Xue Ding
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xue Ding has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Jinliang Wang
Faculty of Geography, Yunnan Normal University, Kunming, People’s Republic of China
4 shared publications - Rongxiang Luo
School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China
4 shared publications - Shuangyun Peng
Faculty of Geography, Yunnan Normal University, Kunming, China
4 shared publications Jinliang Wang
Faculty of Geography, Yunnan Normal University
3 shared publicationsShuangyun Peng
Faculty of Geography, Yunnan Normal University
3 shared publications- Fapeng Cai
Faculty of Geography, Yunnan Normal University, Kunming 650500, China
2 shared publications
Latest Publications
- Open Access
- 5 November 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1943117
CGW-DETR: a multi-scale feature enhanced RT-DETR Qianxi cherry tomato maturity detection model for dense small targets
Detecting the ripeness of QianXi cherry Tomatoes is critical to intelligent harvesting. There are three major challenges associated with this task: (1) Complex environmental interference makes it difficult to extract surface features from the tomatoes; (2) High rates of missed detections and false positives when detecting densely clustered small targets; (3) High computational costs due to the large number of model parameters and the significant computational load. To address these challenges, this study proposes a lightweight detection model, CGW-DETR, based on an improved RT-DETR architecture. First, we propose a lightweight feature enhancement module, CAS, to optimize target feature perception and suppress interference from complex backgrounds. Second, we introduce a gradient-space pyramid pooling layer (GSPP) that balances local and global feature extraction through multi-scale spatial pyramid pooling and an efficient layer aggregation network, improving the model’s detection of small and densely clustered targets. Finally, we introduce the WIoU loss function and optimize the gradient gain allocation strategy to improve detection accuracy while maintaining the model’s low computational complexity. Experimental results show that, on our self-built QianXi cherry Tomato ripeness detection dataset, compared to the baseline model RT-DETR, the proposed model achieves a detection accuracy of 94.2% (an increase of 2.0%), a recall rate of 88.2% (an increase of 4.4%), an mAP50 of 91.3% (an increase of 3.1%), and an mAP50:95 of 74.6% (an increase of 5.5%). Under the experimental settings of this study, CGW-DETR showed relatively favorable detection results for densely distributed small-scale QianXi cherry tomatoes in complex environments. Its performance was compared with several mainstream models on the self-built dataset.
- 5 November 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1943117
Open AccessCGW-DETR: a multi-scale feature enhanced RT-DETR Qianxi cherry tomato maturity detection model for dense small targets
Detecting the ripeness of QianXi cherry Tomatoes is critical to intelligent harvesting. There are three major challenges associated with this task: (1) Complex environmental interference makes it difficult to extract surface features from the tomatoes; (2) High rates of missed detections and false positives when detecting densely clustered small targets; (3) High computational costs due to the large number of model parameters and the significant computational load. To address these challenges, this study proposes a lightweight detection model, CGW-DETR, based on an improved RT-DETR architecture. First, we propose a lightweight feature enhancement module, CAS, to optimize target feature perception and suppress interference from complex backgrounds. Second, we introduce a gradient-space pyramid pooling layer (GSPP) that balances local and global feature extraction through multi-scale spatial pyramid pooling and an efficient layer aggregation network, improving the model’s detection of small and densely clustered targets. Finally, we introduce the WIoU loss function and optimize the gradient gain allocation strategy to improve detection accuracy while maintaining the model’s low computational complexity. Experimental results show that, on our self-built QianXi cherry Tomato ripeness detection dataset, compared to the baseline model RT-DETR, the proposed model achieves a detection accuracy of 94.2% (an increase of 2.0%), a recall rate of 88.2% (an increase of 4.4%), an mAP50 of 91.3% (an increase of 3.1%), and an mAP50:95 of 74.6% (an increase of 5.5%). Under the experimental settings of this study, CGW-DETR showed relatively favorable detection results for densely distributed small-scale QianXi cherry tomatoes in complex environments. Its performance was compared with several mainstream models on the self-built dataset.
- Open Access
- 28 July 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1897082
WaveletUMamba: a frequency-enhanced state space model for extraction of multi-stage celery planting areas from UAV imagery
In the task of extracting celery cultivation areas across different growth stages from high-resolution UAV remote sensing imagery, the original Mamba model exhibits a bias toward low-frequency information during state-space modeling and responds relatively poorly to high-frequency details such as boundaries and textures, thereby affecting its ability to characterize fine-grained spatial structures in complex scenes. To address this issue, this paper proposes a WaveletUMamba network that integrates frequency-domain enhancement with state-space modeling. First, a Low-Frequency Masking High-Frequency Enhancer (LFM-HFE) was designed to enhance high-frequency information—such as edges and textures—based on two-dimensional Haar wavelet decomposition, thereby compensating for the state-space model’s shortcomings in modeling local details. Second, a Dual-Gated Frequency-Spatial State-Space Module (DG-SSM) was constructed to achieve the synergistic fusion of high-frequency detail features with the global state-space modeling process, thereby enhancing the model’s ability to represent complex spatial structures. Finally, to mitigate category confusion caused by similar textural and spectral features across different growth stages, a Context-Guided Feature Supervision module (CGFS) was designed to enhance the discriminative power and consistency of intermediate layer features through global semantic constraints. Experimental results show that this method achieves 88.70% and 93.90% for the mIoU and mF1 metrics, respectively—representing improvements of 1.07% and 0.30% over the second-best model, UNetMamba—while striking an optimal balance between extraction accuracy and computational efficiency. Ablation experiments and visualization results further validate the effectiveness of each module. The WaveletUMamba framework proposed in this paper offers a new methodological approach for the precise extraction of crop planting areas across multiple growth stages in complex open-field agricultural environments, while also providing a technical solution for the practical application of UAV remote sensing technology in extracting crop planting areas.
- 28 July 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1897082
Open AccessWaveletUMamba: a frequency-enhanced state space model for extraction of multi-stage celery planting areas from UAV imagery
In the task of extracting celery cultivation areas across different growth stages from high-resolution UAV remote sensing imagery, the original Mamba model exhibits a bias toward low-frequency information during state-space modeling and responds relatively poorly to high-frequency details such as boundaries and textures, thereby affecting its ability to characterize fine-grained spatial structures in complex scenes. To address this issue, this paper proposes a WaveletUMamba network that integrates frequency-domain enhancement with state-space modeling. First, a Low-Frequency Masking High-Frequency Enhancer (LFM-HFE) was designed to enhance high-frequency information—such as edges and textures—based on two-dimensional Haar wavelet decomposition, thereby compensating for the state-space model’s shortcomings in modeling local details. Second, a Dual-Gated Frequency-Spatial State-Space Module (DG-SSM) was constructed to achieve the synergistic fusion of high-frequency detail features with the global state-space modeling process, thereby enhancing the model’s ability to represent complex spatial structures. Finally, to mitigate category confusion caused by similar textural and spectral features across different growth stages, a Context-Guided Feature Supervision module (CGFS) was designed to enhance the discriminative power and consistency of intermediate layer features through global semantic constraints. Experimental results show that this method achieves 88.70% and 93.90% for the mIoU and mF1 metrics, respectively—representing improvements of 1.07% and 0.30% over the second-best model, UNetMamba—while striking an optimal balance between extraction accuracy and computational efficiency. Ablation experiments and visualization results further validate the effectiveness of each module. The WaveletUMamba framework proposed in this paper offers a new methodological approach for the precise extraction of crop planting areas across multiple growth stages in complex open-field agricultural environments, while also providing a technical solution for the practical application of UAV remote sensing technology in extracting crop planting areas.
- Open Access
- 15 May 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1843631
SDGD-YOLO: a lightweight detection model for assessing the ripeness of black raspberries in complex greenhouse environments
In complex greenhouse environments, black raspberries present challenges such as dense clusters, variable fruit sizes, continuous colour changes during ripening, and interference from foliage and uneven lighting. These issues lead to high false positives and false negatives in existing ripeness detection models, limiting their application in intelligent precision harvesting. To address this, this study proposes SDGD-YOLO, a novel ripeness detection model. First, a StarNet architecture is embedded into the feature extraction network to enhance cross-channel interaction and global semantic association, improving the extraction of key ripeness features. Second, a DySample dynamic upsampling module is introduced during multi-scale feature fusion to adapt to variations in fruit size and morphology across ripeness stages. Third, a collaborative optimization mechanism combining Soft-NMS and GIoU is applied in post-processing to reduce redundant bounding boxes and improve localization accuracy, effectively mitigating false positives and negatives under occlusion. Finally, a refined knowledge distillation mechanism via teacher-student joint training enhances detection performance while maintaining lightweight inference. The experimental results show that, compared with the baseline YOLOv13n, SDGD-YOLO achieves a precision of 91.0% (an increase of 3.6%), a recall of 71.8% (an increase of 4.7%), and an F1-score of 80.68% (an increase of 4.69%). with mAP50 and mAP50–95 reaching 81.7% (an increase of 5.7%) and 68.7% (an increase of 6.6%) respectively. Meanwhile, the number of model parameters has been reduced to 1.988 M, and GFLOPs to 5.8 G, achieving an effective balance between improved accuracy and reduced computational complexity. The SDGD-YOLO proposed in this study provides a technical reference for the accurate detection of berry ripeness in complex greenhouse environments.
- 15 May 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1843631
Open AccessSDGD-YOLO: a lightweight detection model for assessing the ripeness of black raspberries in complex greenhouse environments
In complex greenhouse environments, black raspberries present challenges such as dense clusters, variable fruit sizes, continuous colour changes during ripening, and interference from foliage and uneven lighting. These issues lead to high false positives and false negatives in existing ripeness detection models, limiting their application in intelligent precision harvesting. To address this, this study proposes SDGD-YOLO, a novel ripeness detection model. First, a StarNet architecture is embedded into the feature extraction network to enhance cross-channel interaction and global semantic association, improving the extraction of key ripeness features. Second, a DySample dynamic upsampling module is introduced during multi-scale feature fusion to adapt to variations in fruit size and morphology across ripeness stages. Third, a collaborative optimization mechanism combining Soft-NMS and GIoU is applied in post-processing to reduce redundant bounding boxes and improve localization accuracy, effectively mitigating false positives and negatives under occlusion. Finally, a refined knowledge distillation mechanism via teacher-student joint training enhances detection performance while maintaining lightweight inference. The experimental results show that, compared with the baseline YOLOv13n, SDGD-YOLO achieves a precision of 91.0% (an increase of 3.6%), a recall of 71.8% (an increase of 4.7%), and an F1-score of 80.68% (an increase of 4.69%). with mAP50 and mAP50–95 reaching 81.7% (an increase of 5.7%) and 68.7% (an increase of 6.6%) respectively. Meanwhile, the number of model parameters has been reduced to 1.988 M, and GFLOPs to 5.8 G, achieving an effective balance between improved accuracy and reduced computational complexity. The SDGD-YOLO proposed in this study provides a technical reference for the accurate detection of berry ripeness in complex greenhouse environments.
- Open Access
- 1 October 2025
- Published by MDPI AG in Agriengineering
- Vol. 7 (10) , 321
SCS-YOLO: A Lightweight Cross-Scale Detection Network for Sugarcane Surface Cracks with Dynamic Perception
Detecting surface cracks on sugarcane is a critical step in ensuring product quality control, with detection precision directly impacting raw material screening efficiency and economic benefits in the sugar industry. Traditional methods face three core challenges: (1) complex background interference complicates texture feature extraction; (2) variable crack scales limit models’ cross-scale feature generalization capabilities; and (3) high computational complexity hinders deployment on edge devices. To address these issues, this study proposes a lightweight sugarcane surface crack detection model, SCS-YOLO (Surface Cracks on Sugarcane-YOLO), based on the YOLOv10 architecture. This model incorporates three key technical innovations. First, the designed RFAC2f module (Receptive-Field Attentive CSP Bottleneck with Dual Convolution) significantly enhances feature representation capabilities in complex backgrounds through dynamic receptive field modeling and multi-branch feature processing/fusion mechanisms. Second, the proposed DSA module (Dynamic SimAM Attention) achieves adaptive spatial optimization of cross-layer crack features by integrating dynamic weight allocation strategies with parameter-free spatial attention mechanisms. Finally, the DyHead detection head employs a dynamic feature optimization mechanism to reduce parameter count and computational complexity. Experiments demonstrate that on the Sugarcane Crack Dataset v3.1, compared to the baseline model YOLOv10, our model achieves mAP50:95 to 71.8% (up 2.1%). Simultaneously, it achieves significant reductions in parameter count (down 19.67%) and computational load (down 11.76%), while boosting FPS to 122 to meet real-time detection requirements. Considering the multiple dimensions of precision indicators, complexity indicators, and FPS comprehensively, the SCS—YOLO detection framework proposed in this study provides a feasible technical reference for the intelligent detection of sugarcane quality in the raw materials of the sugar industry.
- 1 October 2025
- Published by MDPI AG in Agriengineering
- Vol. 7 (10) , 321
Open AccessSCS-YOLO: A Lightweight Cross-Scale Detection Network for Sugarcane Surface Cracks with Dynamic Perception
Detecting surface cracks on sugarcane is a critical step in ensuring product quality control, with detection precision directly impacting raw material screening efficiency and economic benefits in the sugar industry. Traditional methods face three core challenges: (1) complex background interference complicates texture feature extraction; (2) variable crack scales limit models’ cross-scale feature generalization capabilities; and (3) high computational complexity hinders deployment on edge devices. To address these issues, this study proposes a lightweight sugarcane surface crack detection model, SCS-YOLO (Surface Cracks on Sugarcane-YOLO), based on the YOLOv10 architecture. This model incorporates three key technical innovations. First, the designed RFAC2f module (Receptive-Field Attentive CSP Bottleneck with Dual Convolution) significantly enhances feature representation capabilities in complex backgrounds through dynamic receptive field modeling and multi-branch feature processing/fusion mechanisms. Second, the proposed DSA module (Dynamic SimAM Attention) achieves adaptive spatial optimization of cross-layer crack features by integrating dynamic weight allocation strategies with parameter-free spatial attention mechanisms. Finally, the DyHead detection head employs a dynamic feature optimization mechanism to reduce parameter count and computational complexity. Experiments demonstrate that on the Sugarcane Crack Dataset v3.1, compared to the baseline model YOLOv10, our model achieves mAP50:95 to 71.8% (up 2.1%). Simultaneously, it achieves significant reductions in parameter count (down 19.67%) and computational load (down 11.76%), while boosting FPS to 122 to meet real-time detection requirements. Considering the multiple dimensions of precision indicators, complexity indicators, and FPS comprehensively, the SCS—YOLO detection framework proposed in this study provides a feasible technical reference for the intelligent detection of sugarcane quality in the raw materials of the sugar industry.
- Open Access
- 21 August 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (8) , 993
Lightweight YOLOv11n-Based Detection and Counting of Early-Stage Cabbage Seedlings from UAV RGB Imagery
This study proposes a lightweight adaptive neural network framework based on an improved YOLOv11n model to address the core challenges in identifying cabbage seedlings in visible light images captured by UAVs. These challenges include the loss of small-target features, poor adaptability to complex lighting conditions, and the low deployment efficiency of edge devices. First, the adaptive dual-path downsampling module (ADown) integrates average pooling and maximum pooling into a dual-branch structure to enhance background texture and crop edge features in a synergistic manner. Secondly, the Illumination Robust Contrast Learning Head (IRCLHead) utilizes a temperature-adaptive network to adjust the contrast loss function parameters dynamically. Combined with a dual-output supervision mechanism that integrates growth stage prediction and interference-resistant feature embedding, this module enhances the model’s robustness in complex lighting scenarios. Finally, a lightweight spatial-channel attention convolution module (LAConv) has been developed to optimize the model’s computational load by using multi-scale feature extraction paths and depth decomposition structures. Experiments demonstrate that the proposed architecture achieves an mAP@0.5 of 99.0% in detecting cabbage seedling growth cycles, improving upon the baseline model by 0.71 percentage points. Furthermore, it achieves an mAP@0.5:0.95 of 2.4 percentage points, reduces computational complexity (GFLOPs) by 12.7%, and drastically reduces inference time from 3.7 ms to 1.0 ms. Additionally, the model parameters are simplified by 3%. This model provides an efficient solution for the real-time counting of cabbage seedlings and lightweight operations in drone-based precision agriculture.
- 21 August 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (8) , 993
Open AccessLightweight YOLOv11n-Based Detection and Counting of Early-Stage Cabbage Seedlings from UAV RGB Imagery
This study proposes a lightweight adaptive neural network framework based on an improved YOLOv11n model to address the core challenges in identifying cabbage seedlings in visible light images captured by UAVs. These challenges include the loss of small-target features, poor adaptability to complex lighting conditions, and the low deployment efficiency of edge devices. First, the adaptive dual-path downsampling module (ADown) integrates average pooling and maximum pooling into a dual-branch structure to enhance background texture and crop edge features in a synergistic manner. Secondly, the Illumination Robust Contrast Learning Head (IRCLHead) utilizes a temperature-adaptive network to adjust the contrast loss function parameters dynamically. Combined with a dual-output supervision mechanism that integrates growth stage prediction and interference-resistant feature embedding, this module enhances the model’s robustness in complex lighting scenarios. Finally, a lightweight spatial-channel attention convolution module (LAConv) has been developed to optimize the model’s computational load by using multi-scale feature extraction paths and depth decomposition structures. Experiments demonstrate that the proposed architecture achieves an mAP@0.5 of 99.0% in detecting cabbage seedling growth cycles, improving upon the baseline model by 0.71 percentage points. Furthermore, it achieves an mAP@0.5:0.95 of 2.4 percentage points, reduces computational complexity (GFLOPs) by 12.7%, and drastically reduces inference time from 3.7 ms to 1.0 ms. Additionally, the model parameters are simplified by 3%. This model provides an efficient solution for the real-time counting of cabbage seedlings and lightweight operations in drone-based precision agriculture.
- Open Access
- 9 August 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (16) , 1723
U-MoEMamba: A Hybrid Expert Segmentation Model for Cabbage Heads in Complex UAV Low-Altitude Remote Sensing Scenarios
To address the challenges of missed and incorrect segmentation in cabbage head detection under complex field conditions using UAV-based low-altitude remote sensing, this study proposes U-MoEMamba, an innovative dynamic state-space framework with a mixture-of-experts (MoE) collaborative segmentation network. The network constructs a dynamic multi-scale expert architecture, integrating three expert paradigms—multi-scale convolution, attention mechanisms, and Mamba pathways—for efficient and accurate segmentation. First, we design the MambaMoEFusion module, a collaborative expert fusion block that employs a lightweight gating network to dynamically integrate outputs from different experts, enabling adaptive selection and optimal feature aggregation. Second, we propose an MSCrossDualAttention module as an attention expert branch, leveraging a dual-path interactive attention mechanism to jointly extract shallow details and deep semantic information, effectively capturing the contextual features of cabbages. Third, the VSSBlock is incorporated as an expert pathway to model long-range dependencies via visual state-space representation. Evaluation on datasets of different cabbage growth stages shows that U-MoEMamba achieves an mIoU of 89.51% on the early-heading dataset, outperforming SegMamba and EfficientPyramidMamba by 3.91% and 1.4%, respectively. On the compact heading dataset, it reaches 91.88%, with improvements of 2.41% and 1.65%. This study provides a novel paradigm for intelligent monitoring of open-field crops.
- 9 August 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (16) , 1723
Open AccessU-MoEMamba: A Hybrid Expert Segmentation Model for Cabbage Heads in Complex UAV Low-Altitude Remote Sensing Scenarios
To address the challenges of missed and incorrect segmentation in cabbage head detection under complex field conditions using UAV-based low-altitude remote sensing, this study proposes U-MoEMamba, an innovative dynamic state-space framework with a mixture-of-experts (MoE) collaborative segmentation network. The network constructs a dynamic multi-scale expert architecture, integrating three expert paradigms—multi-scale convolution, attention mechanisms, and Mamba pathways—for efficient and accurate segmentation. First, we design the MambaMoEFusion module, a collaborative expert fusion block that employs a lightweight gating network to dynamically integrate outputs from different experts, enabling adaptive selection and optimal feature aggregation. Second, we propose an MSCrossDualAttention module as an attention expert branch, leveraging a dual-path interactive attention mechanism to jointly extract shallow details and deep semantic information, effectively capturing the contextual features of cabbages. Third, the VSSBlock is incorporated as an expert pathway to model long-range dependencies via visual state-space representation. Evaluation on datasets of different cabbage growth stages shows that U-MoEMamba achieves an mIoU of 89.51% on the early-heading dataset, outperforming SegMamba and EfficientPyramidMamba by 3.91% and 1.4%, respectively. On the compact heading dataset, it reaches 91.88%, with improvements of 2.41% and 1.65%. This study provides a novel paradigm for intelligent monitoring of open-field crops.
- Open Access
Using PLUS-InVEST-OPGD model to explore spatiotemporal variation of ecosystem carbon storage and its drivers in Jinsha river basin, China
Land-Use/Land-Cover Change (LUCC) is a key disturbance factor of the carbon cycle in terrestrial ecosystems, and the study on the coupling mechanism between LUCC and carbon storage is of great scientific value for implementing a regional carbon-neutral strategy. In this study, the Jinsha River Basin in Yunnan Province, which has outstanding ecological vulnerability, is taken as the research object, and a synergistic analytical framework of “spatial and temporal pattern drivers” is constructed by integrating multi-temporal remote sensing data and multi-model coupling method. Based on the high-precision 30 m land use data from 1990 to 2020, the PLUS-InVEST-OPGD multi-model coupled system was used to simulate and predict the characteristics of spatial and temporal carbon storage differentiation in 2030 under four development scenarios, namely, natural development (ND), ecological protection (EP), farmland protection (FP), and economic development (ED), and to analyze the driving mechanism using the Optimal Parameter Geodetic Probe (OPGP). The driving mechanism is analyzed using an optimal parameter geodetector. The main findings were: (1) The land use structure of the watershed in the study area showed a significant ecological-productive dichotomy, with forest land (60.58%), grassland (28.85%) and cultivated land (7.19%) constituting the core carbon sink carriers (the average proportion of which was 96.62% from 1990 to 2020). Still, the area of forest and grassland decreased by a total of 2,757.84 km2 in the past 30 years, and the expansion of construction land amounted to 2,321.91 km2; (2) the spatial and temporal evolution of carbon storage shows the heterogeneous characteristics of “overall decreasing and local optimization”, in which the carbon loss from forest to grassland conversion is as high as 30% of the total carbon loss, and the expansion of construction land leads to irreversible decay of carbon sinks of about 50%; (3) a multi-scenario simulation shows that the EP scenario minimizes the loss of carbon storage (−2.46 × 106 t) by maintaining a 96.82% ecological land share in 2030, reducing the carbon deficit by 7.79 × 106 t compared with the ND scenario; (4) the average annual temperature is the largest single factor affecting carbon storage, and its interaction with the population factor has a high q value of 0.84. This study innovatively reveals the nonlinear threshold effect of LUCC-carbon storage response in the Jinsha River Basin of Yunnan Province, and the proposed optimization model of “ecological protection” can provide decision support and corresponding reference for the construction of ecological security barriers in the upper reaches of the Yangtze River.
Open AccessUsing PLUS-InVEST-OPGD model to explore spatiotemporal variation of ecosystem carbon storage and its drivers in Jinsha river basin, China
Land-Use/Land-Cover Change (LUCC) is a key disturbance factor of the carbon cycle in terrestrial ecosystems, and the study on the coupling mechanism between LUCC and carbon storage is of great scientific value for implementing a regional carbon-neutral strategy. In this study, the Jinsha River Basin in Yunnan Province, which has outstanding ecological vulnerability, is taken as the research object, and a synergistic analytical framework of “spatial and temporal pattern drivers” is constructed by integrating multi-temporal remote sensing data and multi-model coupling method. Based on the high-precision 30 m land use data from 1990 to 2020, the PLUS-InVEST-OPGD multi-model coupled system was used to simulate and predict the characteristics of spatial and temporal carbon storage differentiation in 2030 under four development scenarios, namely, natural development (ND), ecological protection (EP), farmland protection (FP), and economic development (ED), and to analyze the driving mechanism using the Optimal Parameter Geodetic Probe (OPGP). The driving mechanism is analyzed using an optimal parameter geodetector. The main findings were: (1) The land use structure of the watershed in the study area showed a significant ecological-productive dichotomy, with forest land (60.58%), grassland (28.85%) and cultivated land (7.19%) constituting the core carbon sink carriers (the average proportion of which was 96.62% from 1990 to 2020). Still, the area of forest and grassland decreased by a total of 2,757.84 km2 in the past 30 years, and the expansion of construction land amounted to 2,321.91 km2; (2) the spatial and temporal evolution of carbon storage shows the heterogeneous characteristics of “overall decreasing and local optimization”, in which the carbon loss from forest to grassland conversion is as high as 30% of the total carbon loss, and the expansion of construction land leads to irreversible decay of carbon sinks of about 50%; (3) a multi-scenario simulation shows that the EP scenario minimizes the loss of carbon storage (−2.46 × 106 t) by maintaining a 96.82% ecological land share in 2030, reducing the carbon deficit by 7.79 × 106 t compared with the ND scenario; (4) the average annual temperature is the largest single factor affecting carbon storage, and its interaction with the population factor has a high q value of 0.84. This study innovatively reveals the nonlinear threshold effect of LUCC-carbon storage response in the Jinsha River Basin of Yunnan Province, and the proposed optimization model of “ecological protection” can provide decision support and corresponding reference for the construction of ecological security barriers in the upper reaches of the Yangtze River.
- Open Access
- 3 July 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (7) , 785
High-Precision Complex Orchard Passion Fruit Detection Using the PHD-YOLO Model Improved from YOLOv11n
This study proposes the PHD-YOLO model as a means to enhance the precision of passion fruit detection in intricate orchard settings. The model has been meticulously engineered to circumvent salient challenges, including branch and leaf occlusion, variances in illumination, and fruit overlap. This study introduces a pioneering partial convolution module (ParConv), which employs a channel grouping and independent processing strategy to mitigate computational complexity. The module under consideration has been demonstrated to enhance the efficacy of local feature extraction in dense fruit regions by integrating sub-group feature-independent convolution and channel concatenation mechanisms. Secondly, deep separable convolution (DWConv) is adopted to replace standard convolution. The proposed method involves decoupling spatial convolution and channel convolution, a strategy that enables the retention of multi-scale feature expression capabilities while achieving a substantial reduction in model computation. The integration of the HSV Attentional Fusion (HSVAF) module within the backbone network facilitates the fusion of HSV color space characteristics with an adaptive attention mechanism, thereby enhancing feature discriminability under dynamic lighting conditions. The experiment was conducted on a dataset of 1212 original images collected from a planting base in Yunnan, China, covering multiple periods and angles. The dataset was constructed using enhancement strategies, including rotation and noise injection, and contains 2910 samples. The experimental results demonstrate that the improved model achieves a detection accuracy of 95.4%, a recall rate of 85.0%, mAP@0.5 of 91.5%, and an F1 score of 90.0% on the test set, which are 0.7%, 3.5%, 1.3%, and 2. The model demonstrated a 4% increase in accuracy compared to the baseline model YOLOv11n, with a single-frame inference time of 0.6 milliseconds. The model exhibited significant robustness in scenarios with dense fruits, leaf occlusion, and backlighting, validating the synergistic enhancement of staged convolution optimization and hybrid attention mechanisms. This solution offers a means to automate the monitoring of orchards, achieving a balance between accuracy and real-time performance.
- 3 July 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (7) , 785
Open AccessHigh-Precision Complex Orchard Passion Fruit Detection Using the PHD-YOLO Model Improved from YOLOv11n
This study proposes the PHD-YOLO model as a means to enhance the precision of passion fruit detection in intricate orchard settings. The model has been meticulously engineered to circumvent salient challenges, including branch and leaf occlusion, variances in illumination, and fruit overlap. This study introduces a pioneering partial convolution module (ParConv), which employs a channel grouping and independent processing strategy to mitigate computational complexity. The module under consideration has been demonstrated to enhance the efficacy of local feature extraction in dense fruit regions by integrating sub-group feature-independent convolution and channel concatenation mechanisms. Secondly, deep separable convolution (DWConv) is adopted to replace standard convolution. The proposed method involves decoupling spatial convolution and channel convolution, a strategy that enables the retention of multi-scale feature expression capabilities while achieving a substantial reduction in model computation. The integration of the HSV Attentional Fusion (HSVAF) module within the backbone network facilitates the fusion of HSV color space characteristics with an adaptive attention mechanism, thereby enhancing feature discriminability under dynamic lighting conditions. The experiment was conducted on a dataset of 1212 original images collected from a planting base in Yunnan, China, covering multiple periods and angles. The dataset was constructed using enhancement strategies, including rotation and noise injection, and contains 2910 samples. The experimental results demonstrate that the improved model achieves a detection accuracy of 95.4%, a recall rate of 85.0%, mAP@0.5 of 91.5%, and an F1 score of 90.0% on the test set, which are 0.7%, 3.5%, 1.3%, and 2. The model demonstrated a 4% increase in accuracy compared to the baseline model YOLOv11n, with a single-frame inference time of 0.6 milliseconds. The model exhibited significant robustness in scenarios with dense fruits, leaf occlusion, and backlighting, validating the synergistic enhancement of staged convolution optimization and hybrid attention mechanisms. This solution offers a means to automate the monitoring of orchards, achieving a balance between accuracy and real-time performance.
- Open Access
- 27 May 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (11) , 1152
MAMNet: Lightweight Multi-Attention Collaborative Network for Fine-Grained Cropland Extraction from Gaofen-2 Remote Sensing Imagery
To address the issues of high computational complexity and boundary feature loss encountered when extracting farmland information from high-resolution remote sensing images, this study proposes an innovative CNN–Transformer hybrid network, MAMNet. This framework integrates a lightweight encoder, a global–local Transformer decoder, and a bidirectional attention architecture to achieve efficient and accurate farmland information extraction. First, we reconstruct the ResNet-18 backbone network using deep separable convolutions, reducing computational complexity while preserving feature representation capabilities. Second, the global–local Transformer block (GLTB) decoder uses multi-head self-attention mechanisms to dynamically fuse multi-scale features across layers, effectively restoring the topological structure of fragmented farmland boundaries. Third, we propose a novel bidirectional attention architecture: the Detail Improvement Module (DIM) uses channel attention to transfer semantic features to geometric features. The Context Enhancement Module (CEM) utilizes spatial attention to achieve dynamic geometric–semantic fusion, quantitatively distinguishing farmland textures from mixed ground cover. The positional attention mechanism (PAM) enhances the continuity of linear features by strengthening spatial correlations in jump connections. By cascading front-end feature module (FEM) to expand the receptive field and combining an adaptive feature reconstruction head (FRH), this method improves information integrity in fragmented areas. Evaluation results on the 2022 high-resolution two-channel image dataset from Chenggong District, Kunming City, demonstrate that MAMNet achieves an mIoU of 86.68% (an improvement of 1.66% and 2.44% over UNetFormer and BANet, respectively) and an F1-Score of 92.86% with only 12 million parameters. This method provides new technical insights for plot-level farmland monitoring in precision agriculture.
- 27 May 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (11) , 1152
Open AccessMAMNet: Lightweight Multi-Attention Collaborative Network for Fine-Grained Cropland Extraction from Gaofen-2 Remote Sensing Imagery
To address the issues of high computational complexity and boundary feature loss encountered when extracting farmland information from high-resolution remote sensing images, this study proposes an innovative CNN–Transformer hybrid network, MAMNet. This framework integrates a lightweight encoder, a global–local Transformer decoder, and a bidirectional attention architecture to achieve efficient and accurate farmland information extraction. First, we reconstruct the ResNet-18 backbone network using deep separable convolutions, reducing computational complexity while preserving feature representation capabilities. Second, the global–local Transformer block (GLTB) decoder uses multi-head self-attention mechanisms to dynamically fuse multi-scale features across layers, effectively restoring the topological structure of fragmented farmland boundaries. Third, we propose a novel bidirectional attention architecture: the Detail Improvement Module (DIM) uses channel attention to transfer semantic features to geometric features. The Context Enhancement Module (CEM) utilizes spatial attention to achieve dynamic geometric–semantic fusion, quantitatively distinguishing farmland textures from mixed ground cover. The positional attention mechanism (PAM) enhances the continuity of linear features by strengthening spatial correlations in jump connections. By cascading front-end feature module (FEM) to expand the receptive field and combining an adaptive feature reconstruction head (FRH), this method improves information integrity in fragmented areas. Evaluation results on the 2022 high-resolution two-channel image dataset from Chenggong District, Kunming City, demonstrate that MAMNet achieves an mIoU of 86.68% (an improvement of 1.66% and 2.44% over UNetFormer and BANet, respectively) and an F1-Score of 92.86% with only 12 million parameters. This method provides new technical insights for plot-level farmland monitoring in precision agriculture.
- Open Access
- 18 April 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (8) , 881
Red Raspberry Maturity Detection Based on Multi-Module Optimized YOLOv11n and Its Application in Field and Greenhouse Environments
In order to achieve accurate and rapid identification of red raspberry fruits in the complex environments of fields and greenhouses, this study proposes a new red raspberry maturity detection model based on YOLOv11n. First, the proposed hybrid attention mechanism HCSA (halo attention with channel and spatial attention modules) is embedded in the neck of the YOLOv11n network. This mechanism integrates halo, channel, and spatial attention to enhance feature extraction and representation in fruit detection and improve attention to spatial and channel information. Secondly, dilation-wise residual (DWR) is fused with the C3k2 module of the network and applied to the entire network structure to enhance feature extraction, multi-scale perception, and computational efficiency in red raspberry detection. Concurrently, the DWR module optimizes the learning process through residual connections, thereby enhancing the accuracy and real-time performance of the model. Finally, a lightweight and efficient dynamic upsampling module (DySample) is introduced between the backbone and neck of the network. This module enhances the network’s multi-scale feature extraction capabilities, reduces the interference of background noise, improves the recognition of structural details, and optimizes the spatial resolution of the image through the dynamic sampling mechanism. Reducing network parameters helps the model better capture the maturity characteristics of red raspberry fruits. Experiments were conducted on a custom-built 3167-image dataset of red raspberries, and the results demonstrated that the enhanced YOLOv11n model attained a precision of 0.922, mAP@0.5 of 0.925, and mAP@0.5 of 0.943, respectively, representing improvements of 0.7%, 4.4%, and 4.4%, respectively. At 3.4%, mAP@0.5-0.95 was 0.798, which was 2.0%, 9.8% and 3.7% higher than the original YOLOv11n model, respectively. The mAP@0.5 of unripe and ripe berries was 0.925 and 0.943, which was improved by 0.7% and 4.4%, respectively. The F1-score was enhanced to 0.89, while the computational complexity of the model was only 8.2 GFLOPs, thereby achieving a favorable balance between accuracy and efficiency. This research provides new technical support for precision agriculture and intelligent robotic harvesting.
- 18 April 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (8) , 881
Open AccessRed Raspberry Maturity Detection Based on Multi-Module Optimized YOLOv11n and Its Application in Field and Greenhouse Environments
In order to achieve accurate and rapid identification of red raspberry fruits in the complex environments of fields and greenhouses, this study proposes a new red raspberry maturity detection model based on YOLOv11n. First, the proposed hybrid attention mechanism HCSA (halo attention with channel and spatial attention modules) is embedded in the neck of the YOLOv11n network. This mechanism integrates halo, channel, and spatial attention to enhance feature extraction and representation in fruit detection and improve attention to spatial and channel information. Secondly, dilation-wise residual (DWR) is fused with the C3k2 module of the network and applied to the entire network structure to enhance feature extraction, multi-scale perception, and computational efficiency in red raspberry detection. Concurrently, the DWR module optimizes the learning process through residual connections, thereby enhancing the accuracy and real-time performance of the model. Finally, a lightweight and efficient dynamic upsampling module (DySample) is introduced between the backbone and neck of the network. This module enhances the network’s multi-scale feature extraction capabilities, reduces the interference of background noise, improves the recognition of structural details, and optimizes the spatial resolution of the image through the dynamic sampling mechanism. Reducing network parameters helps the model better capture the maturity characteristics of red raspberry fruits. Experiments were conducted on a custom-built 3167-image dataset of red raspberries, and the results demonstrated that the enhanced YOLOv11n model attained a precision of 0.922, mAP@0.5 of 0.925, and mAP@0.5 of 0.943, respectively, representing improvements of 0.7%, 4.4%, and 4.4%, respectively. At 3.4%, mAP@0.5-0.95 was 0.798, which was 2.0%, 9.8% and 3.7% higher than the original YOLOv11n model, respectively. The mAP@0.5 of unripe and ripe berries was 0.925 and 0.943, which was improved by 0.7% and 4.4%, respectively. The F1-score was enhanced to 0.89, while the computational complexity of the model was only 8.2 GFLOPs, thereby achieving a favorable balance between accuracy and efficiency. This research provides new technical support for precision agriculture and intelligent robotic harvesting.