[1] [1] Zhang T T. Study on LIBS calibration inversion of Martian material composition explation[D]. Shanghai: University of Chinese Academy of Sciences (Shanghai Institute of Technical Physics, Chinese Academy of Sciences), 2017. (in Chinese)

[2] Fu Lin, Li Yeqiu, Zhen Jia, et al. Spectral characteristics of laser-induced breakdown of organic explosives at low atmospheric pressure[J]. Infrared and Laser Engineering, 51, 20210720(2022).

[3] Yang Yanwei, Hao Xiaojian, Pan Baowu, et al. Parameter optimization of laser-induced breakdown bauxite spectra based on cavity confinement[J]. Infrared and Laser Engineering, 51, 20210661(2022).

[4] Ren J, Gao X. Detection of heavy metal Pb in soil by femtosecond filament nanosecond laser induced breakdown spectroscopy[J]. Optical and Precision Engineering, 27, 1069-1074(2019).

[5] Chen S H, Lu J D, Zhang B, et al. Controlling factors of measuring pulverized coal flow by laser induced breakdown spectroscopy[J]. Optical and Precision Engineering, 21, 1651-1658(2013).

[6] Li C Y, Qu L, Gao F, et al. Analysis of surface and depth distribution of metal and ceramic cultural relics by laser-induced breakdown spectroscopy[J]. Chinese Optics, 13, 1239-1248(2020).

[7] Li A Z, Wang X S, Xu X J, et?al. Study on rapid classification of tobacco by laser induced breakdown spectroscopy[J]. Chinese Optics, 12, 1139-1146(2019).

[8] Yang Y L, Wang L, Ma C H. Quantitative analysis of elements in LIBS liquid steel optimized by improved particle swarm optimization SVR[J]. Laser & Optoelectronics Progress, 57, 053002(2020).

[9] Anderson R B, Clegg S M, Frydenvang J, et al. Improved accuracy in quantitative laser-induced breakdown spectroscopy using sub-models[J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 129, 49-57(2017).

[10] Clegg S M, Wiens R C, Anderson R, et al. Recalibration of the Mars science laboratory ChemCam instrument with an expanded geochemical database[J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 129, 64-85(2017).

[11] Ma C H, Zhao S C. Quantitative analysis of Mn in molten steel by genetic neural network combined with LIBS technology[J]. Modern Electronics Technique, 41, 169-173(2018).

[12] Jiang H, Hu H, Zhong R, et al. A deep learning approach to conflating heterogeneous geospatial data for corn yield estimation: A case study of the US Corn Belt at the county level[J]. Global Change Biology, 26, 1754-1766(2020).

[13] [13] Deng Lei. Infrared human target detection motion recognition based on deep learning[D]. Hangzhou: Zhejiang University, 2020. (in Chinese)

[14] Lazic V, De Ninno A. Calibration approach for extremely variable laser induced plasmas and a strategy to reduce the matrix effect in general[J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 137, 28-38(2017).

[15] Gong T T, Tian Y, Chen Q, et?al. Matrix effect and quantitative analysis of LIBS spectra of iron filings with different particle sizes[J]. Spectroscopy and Spectral Analysis, 40, 1207-1213(2020).

[16] [16] He K, Zhang X, Ren S, et al. Deep residual learning f image recognition. 3. Deep Residual Learning 34[C]Proceedings of the IEEE Conference on Computer Vision Pattern Recognition, 2016: 770778.

[17] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 15, 1929-1958(2014).

[18] Nagelkerke N J D. A note on a general definition of the coefficient of determination[J]. Biometrika, 78, 691-692(1991).

[19] Zeiler M D. Adadelta: An adaptive learning rate method[J]. arXiv preprint arXiv, 1212.5701(2012).

[20] [20] Chollet F. Xception: Deep learning with depthwise separable convolutions[C]Proceedings of the IEEE , 2017: 12511258.