 release caused by a $$10^\circ$$ Celsius rise in temperature, serving as a key indicator of this sensitivity. However, predicting Q10 across diverse soil types remains a challenge, especially when considering the complex interactions between biochemical, microbiome, and environmental factors. In this study, we applied explainable artificial intelligence (XAI) to machine learning models to predict soil respiration sensitivity (Q10) and uncover the key factors driving this process. Using SHAP (SHapley Additive exPlanations) values, we identified glucose-induced soil respiration and the proportion of bacteria positively associated with Q10 as the most influential predictors. Our machine learning models achieved an accuracy of $$0.813 \pm 0.007$$ , precision of $$0.812 \pm 0.008$$ , an AUC-ROC of $$0.884 \pm 0.003$$ , and an AUC-PRC of $$0.883 \pm 0.007$$ , ensuring robust and reliable predictions. By leveraging t-SNE (t-distributed Stochastic Neighbor Embedding) and clustering techniques, we further segmented low Q10 soils into distinct subgroups, identifying soils with a higher probability of transitioning to high Q10 states. Our findings not only highlight the potential of XAI in making model predictions transparent and interpretable, but also provide actionable insights into managing soil carbon release in response to climate change. This research bridges the gap between AI-driven environmental modeling and practical applications in agriculture, offering new directions for targeted soil management and climate resilience strategies.
format Article
id doaj-art-ff96a043ea6b4d1d86d607819e04d9b5
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ff96a043ea6b4d1d86d607819e04d9b52025-08-20T03:06:49ZengNature PortfolioScientific Reports2045-23222025-04-0115111310.1038/s41598-025-96216-yLeveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigationPierfrancesco Novielli0Michele Magarelli1Donato Romano2Pierpaolo Di Bitonto3Anna Maria Stellacci4Alfonso Monaco5Nicola Amoroso6Roberto Bellotti7Sabina Tangaro8Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo MoroDipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo MoroDipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo MoroDipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo MoroDipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo MoroIstituto Nazionale di Fisica Nucleare, Sezione di BariIstituto Nazionale di Fisica Nucleare, Sezione di BariIstituto Nazionale di Fisica Nucleare, Sezione di BariDipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo MoroAbstract Global warming is one of the most pressing and critical problems facing the world today. It is mainly caused by the increase in greenhouse gases in the atmosphere, such as carbon dioxide (CO2). Understanding how soils respond to rising temperatures is critical for predicting carbon release and informing climate mitigation strategies. Q10, a measure of soil microbial respiration, quantifies the increase in CO2 release caused by a $$10^\circ$$ Celsius rise in temperature, serving as a key indicator of this sensitivity. However, predicting Q10 across diverse soil types remains a challenge, especially when considering the complex interactions between biochemical, microbiome, and environmental factors. In this study, we applied explainable artificial intelligence (XAI) to machine learning models to predict soil respiration sensitivity (Q10) and uncover the key factors driving this process. Using SHAP (SHapley Additive exPlanations) values, we identified glucose-induced soil respiration and the proportion of bacteria positively associated with Q10 as the most influential predictors. Our machine learning models achieved an accuracy of $$0.813 \pm 0.007$$ , precision of $$0.812 \pm 0.008$$ , an AUC-ROC of $$0.884 \pm 0.003$$ , and an AUC-PRC of $$0.883 \pm 0.007$$ , ensuring robust and reliable predictions. By leveraging t-SNE (t-distributed Stochastic Neighbor Embedding) and clustering techniques, we further segmented low Q10 soils into distinct subgroups, identifying soils with a higher probability of transitioning to high Q10 states. Our findings not only highlight the potential of XAI in making model predictions transparent and interpretable, but also provide actionable insights into managing soil carbon release in response to climate change. This research bridges the gap between AI-driven environmental modeling and practical applications in agriculture, offering new directions for targeted soil management and climate resilience strategies.https://doi.org/10.1038/s41598-025-96216-ySoil Respiration SensitivityMachine LearningExplainable Artificial Intelligence (XAI)Q10Climate Change
spellingShingle Pierfrancesco Novielli
Michele Magarelli
Donato Romano
Pierpaolo Di Bitonto
Anna Maria Stellacci
Alfonso Monaco
Nicola Amoroso
Roberto Bellotti
Sabina Tangaro
Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation
Scientific Reports
Soil Respiration Sensitivity
Machine Learning
Explainable Artificial Intelligence (XAI)
Q10
Climate Change
title Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation
title_full Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation
title_fullStr Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation
title_full_unstemmed Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation
title_short Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation
title_sort leveraging explainable ai to predict soil respiration sensitivity and its drivers for climate change mitigation
topic Soil Respiration Sensitivity
Machine Learning
Explainable Artificial Intelligence (XAI)
Q10
Climate Change
url https://doi.org/10.1038/s41598-025-96216-y
work_keys_str_mv AT pierfrancesconovielli leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT michelemagarelli leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT donatoromano leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT pierpaolodibitonto leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT annamariastellacci leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT alfonsomonaco leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT nicolaamoroso leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT robertobellotti leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation
AT sabinatangaro leveragingexplainableaitopredictsoilrespirationsensitivityanditsdriversforclimatechangemitigation