Abandoned Land Mapping Based on Spatiotemporal Features from PolSAR Data via Deep Learning Methods
文献类型: 外文期刊
第一作者: Yang, Yingpin
作者: Yang, Yingpin;Wu, Zhifeng;Xiao, Wenju;Yang, Yingpin;Wang, Haiyun;Zhou, Ya'nan;Huang, Qiting;Wu, Tianjun;Luo, Jiancheng;Luo, Jiancheng
作者机构:
关键词: abandoned land identification; PolSAR; time series; LSTM; deep learning
期刊名称:REMOTE SENSING ( 影响因子:5.0; 五年影响因子:5.6 )
ISSN:
年卷期: 2023 年 15 卷 16 期
页码:
收录情况: SCI
摘要: Monitoring agricultural abandonment is essential in understanding the effects on the environment and food security. Polarimetric synthetic aperture radar (PolSAR) is an efficient approach for the monitoring of large-scale agricultural land cover in cloudy and rainy areas. However, previous studies have not taken advantage of the valuable phase information and not fully utilized the spatiotemporal features of farmland parcels, which has seriously limited the abandoned land identification accuracy. In this study, we developed a new method for the mapping of abandoned land based on the spatiotemporal features from PolSAR Single Look Complex (SLC) images via deep learning methods. First, backscattering coefficients (s(0)VV, s(0)VH) were derived, and the polarimetric parameters (entropy, anisotropy and mean alpha angle) were obtained based on Cloude-Pottier polarimetric decomposition. Then, the VGG16 deep convolutional network was innovatively used to extract spatial features from both the backscattering coefficients and polarimetric parameters. Next, the separability index was calculated to select the most effective spatial features. Finally, LSTM classifications were conducted based on the time series of backscattering features, the polarimetric parameters, the extracted spatial features and their combinations. The results showed that the introduction of multitemporal polarimetric parameters and spatial features both led to an improvement in the abandoned land identification accuracy. The combination of backscattering features, polarimetric parameters and spatial features yielded the best performance in identifying abandoned land, with producer's accuracy of 88.29% and user's accuracy of 84.03%. This study demonstrated the potential of polarimetric parameters and validated the effectiveness of spatiotemporal features in abandoned land identification. It provided a practical method for the production of a highly reliable abandoned land mapping in cloudy and rainy areas.
分类号:
- 相关文献
作者其他论文 更多>>
-
Recognition of maize seed varieties based on hyperspectral imaging technology and integrated learning algorithms
作者:Yang, Huan;Wang, Cheng;Zhang, Han;Zhou, Ya'nan;Luo, Bin;Yang, Huan;Wang, Cheng;Zhang, Han;Zhou, Ya'nan;Luo, Bin;Yang, Huan;Wang, Cheng
关键词:Hyperspectral; Random subspace ensemble learning; Maize seed; Variety recognition
-
A spatiotemporal collaborative approach for precise crop planting structure mapping based on multi-source remote-sensing data
作者:Sun, Yingwei;Leng, Pei;Liu, Xiangyang;Yao, Na;Luo, Jiancheng;Yao, Na
关键词:remote sensing; crop classification; multi-platform integration; fine-scale mapping; time-series analysis
-
Comparing cadmium uptake kinetics, xylem translocation, chemical forms, and subcellular distribution of two tobacco (Nicotiana tabacum L.) cultivars
作者:Liu, Haiwei;Zhang, Yan;Wang, Haiyun;Zhang, Biao;He, Yuan;Wang, Haohao;Zhu, Yingying;Shi, Yi;Holm, Peter E.;Holm, Peter E.
关键词:Heavy metal; Xylem sap; Bioaccumulation factor; Transfer factor; Kinetics
-
Farmland parcel-based crop classification in cloudy/rainy mountains using Sentinel-1 and Sentinel-2 based deep learning
作者:Sun, Yingwei;Li, Zhao-Liang;Liu, Niantang;Luo, Jiancheng;Luo, Jiancheng;Wu, Tianjun
关键词:cloudy; rainy mountainous area; crop classification; multitemporal data; combined utilization; feature transfer; optimization
-
Intestinal Microbiota and Serum Metabolic Profile Responded to Two Nutritional Different Diets in Mice
作者:Wu, Zhifeng;Cheng, Wei;Feng, Shuaifei;Zou, Huicong;Tan, Xiang;Yang, Yapeng;Wang, Yuqing;Zhang, Hang;Dong, Miaomiao;Tao, Shiyu;Wei, Hong;Wang, Zhenyu;Xiao, Yingping
关键词:germ-free diet; nutrient; microbiota; metabolism; gut development
-
Mapping crop leaf area index at the parcel level via inverting a radiative transfer model under spatiotemporal constraints: A case study on sugarcane
作者:Yang, Yingpin;Wu, Zhifeng;Yang, Yingpin;Huang, Qiting;Wu, Zhifeng;Wu, Tianjun;Luo, Jiancheng;Dong, Wen;Zhang, Xin;Zhang, Dongyun;Luo, Jiancheng;Dong, Wen;Zhang, Xin;Zhang, Dongyun;Sun, Yingwei
关键词:Parcel level; Leaf area index; Radiative transfer model; Regularization; Spatiotemporal constraints; Sugarcane
-
Identification and Characterization of a New Type of Holin-Endolysin Lysis Cassette in Acidovorax oryzae Phage AP1
作者:Zhang, Muchen;Chen, Jie;Hong, Xianxian;Xu, Xinyan;Wu, Zhifeng;Ahmed, Temoor;Li, Bin;Wang, Yanli;Sun, Guochang;Loh, Belinda;Leptihn, Sebastian;Hassan, Sabry;Hassan, Mohamed M.
关键词:Acidovorax oryzae phage AP1; lysis cassette; holin; endolysin