Consistent with theAgriculture 2021, 11,12 ofclassification facts inside the complete time series data. When faced with more complex rice extraction tasks in tropical and subtropical regions, the presence with the consideration layer enabled the network model to reduce the misclassification of rice and non-rice. Initial, the hidden vector hit obtained from the two BiLSTM layers was input into a single-layer neural network to acquire uit , then the transposition of uit and uw , have been multiplied and after that normalized by softmax to acquire the weight it . Subsequently, it and hit were multiplied and summed to get the weighted vector ci . Ultimately, the output of interest ci successively was sent to two totally connected layers and a single softmax layer to acquire the final classification outcome. uit = tan h(Ww hit + bw ) (1) it =T exp uit uw T t exp uit uw(2) (3)ci =htit itwhere hit represents the hidden vector at time t in the ith sample, it , Ww and uw will be the weights, bw is bias, and cit represents the output from the attention mechanism. The hidden vector hit obtained from BiLSTM obtains uit soon after activating the function. Moreover, uw and Ww had been randomly initialized. The BiLSTM-Attention model could efficiently mine the transform info between the preceding time as well as the next time inside the SAR time series data and could discern the high-dimensional time characteristics of rice and non-rice in the time series information. Furthermore, by finding out the variation traits of the temporal backscatter coefficient on the rice growth cycle and the variation traits from the temporal backscatter coefficient of non-rice, the model could extract the crucial temporal data for rice and non-rice, strengthen the capability to distinguish rice and non-rice, and assistance to improve the classification impact in the model. two.two.5. Optimization of Classification Final results Based on FROM-GLC10 As a result of fragmentation of rice plots inside the study area as well as the effect of buildings and water bodies, there may be a misclassification of rice inside the classification results. Additional post-processing was required to improve the classification results. In 2019, the analysis team of Professor Gong Peng, Department of Earth Method Science at Tsinghua University, released the method and final results of worldwide surface coverage mapping with ten m resolution (FROM-GLC10), which is Piperonylic acid Autophagy usually passed by way of http://data. ess.tsinghua.edu.cn (accessed on 22 January 2021) free of charge download. The experimental final results show that the all round accuracy of FROM-GLC10 product is 72.76 [50]. As shown in Figure three, the water layer mask and impermeable layer mask had been extracted from FROM-GLC10, then the rice classification benefits have been optimized working with the intersection from the initial extraction final results as well as the mask layer. 2.two.six. Accuracy Evaluation In this analysis, the precision indicators of your confusion matrix Promestriene Cancer widely used in crop classification analysis have been employed, such as accuracy, precision, recall, F1, and kappa [546]. accuracy = TP + TN TP + TN + FN + FP TP TP + FP (four) (5) (6) (7)precision = recall = F1 =TP TP + FN2TP 2TP + FP + FNAgriculture 2021, 11,13 ofkappa = Pe =accuracy – Pe 1 – Pe(eight) (9)( TP + FP) ( TP + FN ) + ( FN + TN ) ( FP + TN ) ( TP + TN + FN + FP)where TP is definitely the quantity of the rice pixels actually classified as rice pixels, TN will be the variety of non-rice pixels definitely classified as non-rice pixels, FP could be the number of non-rice pixels falsely classified as rice, FN is definitely the number of rice pixels falsely classified as non-rice pi.