Mporal SAR data: (1) it truly is very difficult to construct rice samples using only SAR time series data without rice prior distribution data; (2) the rice planting cycleAgriculture 2021, 11,4 ofin tropical or subtropical places is complicated, along with the existing rice extraction strategies don’t make complete use with the temporal characteristics of rice, and the classification accuracy must be enhanced; (3) furthermore, smaller rice plots are normally impacted by tiny roads and shadows. You will find some false alarms in the extraction results, so the classification outcomes need to be optimized.Table 1. SAR data list table.Orbit Number–Frame Number: 157-63 No. 1 two 3 4 5 6 Ferrous bisglycinate manufacturer Acquisition Time 2019/4/5 2019/4/17 2019/5/11 2019/5/12 2019/6/4 2019/6/16 No. 7 8 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 Quantity: 157-66 No. 1 2 three four 5 6 Acquisition Time 2019/3/30 2019/4/11 2019/5/5 2019/5/17 2019/5/29 2019/6/10 No. 7 eight 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 Number: 84-65 No. 1 2 three 4 5 6 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 system applying multitemporal SAR information, as shown in Figure two. This analysis was carried out in the following components: (1) pixel-level rice sample production based on temporal statistical characteristics; (2) the BiLSTM-Attention network model constructed by combining BiLSTM model and focus mechanism for rice region, and (three) the optimization of classification final results primarily based on FROM-GLC10 information. two.2.1. Preprocessing Since VH polarization is superior to VV polarization in monitoring rice phenology, particularly through the rice flooding period [52,53], the VH polarization was selected. Several preprocessing actions were carried out. 1st, the S1A level-1 GRD information format had been imported to create the VH intensity images. Second, the multitemporal intensity image in the same coverage region had been registered employing ENVI computer software. Then, the De Grandi Spatio-temporal Filter was utilised to filter the intensity image within the time-space combination domain. Lastly, Shuttle Radar Topography Mission (SRTM)-90 m DEM was made use of to calibrate and geocode the intensity map, as well as the intensity data value was converted in to the backscattering coefficient around the logarithmic dB scale. The pixel size in the orthophoto is ten m, that is reprojected to the UTM area 49 N inside the WGS-84 4′-Methoxychalcone Epigenetics geographic coordinate method.Agriculture 2021, 11,five ofFigure two. Flow chart on the proposed framework.two.two.two. Time Series Curves of Diverse Landcovers To understand the time series characteristics of rice and non-rice within the study area, typical rice, buildings, water, and vegetation samples within the study area had been selected for time series curve analysis. The sample regions of 4.