Guochen Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guochen Li has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Yunting Fang
CAS Key Laboratory of Forest Ecology and Management, Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang 110016, China
5 shared publications - Ang Wang
CAS Key Laboratory of Forest Ecology and Management, Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang 110016, China
2 shared publications Boyuan Bi
2 shared publications- Chao Wang
CAS Key Laboratory of Forest Ecology and Silviculture Institute of Applied Ecology, Chinese Academy of Sciences Shenyang Liaoning China
2 shared publications - Huimin Dai
Key Laboratory of Black Soil Evolution and Ecological Effect, Ministry of Natural Resources/Liaoning Province, Shenyang 110034, China
2 shared publications - Nana Fang
China Geological Survey Shenyang Center, Shenyang 110034, China
2 shared publications
Latest Publications
- Open Access
Improved Inversion and Digital Mapping of Soil Organic Carbon Content by Combining Crop-Lush Period Vegetation Indices with Ensemble Learning: A Case Study for Liaoning, Northeast China
Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modeling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; and MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that (1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modeling strategies; (2) for XGBoost, MS-1 yielded the highest inversion accuracy (R2 = 0.84, RMSE = 2.22 g·kg−1, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg−1, increased R2 from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg−1, increased R2 from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; (3) based on the SHAP analysis of the three modeling strategies, it is considered that precipitation, terrain and terrain analysis results are important indicators for SOC content inversion, and it is confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and (4) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg−1), with values ranging from 2.19 g·kg−1 (sandy central–western area) to 33.86 g·kg−1 (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction.
Open AccessImproved Inversion and Digital Mapping of Soil Organic Carbon Content by Combining Crop-Lush Period Vegetation Indices with Ensemble Learning: A Case Study for Liaoning, Northeast China
Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modeling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; and MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that (1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modeling strategies; (2) for XGBoost, MS-1 yielded the highest inversion accuracy (R2 = 0.84, RMSE = 2.22 g·kg−1, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg−1, increased R2 from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg−1, increased R2 from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; (3) based on the SHAP analysis of the three modeling strategies, it is considered that precipitation, terrain and terrain analysis results are important indicators for SOC content inversion, and it is confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and (4) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg−1), with values ranging from 2.19 g·kg−1 (sandy central–western area) to 33.86 g·kg−1 (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction.
- Open Access
- 22 August 2025
- Published by MDPI AG in Preprints.org
Improved Inversion and Digital Mapping of Soil Organic Carbon Content by Combining Crop-Lush Period Vegetation Indices with Ensemble Learning: A Case Study in Liaoning, Northeast China
Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modelling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that 1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modelling strategies; 2) for XGBoost, MS-1 yielded the highest inversion accuracy (R² = 0.84, RMSE = 2.22 g·kg⁻¹, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg⁻¹, increased R² from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg⁻¹, increased R² from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; 2) SHAP analysis confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and 3) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg⁻¹), with values ranging from 2.19 g·kg⁻¹ (sandy central–western area) to 33.86 g·kg⁻¹ (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction.
- 22 August 2025
- Published by MDPI AG in Preprints.org
Open AccessImproved Inversion and Digital Mapping of Soil Organic Carbon Content by Combining Crop-Lush Period Vegetation Indices with Ensemble Learning: A Case Study in Liaoning, Northeast China
Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modelling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that 1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modelling strategies; 2) for XGBoost, MS-1 yielded the highest inversion accuracy (R² = 0.84, RMSE = 2.22 g·kg⁻¹, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg⁻¹, increased R² from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg⁻¹, increased R² from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; 2) SHAP analysis confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and 3) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg⁻¹), with values ranging from 2.19 g·kg⁻¹ (sandy central–western area) to 33.86 g·kg⁻¹ (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction.
- Open Access
- 8 August 2025
- Published by Springer Nature in Communications Earth & Environment
Divergent responses of carbon and nitrogen functional genes composition to enhanced rock weathering
Enhanced rock weathering (ERW) is a scalable strategy for atmospheric carbon dioxide removal. The microbiome function critically regulates the below-ground cycle of carbon and nitrogen in terrestrial ecosystems. However, microbial functioning related to carbon and nitrogen under ERW remains elusive. Here we investigated how wollastonite addition affects key microbial carbon and nitrogen-cycles genes investigated using metagenomic, in a tropic rubber plantation. After two-year, ERW had enhanced the alpha diversity of biogeochemical cycling genes was mainly driven by increased soil pH. ERW led to an increase in the relative abundance of carbon-fixation genes, and a decrease in the carbon-degradation genes, providing microbiological evidence for carbon dioxide emissions. Additionally, the relative abundance of nitrogen-cycling functional genes, and available iron increased after wollastonite addition, indicating ERW may influence nitrous oxide emissions through biological and chemical processes. Altogether, our results illustrate how the effect of ERW alters microbial functioning, impacting soil organic matter dynamics.
- 8 August 2025
- Published by Springer Nature in Communications Earth & Environment
Open AccessDivergent responses of carbon and nitrogen functional genes composition to enhanced rock weathering
Enhanced rock weathering (ERW) is a scalable strategy for atmospheric carbon dioxide removal. The microbiome function critically regulates the below-ground cycle of carbon and nitrogen in terrestrial ecosystems. However, microbial functioning related to carbon and nitrogen under ERW remains elusive. Here we investigated how wollastonite addition affects key microbial carbon and nitrogen-cycles genes investigated using metagenomic, in a tropic rubber plantation. After two-year, ERW had enhanced the alpha diversity of biogeochemical cycling genes was mainly driven by increased soil pH. ERW led to an increase in the relative abundance of carbon-fixation genes, and a decrease in the carbon-degradation genes, providing microbiological evidence for carbon dioxide emissions. Additionally, the relative abundance of nitrogen-cycling functional genes, and available iron increased after wollastonite addition, indicating ERW may influence nitrous oxide emissions through biological and chemical processes. Altogether, our results illustrate how the effect of ERW alters microbial functioning, impacting soil organic matter dynamics.
- 30 November 2024
- Published by Elsevier in Journal of Environmental Management
- Vol. 373, 123477
Enhanced rock weathering boosts ecosystem multifunctionality via improving microbial networks complexity in a tropical forest plantation
- 30 November 2024
- Published by Elsevier in Journal of Environmental Management
- Vol. 373, 123477
Enhanced rock weathering boosts ecosystem multifunctionality via improving microbial networks complexity in a tropical forest plantation
- Top Cited PapersOpen Access
- 23 August 2023
- Published by Oxford University Press (OUP) in ISME Communications
- Vol. 3 (1) , 1-10
Integrating microbial community properties, biomass and necromass to predict cropland soil organic carbon
Manipulating microorganisms to increase soil organic carbon (SOC) in croplands remains a challenge. Soil microbes are important drivers of SOC sequestration, especially via their necromass accumulation. However, microbial parameters are rarely used to predict cropland SOC stocks, possibly due to uncertainties regarding the relationships between microbial carbon pools, community properties and SOC. Herein we evaluated the microbial community properties (diversity and network complexity), microbial carbon pools (biomass and necromass carbon) and SOC in 468 cropland soils across northeast China. We found that not only microbial necromass carbon but also microbial community properties (diversity and network complexity) and biomass carbon were correlated with SOC. Microbial biomass carbon and diversity played more important role in predicting SOC for maize, while microbial network complexity was more important for rice. Models to predict SOC performed better when the microbial community and microbial carbon pools were included simultaneously. Taken together our results suggest that microbial carbon pools and community properties influence SOC accumulation in croplands, and management practices that improve these microbial parameters may increase cropland SOC levels.
- 23 August 2023
- Published by Oxford University Press (OUP) in ISME Communications
- Vol. 3 (1) , 1-10
Top Cited PapersOpen AccessIntegrating microbial community properties, biomass and necromass to predict cropland soil organic carbon
Manipulating microorganisms to increase soil organic carbon (SOC) in croplands remains a challenge. Soil microbes are important drivers of SOC sequestration, especially via their necromass accumulation. However, microbial parameters are rarely used to predict cropland SOC stocks, possibly due to uncertainties regarding the relationships between microbial carbon pools, community properties and SOC. Herein we evaluated the microbial community properties (diversity and network complexity), microbial carbon pools (biomass and necromass carbon) and SOC in 468 cropland soils across northeast China. We found that not only microbial necromass carbon but also microbial community properties (diversity and network complexity) and biomass carbon were correlated with SOC. Microbial biomass carbon and diversity played more important role in predicting SOC for maize, while microbial network complexity was more important for rice. Models to predict SOC performed better when the microbial community and microbial carbon pools were included simultaneously. Taken together our results suggest that microbial carbon pools and community properties influence SOC accumulation in croplands, and management practices that improve these microbial parameters may increase cropland SOC levels.
- Open Access
- 8 June 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (12) , 6526
Identifying the Source of Heavy Metal Pollution and Apportionment in Agricultural Soils Impacted by Different Smelters in China by the Positive Matrix Factorization Model and the Pb Isotope Ratio Method
In this study, the agricultural soil around Zhuzhou Smelter in Zhuzhou district, Hunan, China and Huludao Zinc Plant in Huludao district, Liaoning, China was selected as the research area to discuss the current situation of heavy metal pollution in the surrounding agricultural soil caused by different smelting plants for soil environmental management and sustainable development of soil resources. Eight elements’ (Cd, Pb, As, Hg, Cr, Ni, Cu, and Zn) contents were measured to assess their pollution risk level and spatial distribution distinction. Correlation analysis, the positive matrix factorization (PMF), and Pb isotope ratio method were employed to analyze the sources of soil heavy metal pollution in the research area. The contents of Cd, Pb, Hg, and Zn in the soil of the two research areas were seriously polluted, and the changes of their spatial content were related to the migration and sedimentation of the smelter waste gas. Four types of pollution sources, including the smelting source, agricultural sources, natural sources, and mixed sources of industrial activity and traffic were identified in both areas by PMF, and the contribution rates of the four pollution sources in both areas were similar. Taking the agricultural soil around Huludao Zinc Plant as an example, the contribution rates of the different pollution sources analyzed by Pb isotope ratio method were the lead smelting source (43.7%), followed by the agricultural source (34.6%), traffic source (14.2%), and natural source (7.5%), which were basically consistent with that of PMF analysis, verifying the reliability of the two methods. The results above showed that the smelters were the main cause of heavy metal pollution in agricultural soils around the two research areas, and the analysis results of element content ratio and smelting source characteristic element contribution rate ratio could provide reference for the analysis of heavy metal pollution in agricultural soil around smelters for soil pollution control decision making.
- 8 June 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (12) , 6526
Open AccessIdentifying the Source of Heavy Metal Pollution and Apportionment in Agricultural Soils Impacted by Different Smelters in China by the Positive Matrix Factorization Model and the Pb Isotope Ratio Method
In this study, the agricultural soil around Zhuzhou Smelter in Zhuzhou district, Hunan, China and Huludao Zinc Plant in Huludao district, Liaoning, China was selected as the research area to discuss the current situation of heavy metal pollution in the surrounding agricultural soil caused by different smelting plants for soil environmental management and sustainable development of soil resources. Eight elements’ (Cd, Pb, As, Hg, Cr, Ni, Cu, and Zn) contents were measured to assess their pollution risk level and spatial distribution distinction. Correlation analysis, the positive matrix factorization (PMF), and Pb isotope ratio method were employed to analyze the sources of soil heavy metal pollution in the research area. The contents of Cd, Pb, Hg, and Zn in the soil of the two research areas were seriously polluted, and the changes of their spatial content were related to the migration and sedimentation of the smelter waste gas. Four types of pollution sources, including the smelting source, agricultural sources, natural sources, and mixed sources of industrial activity and traffic were identified in both areas by PMF, and the contribution rates of the four pollution sources in both areas were similar. Taking the agricultural soil around Huludao Zinc Plant as an example, the contribution rates of the different pollution sources analyzed by Pb isotope ratio method were the lead smelting source (43.7%), followed by the agricultural source (34.6%), traffic source (14.2%), and natural source (7.5%), which were basically consistent with that of PMF analysis, verifying the reliability of the two methods. The results above showed that the smelters were the main cause of heavy metal pollution in agricultural soils around the two research areas, and the analysis results of element content ratio and smelting source characteristic element contribution rate ratio could provide reference for the analysis of heavy metal pollution in agricultural soil around smelters for soil pollution control decision making.