Guangchao Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guangchao Yang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Chunli Li
School of Civil Engineering, Qingdao University of Technology, Qingdao, China
2 shared publicationsJiaojiao Tang
School of Civil Engineering, Chang’an University, Xi’an, China
2 shared publicationsJunfang Zheng
School of Civil Engineering, Chang’an University, Xi’an, China
2 shared publicationsXiaoli Zhao
School of Civil Engineering, Qingdao University of Technology, Qingdao, China
2 shared publications- Jian Zhang
College of Transportation, Shandong University of Science and Technology, Qingdao 266590, China
1 shared publication - Jigang Zhang
School of Civil Engineering, Qingdao University of Technology, Qingdao 266520, China
1 shared publication
Latest Publications
- 1 October 2024
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 31 (49) , 58795-58817
Carbon emission prediction in a region of Hainan Province based on improved STIRPAT model
In 2020, China pledged carbon reduction targets at the United Nations: peaking emissions by 2030 and achieving carbon neutrality by 2060. Research and prediction of regional carbon emissions are crucial for achieving these dual carbon targets across China. This study aims to construct an indicator system for regional carbon emissions and utilize it for forecasting. Analyzing carbon emission data from a specific area in Hainan Province from 2010 to 2020, we established an indicator system. Using the interpretable SHAP model, we assessed indicator importance and trends. Employing an improved STIRPAT model with partial least squares regression to address multicollinearity among influencing factors, we developed a carbon emission prediction model. Based on this, we forecasted carbon emissions from 2021 to 2060 in the specified area under three scenarios: natural, baseline, and ambitious. The results show that the growth of resident population and per capita GDP has the most significant promoting effect on carbon emissions in the region while optimizing industrial structure, energy consumption structure, and reducing energy intensity will inhibit carbon emissions. The prediction results indicate that in the natural scenario, regional carbon emissions will peak in 2035, and achieving carbon neutrality by 2060 is not feasible, while the baseline scenario and ambitious scenario can achieve the dual carbon targets on time or even earlier. The research results of this article provide a reference method for predicting carbon emissions in other regions and a guide for future regional emission reduction.
- 1 October 2024
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 31 (49) , 58795-58817
Carbon emission prediction in a region of Hainan Province based on improved STIRPAT model
In 2020, China pledged carbon reduction targets at the United Nations: peaking emissions by 2030 and achieving carbon neutrality by 2060. Research and prediction of regional carbon emissions are crucial for achieving these dual carbon targets across China. This study aims to construct an indicator system for regional carbon emissions and utilize it for forecasting. Analyzing carbon emission data from a specific area in Hainan Province from 2010 to 2020, we established an indicator system. Using the interpretable SHAP model, we assessed indicator importance and trends. Employing an improved STIRPAT model with partial least squares regression to address multicollinearity among influencing factors, we developed a carbon emission prediction model. Based on this, we forecasted carbon emissions from 2021 to 2060 in the specified area under three scenarios: natural, baseline, and ambitious. The results show that the growth of resident population and per capita GDP has the most significant promoting effect on carbon emissions in the region while optimizing industrial structure, energy consumption structure, and reducing energy intensity will inhibit carbon emissions. The prediction results indicate that in the natural scenario, regional carbon emissions will peak in 2035, and achieving carbon neutrality by 2060 is not feasible, while the baseline scenario and ambitious scenario can achieve the dual carbon targets on time or even earlier. The research results of this article provide a reference method for predicting carbon emissions in other regions and a guide for future regional emission reduction.
- Open Access
- 28 December 2023
- Published by Springer Nature in Research Square
Carbon Emission Prediction in a Region ofHainan Province Based on Improved STIRPAT Model
In 2020, China announced significant carbon reduction targets at the United Nations General Assembly: peaking of carbon emissions by 2030 and achieving carbon neutrality before 2060. Research and prediction of regional carbon emissions are crucial for achieving these dual carbon targets across China. This article aims to construct an index system for regional carbon emissions and use this index system to predict carbon emissions in a specific area of Hainan province. By analyzing the current situation of the region, the article uses the interpretable SHAP model to analyze the importance contribution and impact trends of the indicators. Based on an improved STIRPAT model and scenario analysis, the article predicts carbon emissions in the specific area of Hainan province. The results show that the growth of resident population and per capita GDP has the most significant promoting effect on carbon emissions in the region while optimizing industrial structure, energy consumption structure, and reducing energy intensity will inhibit carbon emissions. The prediction results indicate that in the natural scenario, regional carbon emissions will peak in 2035, and achieving carbon neutrality by 2060 is not feasible, while the baseline scenario and ambitious scenario can achieve the dual carbon targets on time or even earlier. The research results of this article provide a reference method for predicting carbon emissions in other regions and a guide for future regional emission reduction.
- 28 December 2023
- Published by Springer Nature in Research Square
Open AccessCarbon Emission Prediction in a Region ofHainan Province Based on Improved STIRPAT Model
In 2020, China announced significant carbon reduction targets at the United Nations General Assembly: peaking of carbon emissions by 2030 and achieving carbon neutrality before 2060. Research and prediction of regional carbon emissions are crucial for achieving these dual carbon targets across China. This article aims to construct an index system for regional carbon emissions and use this index system to predict carbon emissions in a specific area of Hainan province. By analyzing the current situation of the region, the article uses the interpretable SHAP model to analyze the importance contribution and impact trends of the indicators. Based on an improved STIRPAT model and scenario analysis, the article predicts carbon emissions in the specific area of Hainan province. The results show that the growth of resident population and per capita GDP has the most significant promoting effect on carbon emissions in the region while optimizing industrial structure, energy consumption structure, and reducing energy intensity will inhibit carbon emissions. The prediction results indicate that in the natural scenario, regional carbon emissions will peak in 2035, and achieving carbon neutrality by 2060 is not feasible, while the baseline scenario and ambitious scenario can achieve the dual carbon targets on time or even earlier. The research results of this article provide a reference method for predicting carbon emissions in other regions and a guide for future regional emission reduction.
- Open Access
- 17 November 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (22) , 12433
Prediction of Failure Modes of Steel Tube-Reinforced Concrete Shear Walls Using Blending Fusion Model Based on Generative Adversarial Networks Data Augmentation
The steel tube-reinforced concrete (STRC) shear wall plays an important role in the seismic design of high-rise building structures. Due to the synergistic collaboration between steel tubes and concrete, they effectively enhance the ductility and energy dissipation capacity of conventional shear walls. To identify vulnerable areas prone to brittle failure and optimize the design, it is essential to develop a rapid method for identifying the failure mode of STRC shear walls. In this study, a fast identification method of STCR shear wall failure modes based on a Blending fusion model with Generative Adversarial Network (GAN) augmented data is proposed. The GAN is employed to address the issue of inadequate experimental data by generating new samples. This method combines classification boosting (Catboost), Random Forest (RF), K-Nearest Neighbors (KNN), and Least Absolute Shrinkage and Selection Operator (LASSO) to establish the Blending-CRKL fusion model to improve the prediction accuracy of the failure mode of STRC shear walls. The results reveal a significant improvement in the prediction performance of KNN, Backpropagation Neural Network (BPNN), RF, Light Gradient Boosting Machine (LightGBM), Catboost, and Blending-CRKL models after augmenting the training set with GAN. On average, the accuracy increased by 13%, precision increased by 81%, recall increased by 48%, and F1 score increased by 67%. The proposed Blending-CRKL fusion model outperforms the tested KNN, BPNN, RF, LightGBM, and Catboost models, achieving an accuracy rate of 97% in predicting the failure mode of STRC shear walls. Additionally, the stability and robustness of the Blending-CRKL model were validated, while the important features and value ranges of different failure modes were analyzed. This study provides a reference for the rapid identification of the failure mode of STRC shear walls.
- 17 November 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (22) , 12433
Open AccessPrediction of Failure Modes of Steel Tube-Reinforced Concrete Shear Walls Using Blending Fusion Model Based on Generative Adversarial Networks Data Augmentation
The steel tube-reinforced concrete (STRC) shear wall plays an important role in the seismic design of high-rise building structures. Due to the synergistic collaboration between steel tubes and concrete, they effectively enhance the ductility and energy dissipation capacity of conventional shear walls. To identify vulnerable areas prone to brittle failure and optimize the design, it is essential to develop a rapid method for identifying the failure mode of STRC shear walls. In this study, a fast identification method of STCR shear wall failure modes based on a Blending fusion model with Generative Adversarial Network (GAN) augmented data is proposed. The GAN is employed to address the issue of inadequate experimental data by generating new samples. This method combines classification boosting (Catboost), Random Forest (RF), K-Nearest Neighbors (KNN), and Least Absolute Shrinkage and Selection Operator (LASSO) to establish the Blending-CRKL fusion model to improve the prediction accuracy of the failure mode of STRC shear walls. The results reveal a significant improvement in the prediction performance of KNN, Backpropagation Neural Network (BPNN), RF, Light Gradient Boosting Machine (LightGBM), Catboost, and Blending-CRKL models after augmenting the training set with GAN. On average, the accuracy increased by 13%, precision increased by 81%, recall increased by 48%, and F1 score increased by 67%. The proposed Blending-CRKL fusion model outperforms the tested KNN, BPNN, RF, LightGBM, and Catboost models, achieving an accuracy rate of 97% in predicting the failure mode of STRC shear walls. Additionally, the stability and robustness of the Blending-CRKL model were validated, while the important features and value ranges of different failure modes were analyzed. This study provides a reference for the rapid identification of the failure mode of STRC shear walls.
- Open Access
Prediction and Interpretation of Residual Bearing Capacity of Cfst Columns under Impact Loads Based Interpretable Stacking Fusion Modeling
The utilization of Concrete-filled steel Tubular (CFST) columns is increasingly widespread. However, the assessment of the residual bearing capacity of CFST columns currently relies mainly on costly and time-consuming experiments and numerical simulations. In this study, we propose a machine learning-based model for rapidly identifying the residual bearing capacity of CFST columns. The results demonstrate that the predictions of the proposed Stacking-KRXL model align well with the actual values, with most prediction errors falling within ±10%. The RSquared value of 0.97 significantly surpasses that of other methods. The stability and robustness of the model are analyzed. Additionally, the Shapley additive explanations method is applied for global and local interpretations, revealing positive or negative correlations between different parameters and the residual bearing capacity of CFST columns, mainly influenced by the concrete area in the core region.
Open AccessPrediction and Interpretation of Residual Bearing Capacity of Cfst Columns under Impact Loads Based Interpretable Stacking Fusion Modeling
The utilization of Concrete-filled steel Tubular (CFST) columns is increasingly widespread. However, the assessment of the residual bearing capacity of CFST columns currently relies mainly on costly and time-consuming experiments and numerical simulations. In this study, we propose a machine learning-based model for rapidly identifying the residual bearing capacity of CFST columns. The results demonstrate that the predictions of the proposed Stacking-KRXL model align well with the actual values, with most prediction errors falling within ±10%. The RSquared value of 0.97 significantly surpasses that of other methods. The stability and robustness of the model are analyzed. Additionally, the Shapley additive explanations method is applied for global and local interpretations, revealing positive or negative correlations between different parameters and the residual bearing capacity of CFST columns, mainly influenced by the concrete area in the core region.