2026-10-14T13:47:18Z https://www.scidb.cn/oai

10.57760/sciencedb.25157 2025-05-22T14:42:20Z

2025-05-22 Figures and details of manuscript "GAST-Net: Emission Spectroscopy Tomographic Reconstruction and Prediction with Gated Recurrent Units and Attention Mechanism" doi:10.57760/sciencedb.25157 en This dataset includs the figures and details of manuscript "GAST-Net: Emission Spectroscopy Tomographic Reconstruction and Prediction with Gated Recurrent Units and Attention Mechanism"Figure 1 Schematic Diagram of CTC Imaging SystemFigure 2 GAST-Net neural network model.(a)Network model architecture (b)GRU model structure (c) Attention mechanism diagramFigure 3 GAST-Net algorithm flowchartFigure 4 Comparison between model predicted reconstructed structure and real reconstructed structure. (a) Predicting three-dimensional structures; (b) Real three-dimensional structure; (c) Predicting two-dimensional slices of structures; (d) Real structure two-dimensional slice; (e) Quality evaluation functions for predicting and realistic structuresFigure 5 Comparison between the predicted results of the future time model and the three-dimensional structural view of real data. (a-c) Predict the reconstruction results for the first, third, and fifth moments in the future; (d-f) Traditional reconstruction results for the first, third, and fifth moments in the future; (g) Quality evaluation function of prediction and real structureFigure 6 Cross sectional comparison and difference between combustion field and real data in the future.(a)The first moment of the future;(b)The third moment of the future;(c)The fifth moment of the futureFigure 7 Quality evaluation function between prediction results of multiple time steps and real data.(a)SSIM;(b)CORR;(c)RMSE;(d)PSNRFigure 8 Compare the predicted results with the 3D structural view of the real data when inserting three frames. (a-c) Inter frame prediction reconstruction results; (d-f) Traditional reconstruction results;(g) Quality evaluation function of prediction and real structureFigure 9 Cross sectional comparison and difference between inter frame predicted combustion field results and real data. (a) The first frame in the middle; (b) The second frame in the middle; (c) The third frame in the middleFigure 10 Quality evaluation function for different inter frame prediction quantities. (a) SSIM (b) CORR; (c) RMSE; (d) PSNR computed tomography; three-dimensional reconstruction; time series prediction; deep learning; gate controlled cycle unit; attention mechanism Ying Jin RESTRICTED dataset Science Data Bank