Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types

Chromophoric dissolved organic matter (CDOM), characterized by unique optical properties, is an essential indicator for understanding aquatic organic matter dynamics within global carbon cycles. Soil erosion, a major source of CDOM received by lakes, transports terrestrial organic matter to water bo...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingxin Shang, Kaishan Song, Zhidan Wen, Fengfa Lai, Ge Liu, Hui Tao, Xiangfei Yu
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Environmental Science and Ecotechnology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666498425000481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471545414516736
author Yingxin Shang
Kaishan Song
Zhidan Wen
Fengfa Lai
Ge Liu
Hui Tao
Xiangfei Yu
author_facet Yingxin Shang
Kaishan Song
Zhidan Wen
Fengfa Lai
Ge Liu
Hui Tao
Xiangfei Yu
author_sort Yingxin Shang
collection DOAJ
description Chromophoric dissolved organic matter (CDOM), characterized by unique optical properties, is an essential indicator for understanding aquatic organic matter dynamics within global carbon cycles. Soil erosion, a major source of CDOM received by lakes, transports terrestrial organic matter to water bodies, altering sources, bioavailability and molecular complexity of CDOM significantly. Yet, the spatial patterns of CDOM in lakes from different soil erosion regions are still unknown. Here, we developed a robust machine learning framework (RMSEcalibration = 0.87 m-1) to estimate CDOM concentrations in lakes by integrating over 1300 in situ water samples with Landsat 8 OLI surface reflectance data. We then applied this model to map the spatial distribution of CDOM across lakes larger than 0.1 km2 in 2020. Our analysis revealed distinct spatial patterns, with mean CDOM absorption coefficients at 355 nm of 3.73 m-1 in freeze-thaw erosion regions, 6.31 m-1 in wind erosion regions, and 3.72 m-1 in hydraulic erosion regions, reflecting significant variations driven by erosion intensity. Two axes of PCA analysis explained over 48% variations of CDOM for different soil erosion types. Chemical characterization indicated that polycyclic aromatic predominated in wind and hydraulic erosion regions, whereas freeze-thaw erosion regions exhibited higher proportions of peptides and unsaturated aliphatic compounds. This study highlights the crucial connection between terrestrial soil erosion processes and aquatic DOM composition, providing vital insights for evaluating global carbon cycling and carbon storage within inland ecosystems.
format Article
id doaj-art-acd2046cd1bc4cecb32d91124bff2d3e
institution Kabale University
issn 2666-4984
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Environmental Science and Ecotechnology
spelling doaj-art-acd2046cd1bc4cecb32d91124bff2d3e2025-08-20T03:24:47ZengElsevierEnvironmental Science and Ecotechnology2666-49842025-05-012510057010.1016/j.ese.2025.100570Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion typesYingxin Shang0Kaishan Song1Zhidan Wen2Fengfa Lai3Ge Liu4Hui Tao5Xiangfei Yu6Northeast Institute of Geography and Agroecology, CAS, Changchun, 130102, ChinaNortheast Institute of Geography and Agroecology, CAS, Changchun, 130102, China; Corresponding author.Northeast Institute of Geography and Agroecology, CAS, Changchun, 130102, ChinaNortheast Institute of Geography and Agroecology, CAS, Changchun, 130102, ChinaNortheast Institute of Geography and Agroecology, CAS, Changchun, 130102, ChinaNortheast Institute of Geography and Agroecology, CAS, Changchun, 130102, ChinaJilin Jianzhu University, Changchun, 130118, ChinaChromophoric dissolved organic matter (CDOM), characterized by unique optical properties, is an essential indicator for understanding aquatic organic matter dynamics within global carbon cycles. Soil erosion, a major source of CDOM received by lakes, transports terrestrial organic matter to water bodies, altering sources, bioavailability and molecular complexity of CDOM significantly. Yet, the spatial patterns of CDOM in lakes from different soil erosion regions are still unknown. Here, we developed a robust machine learning framework (RMSEcalibration = 0.87 m-1) to estimate CDOM concentrations in lakes by integrating over 1300 in situ water samples with Landsat 8 OLI surface reflectance data. We then applied this model to map the spatial distribution of CDOM across lakes larger than 0.1 km2 in 2020. Our analysis revealed distinct spatial patterns, with mean CDOM absorption coefficients at 355 nm of 3.73 m-1 in freeze-thaw erosion regions, 6.31 m-1 in wind erosion regions, and 3.72 m-1 in hydraulic erosion regions, reflecting significant variations driven by erosion intensity. Two axes of PCA analysis explained over 48% variations of CDOM for different soil erosion types. Chemical characterization indicated that polycyclic aromatic predominated in wind and hydraulic erosion regions, whereas freeze-thaw erosion regions exhibited higher proportions of peptides and unsaturated aliphatic compounds. This study highlights the crucial connection between terrestrial soil erosion processes and aquatic DOM composition, providing vital insights for evaluating global carbon cycling and carbon storage within inland ecosystems.http://www.sciencedirect.com/science/article/pii/S2666498425000481CDOMRemote sensingFT ICRMSSoil erosionLake
spellingShingle Yingxin Shang
Kaishan Song
Zhidan Wen
Fengfa Lai
Ge Liu
Hui Tao
Xiangfei Yu
Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
Environmental Science and Ecotechnology
CDOM
Remote sensing
FT ICRMS
Soil erosion
Lake
title Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
title_full Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
title_fullStr Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
title_full_unstemmed Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
title_short Machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
title_sort machine learning reveals distinct aquatic organic matter patterns driven by soil erosion types
topic CDOM
Remote sensing
FT ICRMS
Soil erosion
Lake
url http://www.sciencedirect.com/science/article/pii/S2666498425000481
work_keys_str_mv AT yingxinshang machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes
AT kaishansong machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes
AT zhidanwen machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes
AT fengfalai machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes
AT geliu machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes
AT huitao machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes
AT xiangfeiyu machinelearningrevealsdistinctaquaticorganicmatterpatternsdrivenbysoilerosiontypes