Zhongyu Jin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhongyu Jin has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Fenghua Yu
College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China
1 shared publication - Hangbiao Ke
College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China
1 shared publication - Hongze Liu
School of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China
1 shared publication - Huini Cao
School of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China
1 shared publication - Shangrong Wu
Advanced Interdisciplinary Institute of Satellite Applications, Beijing Normal University, Beijing 100875, China
1 shared publication - Shilong Li
College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China
1 shared publication
Latest Publications
- Open Access
- 9 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2301
Integrating Multi-Source Remote Sensing and Meteorological Features for Fine Mapping of Crop in Liaoning Province
Accurate large-scale crop mapping is fundamental to agricultural management. However, in Liaoning Province, undulating terrain and fragmented fields make fine crop classification challenging. In particular, corn and soybean have overlapping phenologies, which can lead to spectral and structural confusion in conventional optical–SAR feature spaces and limit mapping accuracy. This study proposes a fine crop mapping framework integrating optical phenotypic, microwave structural, and meteorological time-series features. To overcome the curse of dimensionality caused by high-dimensional heterogeneous data, an adaptive feature truncation mechanism based on the transition pattern of the marginal-gain curve was designed. Additionally, a pyramid multi-scale sliding window algorithm was constructed to optimize meteorological features, achieving dimensionality reduction and precise identification of phenologically sensitive windows. The results indicate that: (1) The multi-scale feature selection strategy effectively eliminates redundant variables and maximizes the inter-class discriminability of core features, significantly improving computational efficiency and classification performance. (2) High-frequency meteorological features provide key physiological constraints. Specifically, mid-May shortwave radiation, early October precipitation, and early August growing degree days constitute the core environmental–physiological features for distinguishing confused crops, helping to mitigate the spectral confusion of dryland crops. (3) Driven by the multi-source features, the Support Vector Machine (SVM) exhibits the optimal generalization robustness for processing high-dimensional structured data, yielding an overall classification accuracy of 91.80% and a Kappa coefficient of 0.8905. This framework provides a reliable methodological reference for high-precision crop monitoring in large-scale complex planting areas.
- 9 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2301
Open AccessIntegrating Multi-Source Remote Sensing and Meteorological Features for Fine Mapping of Crop in Liaoning Province
Accurate large-scale crop mapping is fundamental to agricultural management. However, in Liaoning Province, undulating terrain and fragmented fields make fine crop classification challenging. In particular, corn and soybean have overlapping phenologies, which can lead to spectral and structural confusion in conventional optical–SAR feature spaces and limit mapping accuracy. This study proposes a fine crop mapping framework integrating optical phenotypic, microwave structural, and meteorological time-series features. To overcome the curse of dimensionality caused by high-dimensional heterogeneous data, an adaptive feature truncation mechanism based on the transition pattern of the marginal-gain curve was designed. Additionally, a pyramid multi-scale sliding window algorithm was constructed to optimize meteorological features, achieving dimensionality reduction and precise identification of phenologically sensitive windows. The results indicate that: (1) The multi-scale feature selection strategy effectively eliminates redundant variables and maximizes the inter-class discriminability of core features, significantly improving computational efficiency and classification performance. (2) High-frequency meteorological features provide key physiological constraints. Specifically, mid-May shortwave radiation, early October precipitation, and early August growing degree days constitute the core environmental–physiological features for distinguishing confused crops, helping to mitigate the spectral confusion of dryland crops. (3) Driven by the multi-source features, the Support Vector Machine (SVM) exhibits the optimal generalization robustness for processing high-dimensional structured data, yielding an overall classification accuracy of 91.80% and a Kappa coefficient of 0.8905. This framework provides a reliable methodological reference for high-precision crop monitoring in large-scale complex planting areas.
- Open Access
- 24 December 2024
- Published by MDPI AG in Agriculture
- Vol. 15 (1) , 11
Hyperspectral Remote Sensing Estimation of Rice Canopy LAI and LCC by UAV Coupled RTM and Machine Learning
Leaf chlorophyll content (LCC) and leaf area index (LAI) are crucial for rice growth and development, serving as key parameters for assessing nutritional status, growth, water management, and yield prediction. This study introduces a novel canopy radiative transfer model (RTM) by coupling the radiation transfer model for rice leaves (RPIOSL) and unified BRDF model (UBM) models, comparing its simulated canopy hyperspectra with those from the PROSAIL model. Characteristic wavelengths were extracted using Sobol sensitivity analysis and competitive adaptive reweighted sampling methods. Using these wavelengths, rice phenotype estimation models were constructed with back propagation neural network (BPNN), extreme learning machine (ELM), and broad learning system (BLS) methods. The results indicate that the RPIOSL-UBM model’s hyperspectra closely match measured data in the 500–650 nm and 750–1000 nm ranges, reducing the root mean square error (RMSE) by 0.0359 compared to the PROSAIL model. The ELM-based models using the RPIOSL-UBM dataset proved most effective for estimating the LAI and LCC, with RMSE values of 0.6357 and 6.0101 μg · cm−2, respectively. These values show significant improvements over the PROSAIL dataset models, with RMSE reductions of 0.1076 and 6.3297 μg · cm−2, respectively. The findings demonstrate that the proposed model can effectively estimate rice phenotypic parameters from UAV-measured hyperspectral data, offering a new approach to assess rice nutritional status and enhance cultivation efficiency and yield. This study underscores the potential of advanced modeling techniques in precision agriculture.
- 24 December 2024
- Published by MDPI AG in Agriculture
- Vol. 15 (1) , 11
Open AccessHyperspectral Remote Sensing Estimation of Rice Canopy LAI and LCC by UAV Coupled RTM and Machine Learning
Leaf chlorophyll content (LCC) and leaf area index (LAI) are crucial for rice growth and development, serving as key parameters for assessing nutritional status, growth, water management, and yield prediction. This study introduces a novel canopy radiative transfer model (RTM) by coupling the radiation transfer model for rice leaves (RPIOSL) and unified BRDF model (UBM) models, comparing its simulated canopy hyperspectra with those from the PROSAIL model. Characteristic wavelengths were extracted using Sobol sensitivity analysis and competitive adaptive reweighted sampling methods. Using these wavelengths, rice phenotype estimation models were constructed with back propagation neural network (BPNN), extreme learning machine (ELM), and broad learning system (BLS) methods. The results indicate that the RPIOSL-UBM model’s hyperspectra closely match measured data in the 500–650 nm and 750–1000 nm ranges, reducing the root mean square error (RMSE) by 0.0359 compared to the PROSAIL model. The ELM-based models using the RPIOSL-UBM dataset proved most effective for estimating the LAI and LCC, with RMSE values of 0.6357 and 6.0101 μg · cm−2, respectively. These values show significant improvements over the PROSAIL dataset models, with RMSE reductions of 0.1076 and 6.3297 μg · cm−2, respectively. The findings demonstrate that the proposed model can effectively estimate rice phenotypic parameters from UAV-measured hyperspectral data, offering a new approach to assess rice nutritional status and enhance cultivation efficiency and yield. This study underscores the potential of advanced modeling techniques in precision agriculture.