Unraveling the Distribution of Black Carbon in Chinese Forest Soils Using Machine Learning Approaches

Chen Zhao; Zhouyang Tian; Qiang Zhang; Yinghui Wang; Peng Zhang; Guodong Sun; Yuanxi Yang; Ding He; Shuxin Tu; Junjian Wang

doi:10.1029/2024GL110618

Unraveling the Distribution of Black Carbon in Chinese Forest Soils Using Machine Learning Approaches

Chen Zhao (Co-first Author), Zhouyang Tian (Co-first Author), Qiang Zhang, Yinghui Wang, Peng Zhang, Guodong Sun, Yuanxi Yang, Ding He, Shuxin Tu, Junjian Wang^*

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

2 Citations (Scopus)

9 Downloads (CityUHK Scholars)

Abstract

Black carbon (BC) is a highly persistent yet poorly understood component of forest soil carbon reservoirs, while its inventory, distribution, and determining factors in forest soils on a large geographic scale remain unclear. Here, we characterized soil BC across 68 Chinese forest sites using benzene polycarboxylic acid method and developed machine learning (ML) models to predict and interpret potential impacts of soil organic matter (SOM) properties, soil physicochemical properties, meteorological conditions, wildfire history, and microbial diversity on BC. Results revealed that SOM properties were the most critical in predicting BC, complemented by the negative impact of mean annual temperature and alkaline mineral composition. The superior prediction accuracy for BC with higher condensed aromaticity (more benzene hexa- and penta-carboxylic acid monomers) likely results from its simpler sources and greater resistance to transformation. This study introduces an effective ML model for predicting and interpreting soil BC inventory to better understand BC cycling.

Original language	English
Article number	e2024GL110618
Journal	Geophysical Research Letters
Volume	51
Issue number	19
Online published	8 Oct 2024
DOIs	https://doi.org/10.1029/2024GL110618
Publication status	Published - 16 Oct 2024
Externally published	Yes

Funding

This work was financially supported by the National Natural Science Foundation of China (42192513 and 42122054), the Guangdong Basic and Applied Basic Research Foundation (2021B1515020082), the Shenzhen Science and Technology Innovation Commission (JCYJ20220818100403007), the Key Platform and Scientific Research Projects of Guangdong Provincial Education Department (2020KCXTD006), Guangdong Provincial Key Laboratory of Soil and Groundwater Pollution Control (2023B1212060002), the High-level University Special Fund (G030290001), the Research Grants Council of the Hong Kong Special Administrative Region, China (AoE/P-601/23-N), and the Center for Ocean Research in Hong Kong and Macau (CORE). CORE is a joint research center for ocean research between Laoshan Laboratory and HKUST.

Research Keywords

black carbon
machine learning
benzenepolycarboxylic acids
soil properties
forest soils

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-ND 4.0. https://creativecommons.org/licenses/by-nc-nd/4.0/

RGC Funding Information

RGC-funded

Access Output

10.1029/2024GL110618

252274975.pdfFinal Published version, 1.98 MBLicence: CC BY-NC-ND

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{614b9a2edfb448ca91975ff40c0029d4,

title = "Unraveling the Distribution of Black Carbon in Chinese Forest Soils Using Machine Learning Approaches",

abstract = "Black carbon (BC) is a highly persistent yet poorly understood component of forest soil carbon reservoirs, while its inventory, distribution, and determining factors in forest soils on a large geographic scale remain unclear. Here, we characterized soil BC across 68 Chinese forest sites using benzene polycarboxylic acid method and developed machine learning (ML) models to predict and interpret potential impacts of soil organic matter (SOM) properties, soil physicochemical properties, meteorological conditions, wildfire history, and microbial diversity on BC. Results revealed that SOM properties were the most critical in predicting BC, complemented by the negative impact of mean annual temperature and alkaline mineral composition. The superior prediction accuracy for BC with higher condensed aromaticity (more benzene hexa- and penta-carboxylic acid monomers) likely results from its simpler sources and greater resistance to transformation. This study introduces an effective ML model for predicting and interpreting soil BC inventory to better understand BC cycling.",

keywords = "black carbon, machine learning, benzenepolycarboxylic acids, soil properties, forest soils",

author = "Chen Zhao and Zhouyang Tian and Qiang Zhang and Yinghui Wang and Peng Zhang and Guodong Sun and Yuanxi Yang and Ding He and Shuxin Tu and Junjian Wang",

year = "2024",

month = oct,

day = "16",

doi = "10.1029/2024GL110618",

language = "English",

volume = "51",

journal = "Geophysical Research Letters",

issn = "0094-8276",

publisher = "John Wiley & Sons",

number = "19",

}

Unraveling the Distribution of Black Carbon in Chinese Forest Soils Using Machine Learning Approaches. / Zhao, Chen (Co-first Author); Tian, Zhouyang (Co-first Author); Zhang, Qiang et al.
In: Geophysical Research Letters, Vol. 51, No. 19, e2024GL110618, 16.10.2024.

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

TY - JOUR

T1 - Unraveling the Distribution of Black Carbon in Chinese Forest Soils Using Machine Learning Approaches

AU - Zhao, Chen

AU - Tian, Zhouyang

AU - Zhang, Qiang

AU - Wang, Yinghui

AU - Zhang, Peng

AU - Sun, Guodong

AU - Yang, Yuanxi

AU - He, Ding

AU - Tu, Shuxin

AU - Wang, Junjian

PY - 2024/10/16

Y1 - 2024/10/16

N2 - Black carbon (BC) is a highly persistent yet poorly understood component of forest soil carbon reservoirs, while its inventory, distribution, and determining factors in forest soils on a large geographic scale remain unclear. Here, we characterized soil BC across 68 Chinese forest sites using benzene polycarboxylic acid method and developed machine learning (ML) models to predict and interpret potential impacts of soil organic matter (SOM) properties, soil physicochemical properties, meteorological conditions, wildfire history, and microbial diversity on BC. Results revealed that SOM properties were the most critical in predicting BC, complemented by the negative impact of mean annual temperature and alkaline mineral composition. The superior prediction accuracy for BC with higher condensed aromaticity (more benzene hexa- and penta-carboxylic acid monomers) likely results from its simpler sources and greater resistance to transformation. This study introduces an effective ML model for predicting and interpreting soil BC inventory to better understand BC cycling.

AB - Black carbon (BC) is a highly persistent yet poorly understood component of forest soil carbon reservoirs, while its inventory, distribution, and determining factors in forest soils on a large geographic scale remain unclear. Here, we characterized soil BC across 68 Chinese forest sites using benzene polycarboxylic acid method and developed machine learning (ML) models to predict and interpret potential impacts of soil organic matter (SOM) properties, soil physicochemical properties, meteorological conditions, wildfire history, and microbial diversity on BC. Results revealed that SOM properties were the most critical in predicting BC, complemented by the negative impact of mean annual temperature and alkaline mineral composition. The superior prediction accuracy for BC with higher condensed aromaticity (more benzene hexa- and penta-carboxylic acid monomers) likely results from its simpler sources and greater resistance to transformation. This study introduces an effective ML model for predicting and interpreting soil BC inventory to better understand BC cycling.

KW - black carbon

KW - machine learning

KW - benzenepolycarboxylic acids

KW - soil properties

KW - forest soils

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001328066200001

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85206219616&origin=recordpage

UR - http://www.scopus.com/inward/record.url?scp=85206219616&partnerID=8YFLogxK

U2 - 10.1029/2024GL110618

DO - 10.1029/2024GL110618

M3 - RGC 21 - Publication in refereed journal

SN - 0094-8276

VL - 51

JO - Geophysical Research Letters

JF - Geophysical Research Letters

IS - 19

M1 - e2024GL110618

ER -

Unraveling the Distribution of Black Carbon in Chinese Forest Soils Using Machine Learning Approaches

Abstract

Funding

Research Keywords

Publisher's Copyright Statement

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this