1.人工智能与数字经济广东省实验室(深圳),广东 深圳,518107
2.中国测绘科学研究院,北京,100036
3.深圳大学广东省城市空间信息工程重点实验室,广东 深圳,518061
4.深圳大学自然资源部大湾区地理环境监测重点实验室,广东 深圳,518061
5.深圳大学深圳市空间信息智能感知与服务重点实验室,广东 深圳,518061
6.深圳大学土木与交通工程学院,广东 深圳,518060
熊思婷,博士,副研究员,主要从事合成孔径雷达数据处理工作。xiongsiting@gml.ac.cn
侯伟,博士,副研究员。houwei@casm.ac.cn
收稿:2025-01-15,
纸质出版:2025-08-05
移动端阅览
熊思婷,韦如依,侯伟,等.结合LSTM模型与InSAR相干性矩阵的土地覆盖分类方法[J].武汉大学学报(信息科学版),2025,50(8):1542-1554.
XIONG Siting,WEI Ruyi,HOU Wei,et al. Land Cover Classification Based on InSAR Coherence and LSTM Model[J].Geomatics and Information Science of Wuhan University,2025,50(8):1542-1554.
熊思婷,韦如依,侯伟,等.结合LSTM模型与InSAR相干性矩阵的土地覆盖分类方法[J].武汉大学学报(信息科学版),2025,50(8):1542-1554. DOI:10.13203/j.whugis20240460
XIONG Siting,WEI Ruyi,HOU Wei,et al. Land Cover Classification Based on InSAR Coherence and LSTM Model[J].Geomatics and Information Science of Wuhan University,2025,50(8):1542-1554. DOI:10.13203/j.whugis20240460
土地覆盖类型检测对地表特征理解、生态环境监测和自然资源管理具有重要意义。基于哨兵1号(Sentinel-1)多时相相干性矩阵,搭建长短期记忆网络(long short-term memory,LSTM)土地覆盖分类模型,旨在评估其在土地覆盖分类中的效能,探讨不同分类方法对分类结果的影响,并以中国辽宁省阜新市彰武县为研究区对4种不同土地覆盖分类方法进行验证。实验结果显示,基于Sentinel-1相干性矩阵的LSTM分类模型方法在3个区域的分类精度分别高达93.7%、89.9%和87.6%,具有较高的分类精度和鲁棒性,比基于Sentinel-1相干性向量的支持向量机(support vector machine,SVM)分类模型、基于Sentinel-1相干性矩阵的卷积神经网络分类模型以及基于哨兵2号(Sentinel-2)多光谱影像的SVM分类模型的方法分类精度高约1%~10%。此外,基于Sentinel-1相干性矩阵的LSTM分类模型方法还在不同子研究区之间进行了迁移学习实验,结果显示,该模型在子区域迁移时的泛化能力仍需增强。
Objectives
2
Land cover classification is crucial for understanding surface features
monitoring ecological environments
and managing natural resources. The objective of this research is to construct a long short-term memory (LSTM) model for land cover classification using Sentinel-1 multi-temporal coherence matrices and to evaluate its effectiveness by comparing it against other three classification methods.
Methods
2
Multi-temporal coherence matrices from Sentinel-1 synthetic aperture radar images were used to train an LSTM neural network for land cover classification. The Sentinel-1 coherence matrix was firstly transformed to sequences according to the temporal baseline intervals and then input into the LSTM model to predict the land cover types. This LSTM-based method was then compared against other three methods: (1) support vector machine (SVM) and (2) convolutional neural network models taking the Sentinel-1 coherence vectors and matrices as input
and (3) SVM model with the input of Sentinel-2 multi-spectral features. Transfer learning experiments were also conducted to assess the generalization capability of the LSTM-based method.
Results
2
The study area was selected in Zhangwu County
Fuxin City
Liaoning Province
China
where three test regions are chosen to conduct the land cover classification by using the four different methods
respectively. Experimental results demonstrated that the LSTM model with the Sentinel-1 coherence matrices achieved classification accuracies of 93.7%
89.9% and 87.6% in the three test regions
respectively
with an improvement in classification accuracy by approximately 1% to 10% compared to other methods. However
the results of the transfer learning experiments reveal that the generalization capability of the LSTM model is not desirable and needs further enhancement. When trained solely on region 1 and tested on regions 2 and 3
classification accuracies dropped to 45.7% and 47.4%. To enhance classification performance and model generalizability
a comprehensive sampling strategy was implemented by integrating data from all three regions for unified training. This approach achieved regional classification accuracies of 92.8%
87.8%
and 86.4%
effectively mitigating sample distribution bias and significantly improving cross-region adaptability.
Conclusions
2
The LSTM model utilizing Sentinel-1 coherence matrices as input features shows promising performance in land cover classification
particularly in areas affected by cloud cover. However
transferability of the model has high demand for the training samples
which can inhibit its applicability to wider regions. Future research is needed to optimize transfer learning strategies to enhance the model's adaptability and classification accuracy across different experimental regions.
VITOUSEK P M . Beyond Global Warming: Ecology and Global Change [J]. Ecology , 1994 , 75 ( 7 ): 1861 - 1876 .
PERRING M P , DE FRENNE P , BAETEN L , et al . Global Environmental Change Effects on Ecosystems: The Importance of Land-Use Legacies [J]. Global Change Biology , 2016 , 22 ( 4 ): 1361 - 1371 .
ELLIS E , PONTIUS R . Land-Use and Land-Cover Change [J]. Encyclopedia of Earth , 2007 , 1 : 1 - 4 .
陈军 , 廖安平 , 陈晋 , 等 . 全球30 m地表覆盖遥感数据产品: Globe Land30 [J]. 地理信息世界 , 2017 , 24 ( 1 ): 1 - 8 .
CHEN Jun , LIAO Anping , CHEN Jin , et al . 30-Meter Global Land Cover Data Product:Globe Land30 [J]. Geomatics World , 2017 , 24 ( 1 ): 1 - 8 .
MENDOZA-PONCE A , CORONA-NÚÑEZ R , KRAXNER F , et al . Identifying Effects of Land Use Cover Changes and Climate Change on Terrestrial Ecosystems and Carbon Stocks in Mexico [J]. Global Environmental Change , 2018 , 53 : 12 - 23 .
VERBURG P H , NEUMANN K , NOL L . Challenges in Using Land Use and Land Cover Data for Global Change Studies [J]. Global Change Biology , 2011 , 17 ( 2 ): 974 - 989 .
臧明润 , 廖远鸿 , 陈舟 , 等 . 土地覆盖分类体系分析和总结 [J/OL]. 自然资源遥感 , [ 2024-11-01 ]. http://kns.cnki.net/kcms/detail/10.1759.P.20240205.0831.002.html http://kns.cnki.net/kcms/detail/10.1759.P.20240205.0831.002.html .
ZANG Mingrun , LIAO Yuanhong , CHEN Zhou , et al . Analysis and Summary of Land Cover Classification Systems [J/OL]. Remote Sensing for Natural Resources , [ 2024-11-01 ]. http://kns.cnki.net/kcms/detail/10.1759.P.20240205.0831.002.html http://kns.cnki.net/kcms/detail/10.1759.P.20240205.0831.002.html .
TOWNSHEND J , JUSTICE C , LI W , et al . Global Land Cover Classification by Remote Sensing: Present Capabilities and Future Possibilities [J]. Remote Sensing of Environment , 1991 , 35 ( 2/3 ): 243 - 255 .
DISPERATI L , VIRDIS S G P . Assessment of Land-Use and Land-Cover Changes from 1965 to 2014 in Tam Giang-Cau Hai Lagoon, Central Vietnam [J]. Applied Geography , 2015 , 58 : 48 - 64 .
RWANGA S S , NDAMBUKI J M . Accuracy Assessment of Land Use/Land Cover Classification Using Remote Sensing and GIS [J]. International Journal of Geosciences , 2017 , 8 ( 4 ): 611 - 622 .
PHIRI D , SIMWANDA M , SALEKIN S , et al . Sentinel-2 Data for Land Cover/Use Mapping: A Review [J]. Remote Sensing , 2020 , 12 ( 14 ): 2291 .
GAŠPAROVIĆ M , JOGUN T . The Effect of Fusing Sentinel-2 Bands on Land-Cover Classification [J]. International Journal of Remote Sensing , 2018 , 39 ( 3 ): 822 - 841 .
TALUKDAR S , SINGHA P , MAHATO S , et al . Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations — A Review [J]. Remote Sensing , 2020 , 12 ( 15 ): 1135 .
ZHANG C , SARGENT I , PAN X , et al . Joint Deep Learning for Land Cover and Land Use Classification [J]. Remote Sensing of Environment , 2019 , 221 : 173 - 187 .
VALI A , COMAI S , MATTEUCCI M . Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review [J]. Remote Sensing , 2020 , 12 ( 15 ): 2495 .
KARRA K , KONTGIS C , STATMAN-WEIL Z , et al . Global Land Use / Land Cover with Sentinel-2 and Deep Learning [C]// IEEE International Geoscience and Remote Sensing Symposium IGARSS , Brussels, Belgium , 2021 .
ABDI A M . Land Cover and Land Use Classification Performance of Machine Learning Algorithms in a Boreal Landscape Using Sentinel-2 Data [J]. GIScience & Remote Sensing , 2020 , 57 ( 1 ): 1 - 20 .
MALINOWSKI R , LEWIŃSKI S , RYBICKI M , et al . Automated Production of a Land Cover/Use Map of Europe Based on Sentinel-2 Imagery [J]. Remote Sensing , 2020 , 12 ( 21 ): 3523 .
INGLADA J , VINCENT A , ARIAS M , et al . Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series [J]. Remote Sensing , 2017 , 9 ( 1 ): 95 .
WASKE B , BRAUN M . Classifier Ensembles for Land Cover Mapping Using Multitemporal SAR Imagery [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2009 , 64 ( 5 ): 450 - 457 .
MISHRA P , SINGH D , YAMAGUCHI Y . Land Cover Classification of Palsar Images by Knowledge Based Decision Tree Classi-Fier and Supervised Classifiers Based on Sar Observables [J]. Progress in Electromagnetics Research B , 2011 , 30 ( 30 ): 47 - 70 .
ZHANG R , TANG Z Z , LUO D , et al . Combined Multi-Time Series SAR Imagery and InSAR Technology for Rice Identification in Cloudy Regions [J]. Applied Sciences , 2021 , 11 ( 15 ): 6923 .
周鑫城 , 左小清 , 李勇发 , 等 . 不同地表覆盖对InSAR技术的相干性影响研究 [J]. 贵州大学学报(自然科学版) , 2023 , 40 ( 3 ): 62 - 70 .
ZHOU Xincheng , ZUO Xiaoqing , LI Yongfa , et al . Study on the Influence of Different Surface Coverages on the Coherence of InSAR Technology [J]. Journal of Guizhou University (Natural Sciences) , 2023 , 40 ( 3 ): 62 - 70 .
AMARSAIKHAN D , GANZORIG M , ACHE P , et al . The Integrated Use of Optical and InSAR Data for Urban Land‐Cover Mapping [J]. International Journal of Remote Sensing , 2007 , 28 ( 6 ): 1161 - 1171 .
佀文娜 , 何敏 , 王茂山 . 基于Sentinel-1的典型地物时间失相干分析 [J]. 地理空间信息 , 2022 , 20 ( 2 ): 22 - 26 .
SI Wenna , HE Min , WANG Maoshan . Temporal Decorrelation Analysis of Different Land Coverage Types Based on Sentinel-1 Images [J]. Geospatial Information , 2022 , 20 ( 2 ): 22 - 26 .
李振今 , 王志勇 , 叶凯乐 , 等 . 联合时间序列相干性和后向散射系数的黄河三角洲湿地分类 [J]. 测绘通报 , 2023 ( 2 ): 52 - 57 .
LI Zhenjin , WANG Zhiyong , YE Kaile , et al . Combined Time Series Coherence and Backscattering Coefficient for Wetland Classification in the Yellow River Delta [J]. Bulletin of Surveying and Mapping , 2023 ( 2 ): 52 - 57 .
NIKAEIN T , IANNINI L , MOLIJN R A , et al . On the Value of Sentinel-1 InSAR Coherence Time-Series for Vegetation Classification [J]. Remote Sensing , 2021 , 13 ( 16 ): 3300 .
JACOB A , NOTARNICOLA C , SURESH G , et al . Sentinel-1 InSAR Coherence for Land Cover Mapping: A Comparison of Multiple Feature-Based Classifiers [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 ( 1 ): 535 - 552 .
GIFFARD-ROISIN S , BOUDAOUR S , DOIN M P , et al . Land Cover Classification of the Alps from InSAR Temporal Coherence Matrices [J]. Frontiers in Remote Sensing , 2022 , 3 : 932491 .
GE S J , ANTROPOV O , SU W M , et al . Deep Recurrent Neural Networks for Land-Cover Classification Using Sentinel-1 InSAR Time Series [C]// IEEE International Geoscience and Remote Sensing Symposium , Yokohama, Japan , 2019 .
ZHOU Y N , LUO J C , FENG L , et al . Long-Short-Term-Memory-Based Crop Classification Using High-Resolution Optical Images and Multi-Temporal SAR Data [J]. GIScience & Remote Sensing , 2019 , 56 ( 8 ): 1170 - 1191 .
WANG L , XU X , DONG H , et al . Exploring Convolutional LSTM for PolSAR Image Classification [C]// IEEE International Geoscience and Remote Sensing Symposium , Valencia, Spain , 2018 .
TORRES R , SNOEIJ P , GEUDTNER D , et al . GMES Sentinel-1 Mission [J]. Remote Sensing of Environment , 2012 , 120 : 9 - 24 .
DRUSCH M , DEL BELLO U , CARLIER S , et al . Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services [J]. Remote Sensing of Environment , 2012 , 120 : 25 - 36 .
CHAVES M E D , PICOLI M C A , SANCHES I D . Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review [J]. Remote Sensing , 2020 , 12 ( 18 ): 3062 .
ZANAGA D , KERCHOVE R , KEERSMAECKER W , et al . ESA WorldCover 10 m 2020 V100 [OL]. https://worldcover2020.esa.int/download , 2023 .
VENTER Z S , BARTON D N , CHAKRABORTY T , et al . Global 10 m Land Use Land Cover Datasets: A Comparison of Dynamic World, World Cover and ESRI Land Cover [J]. Remote Sensing , 2022 , 14 ( 16 ): 4101 .
冯昊亮 , 苏鑫 , 朱武 , 等 . 差分信息引导的三分支洪涝水淹道路检测网络 [J]. 武汉大学学报(信息科学版) , 2024 , 49 ( 8 ): 1456 - 1465 .
FENG Haoliang , SU Xin , ZHU Wu , et al . Differential Information Guided Triple Branch Network for Flooded Road Detection [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 8 ): 1456 - 1465 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621