PGSUNet: A Phenology-Guided Deep Network for Tea Plantation Extraction from High-Resolution Remote Sensing Imagery
Source abstract
Abstract
Tea, recognized as one of the world’s three principal beverages, plays a significant role both economically and culturally. The accurate, large-scale mapping of tea plantations is crucial for quality control, industry regulation, and ecological assessments. Challenges arise in high-resolution imagery due to the spectral similarities with other land covers and the intricate nature of their boundaries. We introduce a Phenology-Guided SwinUnet (PGSUNet), a semantic segmentation network that amalgamates Swin Transformer encoding with a parallel phenology context branch. An intelligent fusion module within this network generates spatial attention informed by phenological priors, while a dual-head decoder enhances the precision through explicit edge supervision. Using Hangzhou City as the case study, PGSUNet was compared with seven mainstream models, including DeepLabV3+ and SegFormer. It achieved an F1-score of 0.84, outperforming the second-best model by 0.03, and obtained an mIoU of 84.53%, about 2% higher than the next-best result. This study demonstrates that the integration of phenological priors with edge supervision significantly improves the fine-scale extraction of agricultural land covers from complex remote sensing imagery.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing in Agriculture · Smart Agriculture and AI · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Beijing Key Laboratory of High Dynamic Navigation, Beijing Information Science and Technology University, Beijing 100192, China
Ningxia Hui Autonomous Region Natural Resources Survey and Investigation Institute, Yinchuan 750002, China
Funding
Research and Application Demonstration of Key Technologies for Ecological Protection Red Line Monitoring and Supervision in the Yellow River Basin, Ningxia · National Natural Science Foundation of China
References (39)
Show source-provided references
1. Chen, Y., and Tian, S. (2020). Feature-Level Fusion between Gaofen-5 and Sentinel-1A Data for Tea Plantation Mapping. Forests, 11.10.3390/f11121357 ↗
2. Construction of multidimensional features to identify tea plantations using multisource remote sensing data: A case study of Hangzhou city, China10.1016/j.ecoinf.2023.102185 ↗
3. Impact of land use changes on catchment soil erosion and sediment yield in the northeastern China: A panel data model application10.1016/j.ijsrc.2020.03.017 ↗
4. Effects of land use changes on soil organic carbon, nitrogen and their losses in a typical watershed of the Loess Plateau, China10.1016/j.ecolind.2021.108443 ↗
5. Effects of different management methods on carbon, nitrogen, and phosphorus contents and their stoichiometric ratios in tea plants10.17521/cjpe.2021.0071 ↗
6. Long-term tea plantation effects on composition and stabilization of soil organic matter in Southwest China10.1016/j.catena.2020.105132 ↗
7. An object-oriented and variogram based method for automatic extraction of tea planting area from high resolution remote sensing imagery
8. Research Progress of Remote Sensing on Tea Plantation Monitoring
9. Zhang, Q., Hu, M., Zhou, Y., Wan, B., Jiang, L., Zhang, Q., and Wang, D. (2022). Effects of UAV-LiDAR and Photogrammetric Point Density on Tea Plucking Area Identification. Remote Sens., 14.10.3390/rs14061505 ↗
10. Extracting tea plantations in complex landscapes using Sentinel-2 imagery and machine learning algorithms10.1007/s42974-022-00077-8 ↗
11. Tea plantation identification using GF-1 and Sentinel-2 time series data
12. Extracting tea plantations in southern hilly and mountainous region based on mesoscale spectrum and temporal phenological features
13. Where is tea grown in the world: A robust mapping framework for agroforestry crop with knowledge graph and sentinels images10.1016/j.rse.2024.114016 ↗
14. Huang, Y., Li, S., Yuang, L., Cheng, J., Li, W., Chen, Y., and Huang, J. (2019, January 16–19). Estimating Tea Plantation Area Based on Multi-source Satellite Data. Proceedings of the 2019 8th International Conference on Agro-Geoinformatics, Istanbul, Turkey.10.1109/Agro-Geoinformatics.2019.8820716 ↗
15. Integrating multiple texture methods and NDVI to the Random Forest classification algorithm to detect tea and hazelnut plantation areas in northeast Turkey10.1080/01431161.2014.995276 ↗
16. Tea plantation remote sensing extraction based on random forest feature selection
17. Extracting tea plantations based on ZY-3 satellite data
18. Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique10.1080/01431161.2013.845317 ↗
19. Mapping the Spatial Distribution of Tea Plantations with 10m Resolution in Fujian Province Using Google Earth Engine
20. Maxwell, A.E., Warner, T.A., and Guillén, L.A. (2021). Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 1: Literature Review. Remote Sens., 13.10.3390/rs13132450 ↗
21. Xiao, P., Qian, J., Yu, Q., Lin, X., Xu, J., and Liu, Y. (2025). Identify Tea Plantations Using Multidimensional Features Based on Multisource Remote Sensing Data: A Case Study of the Northwest Mountainous Area of Hubei Province. Remote Sens., 17.10.3390/rs17050908 ↗
22. Tea garden detection from high-resolution imagery using a scene-based framework10.14358/PERS.84.11.723 ↗
23. Zhou, Y., Yang, L., Yuan, L., Li, X., Mao, Y., Dong, J., Lin, Z., and Zhou, X. (2024). High-Precision Tea Plantation Mapping with Multi-Source Remote Sensing and Deep Learning. Agronomy, 14.10.3390/agronomy14122986 ↗
24. Guo, X., Liu, J., and Lu, Y. (2023, January 25–28). Mapping Tea Plantations from Medium-Resolution Remote Sensing Images Using Convolutional Neural Networks and Swin Transformer. Proceedings of the 2023 11th International Conference on Agro-Geoinformatics, Wuhan, China.10.1109/Agro-Geoinformatics59224.2023.10233308 ↗
25. Tang, Z., Li, M., and Wang, X. (2020). Mapping Tea Plantations from VHR Images Using OBIA and Convolutional Neural Networks. Remote Sens., 12.10.3390/rs12182935 ↗
26. Wei, G., and Zhou, R. (2023). Comparison of machine learning and deep learning models for evaluating suitable areas for premium teas in Yunnan, China. PLoS ONE, 18.10.1371/journal.pone.0282105 ↗
27. Yao, Z., Zhu, X., Zeng, Y., and Qiu, X. (2023). Extracting Tea Plantations from Multitemporal Sentinel-2 Images Based on Deep Learning Networks. Agriculture, 13.10.3390/agriculture13010010 ↗
28. Mapping tea plantation area using phenology algorithm, time-series Sentinel-2 and Landsat images10.1080/01431161.2023.2208713 ↗
29. The pruning phenological phase-based method for extracting tea plantations by field hyperspectral data and Landsat time series imagery10.1080/10106049.2020.1801859 ↗
30. Development of a two-band enhanced vegetation index without a blue band10.1016/j.rse.2008.06.006 ↗
31. Quantitative estimation of chlorophyll-a using reflectance spectra: Experiments with autumn chestnut and maple leaves10.1016/1011-1344(93)06963-4 ↗
32. Nguyen, C.T., Chidthaisong, A., Kieu, D.P., and Huo, L.Z. (2021). A Modified Bare Soil Index to Identify Bare Land Features during Agricultural Fallow-Period in Southeast Asia Using Landsat 8. Land, 10.10.3390/land10030231 ↗
33. Effect of different pruning operations on the plant growth, phytohormones and transcriptome profiles of the following spring tea shoots10.48130/BPR-2022-0012 ↗
34. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
35. Deep High-Resolution Representation Learning for Visual Recognition10.1109/TPAMI.2020.2983686 ↗
36. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv.
37. Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., and Wang, M. (2021). Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation. arXiv.
38. Zhang, W., Pang, J., Chen, K., and Loy, C.C. (2021). K-Net: Towards Unified Image Segmentation. arXiv.
39. Cheng, B., Schwing, A.G., and Kirillov, A. (2021). Per-Pixel Classification is Not All You Need for Semantic Segmentation. arXiv.