Mporal SAR data: (1) it is very difficult to construct rice samples employing only SAR time series information with out rice prior distribution information; (2) the rice planting cycleAgriculture 2021, 11,four ofin tropical or subtropical places is complex, and also the current rice extraction techniques don’t make complete use from the temporal qualities of rice, and the classification accuracy needs to be improved; (3) moreover, smaller rice plots are normally affected by smaller roads and shadows. You will discover some false alarms in the extraction results, so the classification results must be optimized.Table 1. SAR data list table.Orbit Number–Frame Quantity: 157-63 No. 1 two 3 four five 6 Acquisition Time 2019/4/5 2019/4/17 2019/5/11 2019/5/12 2019/6/4 2019/6/16 No. 7 eight 9 10 11 12 Acquisition Time 2019/6/28 2019/7/10 2019/7/22 2019/8/3 2019/8/4 2019/8/27 No. 13 14 15 16 17 18 Acquisition Time 2019/9/8 2019/9/20 2019/10/2 2019/10/14 2019/10/26 2019/11/7 No. 19 20 21 22 Acquisition Time 2019/11/19 2019/12/1 2019/12/13 2019/12/Orbit Number–Frame Number: 157-66 No. 1 2 three 4 five six Acquisition Time 2019/3/30 2019/4/11 2019/5/5 2019/5/17 2019/5/29 2019/6/10 No. 7 8 9 10 11 12 Acquisition Time 2019/6/22 2019/7/04 2019/7/16 2019/7/28 2019/8/9 2019/8/21 No. 13 14 15 16 17 18 Acquisition Time 2019/9/2 2019/9/14 2019/9/26 2019/10/8 2019/10/20 2019/11/1 No. 19 20 21 22 Acquisition Time 2019/11/13 2019/11/25 2019/12/19 2019/12/Orbit Number–Frame Quantity: 84-65 No. 1 2 3 4 five six Acquisition Time 2019/3/31 2019/4/12 2019/5/6 2019/5/18 2019/5/30 2019/6/11 No. 7 8 9 ten 11 12 Acquisition Time 2019/6/23 2019/7/5 2019/7/17 2019/7/29 2019/8/10 2019/8/22 No. 13 14 15 16 17 18 Acquisition Time 2019/9/3 2019/9/15 2019/9/27 2019/10/9 2019/10/21 2019/11/2 No. 19 20 21 22 Acquisition Time 2019/11/14 2019/11/26 2019/12/8 2019/12/Therefore, this paper proposes a rice extraction and mapping method applying multitemporal SAR data, as shown in Figure 2. This study was conducted within the following parts: (1) pixel-level rice sample production based on temporal statistical traits; (two) the BiLSTM-Attention network model constructed by combining BiLSTM model and attention mechanism for rice region, and (3) the optimization of classification final results based on FROM-GLC10 information. two.two.1. Preprocessing Simply because VH polarization is superior to VV polarization in monitoring rice phenology, Epigenetics| particularly throughout the rice flooding period [52,53], the VH polarization was selected. Many preprocessing steps were carried out. First, the S1A level-1 GRD data format were imported to create the VH intensity images. Second, the multitemporal intensity image in the identical coverage area were registered utilizing ENVI software. Then, the De Grandi Spatio-temporal Filter was utilized to filter the intensity image in the time-space combination domain. Finally, Butenafine Biological Activity Shuttle Radar Topography Mission (SRTM)-90 m DEM was utilised to calibrate and geocode the intensity map, along with the intensity data value was converted into the backscattering coefficient on the logarithmic dB scale. The pixel size of the orthophoto is 10 m, that is reprojected to the UTM region 49 N inside the WGS-84 geographic coordinate technique.Agriculture 2021, 11,5 ofFigure two. Flow chart of your proposed framework.2.two.2. Time Series Curves of Distinctive Landcovers To understand the time series traits of rice and non-rice in the study area, typical rice, buildings, water, and vegetation samples within the study region have been selected for time series curve evaluation. The sample regions of 4.