Bingzi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bingzi Li has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Xiaolong Cheng
College of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
2 shared publications - Moye Li
College of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
1 shared publication - Weifeng He
School of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
1 shared publication - Yangzhong Ke
College of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
1 shared publication - Yuemei Huang
College of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
1 shared publication - Zhirong Wen
School of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
1 shared publication
Latest Publications
- Open Access
Land Use Classification in Rare Earth Mining Areas Based on Multi-Source Remote Sensing and Feature Optimization
Rare earth elements are vital, non-renewable strategic resources, and their exploitation has significant impacts on regional ecological security and sustainable development. To address the issue of insufficient accuracy in land use classification in rare earth mining areas, this study takes the Lingbei rare earth mining area in Dingnan County, Jiangxi Province, as a case study. Multi-source remote sensing data, including Sentinel-2 imagery, Sentinel-1 SAR data, nighttime light data, and DEM data, were integrated to construct a feature set combining spectral, textural, and topographic information. On this basis, this study developed a feature optimization framework that combines recursive feature elimination (RFE), mean decrease accuracy (MDA), and K-fold cross-validation (CV), termed RFE-MDA-CV. We designed nine feature combination schemes and compared them with the optimal feature subset. Their performance was systematically evaluated across four classifiers: RF, SVM, CART, and GBDT. The results were as follows: (1) the optimized feature set combined with the RF classifier consistently achieved the highest classification performance, with a mean OA of approximately 93.2% and a kappa coefficient of about 0.916, outperforming CART and SVM by around 4-5 percentage points; (2) land use remained generally stable between 2016 and 2023, but frequent conversions occurred between forest land, cropland, and impervious surfaces, mainly driven by urban expansion and mining activities; and (3) cross-regional experiments demonstrated that the proposed feature optimization framework has good applicability and transferability in mining areas with similar geomorphological and metallogenic conditions. Overall, the proposed RFE-MDA-CV method can be effectively implemented on the Google Earth Engine platform, significantly improving the accuracy and robustness of land use classification in rare earth mining areas, while providing reliable technical support for ecological monitoring and land resource management.
Open AccessLand Use Classification in Rare Earth Mining Areas Based on Multi-Source Remote Sensing and Feature Optimization
Rare earth elements are vital, non-renewable strategic resources, and their exploitation has significant impacts on regional ecological security and sustainable development. To address the issue of insufficient accuracy in land use classification in rare earth mining areas, this study takes the Lingbei rare earth mining area in Dingnan County, Jiangxi Province, as a case study. Multi-source remote sensing data, including Sentinel-2 imagery, Sentinel-1 SAR data, nighttime light data, and DEM data, were integrated to construct a feature set combining spectral, textural, and topographic information. On this basis, this study developed a feature optimization framework that combines recursive feature elimination (RFE), mean decrease accuracy (MDA), and K-fold cross-validation (CV), termed RFE-MDA-CV. We designed nine feature combination schemes and compared them with the optimal feature subset. Their performance was systematically evaluated across four classifiers: RF, SVM, CART, and GBDT. The results were as follows: (1) the optimized feature set combined with the RF classifier consistently achieved the highest classification performance, with a mean OA of approximately 93.2% and a kappa coefficient of about 0.916, outperforming CART and SVM by around 4-5 percentage points; (2) land use remained generally stable between 2016 and 2023, but frequent conversions occurred between forest land, cropland, and impervious surfaces, mainly driven by urban expansion and mining activities; and (3) cross-regional experiments demonstrated that the proposed feature optimization framework has good applicability and transferability in mining areas with similar geomorphological and metallogenic conditions. Overall, the proposed RFE-MDA-CV method can be effectively implemented on the Google Earth Engine platform, significantly improving the accuracy and robustness of land use classification in rare earth mining areas, while providing reliable technical support for ecological monitoring and land resource management.
- Open Access
- 17 February 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (4) , 2038
Time Series-Based PM2.5 Concentration Prediction Model Incorporating Attention Mechanism
As a key indicator of air quality, effective forecasting of concentration can provide key technical support for the scientific and precise implementation of air pollution prevention and control. However, predicting concentrations faces challenges such as multiple influencing factors, long-term temporal dependencies, and inherent nonlinearity. Furthermore, traditional Long Short-Term Memory (LSTM) networks not only fail to effectively grasp the dependency relationships in long-time-span data, but also encounter difficulties in fully integrating and exploiting the information of numerous influencing factors. In order to solve these problems, a novel prediction model (OVMD–PeepholeLSTM–attention) for concentration was presented in this study, which includes Peephole Long Short-Term Memory (PeepholeLSTM), optimal variational mode decomposition (OVMD) and an attention mechanism (AM). In this study, K modal components result from the initial decomposition of monitoring data using OVMD. The obtained components are then individually predicted by the PeepholeLSTM–attention model, and the final prediction is reconstructed. The proposed model was comprehensively evaluated on concentration monitoring data sets from Guangzhou and Shenzhen in China from 2020 to 2022, through a series of comparative experiments. The model proposed in this study is shown by experimental results to reduce mean absolute error (MAE) by approximately 39%, root mean square error (RMSE) by 45%, and increases the fitting coefficient () by 0.0457 in Guangzhou compared to the single PeepholeLSTM model. The corresponding improvements in Shenzhen are 45% for MAE, 51% for RMSE, and 0.0765 for . This indicates that the model proposed in this paper exhibits higher accuracy in terms of predicting concentrations, and the research results can provide a basis for quantitative assessment and scientific decision-making for the sustainable development of urban ecological environments.- 17 February 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (4) , 2038
Open AccessTime Series-Based PM2.5 Concentration Prediction Model Incorporating Attention Mechanism
As a key indicator of air quality, effective forecasting of concentration can provide key technical support for the scientific and precise implementation of air pollution prevention and control. However, predicting concentrations faces challenges such as multiple influencing factors, long-term temporal dependencies, and inherent nonlinearity. Furthermore, traditional Long Short-Term Memory (LSTM) networks not only fail to effectively grasp the dependency relationships in long-time-span data, but also encounter difficulties in fully integrating and exploiting the information of numerous influencing factors. In order to solve these problems, a novel prediction model (OVMD–PeepholeLSTM–attention) for concentration was presented in this study, which includes Peephole Long Short-Term Memory (PeepholeLSTM), optimal variational mode decomposition (OVMD) and an attention mechanism (AM). In this study, K modal components result from the initial decomposition of monitoring data using OVMD. The obtained components are then individually predicted by the PeepholeLSTM–attention model, and the final prediction is reconstructed. The proposed model was comprehensively evaluated on concentration monitoring data sets from Guangzhou and Shenzhen in China from 2020 to 2022, through a series of comparative experiments. The model proposed in this study is shown by experimental results to reduce mean absolute error (MAE) by approximately 39%, root mean square error (RMSE) by 45%, and increases the fitting coefficient () by 0.0457 in Guangzhou compared to the single PeepholeLSTM model. The corresponding improvements in Shenzhen are 45% for MAE, 51% for RMSE, and 0.0765 for . This indicates that the model proposed in this paper exhibits higher accuracy in terms of predicting concentrations, and the research results can provide a basis for quantitative assessment and scientific decision-making for the sustainable development of urban ecological environments.