Deep Learning Application of Fruit Planting Classification Based on Multi-Source Remote Sensing Images
Source abstract
Abstract
With global climate change, urbanization, and agricultural resource limitations, precision agriculture and crop monitoring are crucial worldwide. Integrating multi-source remote sensing data with deep learning enables accurate crop mapping, but selecting optimal network architectures remains challenging. To improve remote sensing-based fruit planting classification and support orchard management and rural revitalization, this study explored feature selection and network optimization. We proposed an improved CF-EfficientNet model (incorporating FGMF and CGAR modules) for fruit planting classification. Multi-source remote sensing data (Sentinel-1, Sentinel-2, and SRTM) were used to extract spectral, vegetation, polarization, terrain, and texture features, thereby constructing a high-dimensional feature space. Feature selection identified 13 highly discriminative bands, forming an optimal dataset, namely the preferred bands (PBs). At the same time, two classification datasets—multi-spectral bands (MS) and preferred bands (PBs)—were constructed, and five typical deep learning models were introduced to compare performance: (1) EfficientNetB0, (2) AlexNet, (3) VGG16, (4) ResNet18, (5) RepVGG. The experimental results showed that the EfficientNetB0 model based on the preferred band performed best in terms of overall accuracy (87.1%) and Kappa coefficient (0.677). Furthermore, a Fine-Grained Multi-scale Fusion (FGMF) and a Condition-Guided Attention Refinement (CGAR) were incorporated into EfficientNetB0, and the traditional SGD optimizer was replaced with Adam to construct the CF-EfficientNet architecture. The results indicated that the improved CF-EfficientNet model achieved high performance in crop classification, with an overall accuracy of 92.6% and a Kappa coefficient of 0.830. These represent improvements of 5.5 percentage points and 0.153, compared with the baseline model, demonstrating superiority in both classification accuracy and stability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing and Land Use · Remote Sensing in Agriculture · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Resources and Information, Xinjiang Academy of Forestry Sciences, Urumqi 830063, China
College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China
Institute of Afforestation and Desertification Research, Xinjiang Academy of Forestry Sciences, Urumqi 830063, China
Funding
Xinjiang Uyghur Autonomous Region Key R&D Special Project
References (43)
Show source-provided references
1. Xu, W., Li, Z., Lin, H., Shao, G., Zhao, F., Wang, H., Cheng, J., Lei, L., Chen, R., and Han, S. (2024). Mapping Fruit-Tree Plantation Using Sentinel-1/2 Time Series Images with Multi-Index Entropy Weighting Dynamic Time Warping Method. Remote Sens., 16.10.3390/rs16183390 ↗
2. Zhao, G., Wang, L., Zheng, J., Tuerxun, N., Han, W., and Liu, L. (2023). Optimized Extraction Method of Fruit Planting Distribution Based on Spectral and Radar Data Fusion of Key Time Phase. Remote Sens., 15.10.3390/rs15174140 ↗
3. Zhong, L., Dai, Z., Fang, P., Cao, Y., and Wang, L. (2024). A Review: Tree Species Classification Based on Remote Sensing Data and Classic Deep Learning-Based Methods. Forests, 15.10.20944/preprints202404.0569.v1 ↗
4. Zhou, X.-X., Li, Y.-Y., Luo, Y.-K., Sun, Y.-W., Su, Y.-J., Tan, C.-W., and Liu, Y.-J. (2022). Research on remote sensing classification of fruit trees based on Sentinel-2 multi-temporal imageries. Sci. Rep., 12.10.1038/s41598-022-15414-0 ↗
5. Huang, Y., Wen, X., Gao, Y., Zhang, Y., and Lin, G. (2023). Tree Species Classification in UAV Remote Sensing Images Based on Super-Resolution Reconstruction and Deep Learning. Remote Sens., 15.10.3390/rs15112942 ↗
6. Yan, Y., Tang, X., Zhu, X., and Yu, X. (2023). Optimal Time Phase Identification for Apple Orchard Land Recognition and Spatial Analysis Using Multitemporal Sentinel-2 Images and Random Forest Classification. Sustainability, 15.10.3390/su15064695 ↗
7. Qureshi, S., Koohpayma, J., Firozjaei, M.K., and Kakroodi, A.A. (2021). Evaluation of Seasonal, Drought, and Wet Condition Effects on Performance of Satellite-Based Precipitation Data over Different Climatic Conditions in Iran. Remote Sens., 14.10.3390/rs14010076 ↗
8. Image Recognition of Citrus Diseases Based on Deep Learning
9. Validation and consistency assessment of land surface temperature from geostationary and polar orbit platforms: SEVIRI/MSG and AVHRR/Metop10.1016/j.isprsjprs.2021.03.013 ↗
10. Chen, J., Xu, W., Yu, Y., Peng, C., and Gong, W. (2022). Reliable Label-Supervised Pixel Attention Mechanism for Weakly Supervised Building Segmentation in UAV Imagery. Remote Sens., 14.10.3390/rs14133196 ↗
11. Dong, S., and Chen, Z. (2021). A Multi-Level Feature Fusion Network for Remote Sensing Image Segmentation. Sensors, 21.10.3390/s21041267 ↗
12. Center pivot field delineation and mapping: A satellite-driven object-based image analysis approach for national scale accounting10.1016/j.isprsjprs.2021.02.019 ↗
13. Li, X., He, B., Ding, K., Guo, W., Huang, B., and Wu, L. (2022). Wide-Area and Real-Time Object Search System of UAV. Remote Sens., 14.10.3390/rs14051234 ↗
14. Chen, S., Chen, M., Zhao, B., Mao, T., Wu, J., and Bao, W. (2023). Urban Tree Canopy Mapping Based on Double-Branch Convolutional Neural Network and Multi-Temporal High Spatial Resolution Satellite Imagery. Remote Sens., 15.10.3390/rs15030765 ↗
15. Zhang, D., Liu, Z., and Shi, X. (2020, January 25–27). Transfer learning on efficientnet for remote sensing image classification. Proceedings of the 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), Harbin, China.10.1109/ICMCCE51767.2020.00489 ↗
16. Classification of remote sensing images using EfficientNet-B3 CNN model with attention10.1109/ACCESS.2021.3051085 ↗
17. Yin, H., Yang, C., and Lu, J. (2022, January 15–17). Research on remote sensing image classification algorithm based on EfficientNet. Proceedings of the 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), Xi’an, China.10.1109/ICSP54964.2022.9778437 ↗
18. Classification of Remote Sensing Datasets with Different Deep Learning Architectures10.15446/esrj.v28n4.113518 ↗
19. Tan, M., and Le, Q.V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv.
20. Wu, H., Zhou, H., Wang, A., and Iwahori, Y. (2022). Precise Crop Classification of Hyperspectral Images Using Multi-Branch Feature Fusion and Dilation-Based MLP. Remote Sens., 14.10.3390/rs14112713 ↗
21. Li, L., Liang, P., Ma, J., Jiao, L., Guo, X., Liu, F., and Sun, C. (2020). A Multiscale Self-Adaptive Attention Network for Remote Sensing Scene Classification. Remote Sens., 12.10.3390/rs12142209 ↗
22. A hybrid deep learning-based fruit classification using attention model and convolution autoencoder10.1007/s40747-020-00192-x ↗
23. Li, Q., Yan, D., and Wu, W. (2021). Remote Sensing Image Scene Classification Based on Global Self-Attention Module. Remote Sens., 13.10.3390/rs13224542 ↗
24. Guo, N., Jiang, M., Gao, L., Tang, Y., Han, J., and Chen, X. (2023). CRABR-Net: A Contextual Relational Attention-Based Recognition Network for Remote Sensing Scene Objective. Sensors, 23.10.3390/s23177514 ↗
25. Transfer learning approach based on satellite image time series for the crop classification problem10.1186/s40537-023-00735-2 ↗
26. Boosting crop classification by hierarchically fusing satellite, rotational, and contextual data10.1016/j.rse.2024.114110 ↗
27. Cui, J., Wang, Y., Zhou, T., Jiang, L., and Qi, Q. (2022). Temperature Mediates the Dynamic of MODIS NPP in Alpine Grassland on the Tibetan Plateau, 2001–2019. Remote Sens., 14.10.3390/rs14102401 ↗
28. Ma, Y., Liu, H., Jiang, B., Meng, L., Guan, H., Xu, M., Cui, Y., Kong, F., Yin, Y., and Wang, M. (2020). An Innovative Approach for Improving the Accuracy of Digital Elevation Models for Cultivated Land. Remote Sens., 12.10.3390/rs12203401 ↗
29. Phiri, D., Simwanda, M., Salekin, S., Nyirenda, V., Murayama, Y., and Ranagalage, M. (2020). Sentinel-2 Data for Land Cover/Use Mapping: A Review. Remote Sens., 12.10.3390/rs12142291 ↗
30. Random Forests10.1023/A:1010933404324 ↗
31. Feature Selection
32. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy10.1109/TPAMI.2005.159 ↗
33. An introduction to variable and feature selection
34. Computational prediction of methylation types of covalently modified lysine and arginine residues in proteins
35. Random Forests for Classification in Ecology10.1890/07-0539.1 ↗
36. Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review10.1162/neco_a_00990 ↗
37. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
38. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
39. Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 20–25). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
40. PROMISE: Coupling predictive process mining to process discovery10.1016/j.ins.2022.05.052 ↗
41. Li, A., Huang, W., Lan, X., Feng, J., Li, Z., and Wang, L. (2020, January 13–19). Boosting Few-Shot Learning with Adaptive Margin Loss. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01259 ↗
42. Cai, J., Pan, R., Lin, J., Liu, J., Zhang, L., Wen, X., Chen, X., and Zhang, X. (2023). Improved EfficientNet for corn disease identification. Front. Plant Sci., 14.10.3389/fpls.2023.1224385 ↗
43. Autumn crops remote sensing classification based on improved separability threshold feature selection