[1] Ronse K, Jonckheere R, Gallagher E et al. EUVL is being inserted in manufacturing in 2019: what are the mask related challenges remaining?[J]. Proceedings of SPIE, 11177, 111770A(2019).

[2] Verhoeven E, Schuurhuis R, Mastenbroek M et al. 0.33 NA EUV systems for high volume manufacturing[J]. Proceedings of SPIE, 11517, 1151703(2020).

[3] Capelli R, Dietzel M, Hellweg D et al. Actinic metrology platform for defect review and mask qualification: flexibility and performance[J]. Proceedings of SPIE, 10957, 109570X(2019).

[4] Zhang H, Li S K, Wang X Z. A rapid simulation method for diffraction spectra of EUV lithography mask based on improved structural decomposition[J]. Acta Optica Sinica, 38, 0105001(2018).

[5] Barty A, Mirkarimi P B, Stearns D G et al. EUVL mask blank repair[J]. Proceedings of SPIE, 4688, 385-394(2002).

[6] Bakshi V[M]. EUV lithography(2018).

[7] Liu X L, Li S K, Wang X Z. Simplified model for defective multilayer diffraction spectrum simulation in extreme ultraviolet lithography[J]. Acta Optica Sinica, 34, 0905002(2014).

[8] Hashimoto T, Yamanashi H, Sugawara M et al. Lithographic characterization of EUVL mask blank defects[J]. Proceedings of SPIE, 5374, 740-750(2004).

[9] Zhang H, Li S K, Wang X Z et al. Optimization of defect compensation for extreme ultraviolet lithography mask by covariance-matrix-adaption evolution strategy[J]. Journal of Micro/Nanolithography, MEMS, and MOEMS, 17, 043505(2018).

[10] Jonckheere R, Yamane T, Morikawa Y et al. Blank defect coverage budget for 16 nm half-pitch single EUV exposure[J]. Proceedings of SPIE, 10807, 108070H(2018).

[11] Liu X L, Li S K, Wang X Z et al. Optimal shift of pattern shifting for mitigation of mask defects in extreme ultraviolet lithography[J]. Journal of Vacuum Science & Technology B, 33, 051603(2015).

[12] Miyai H, Suzuki T, Takehisa K et al. The capability of high magnification review function for EUV actinic blank inspection tool[J]. Proceedings of SPIE, 8701, 870118(2013).

[13] Suzuki T, Miyai H, Takehisa K et al. Defect analysis on actinic blank inspection tool[J]. Proceedings of SPIE, 9256, 92560O(2014).

[14] Yamane T, Amano T, Takagi N et al. Advances in the detection capability on actinic blank inspection[J]. Proceedings of SPIE, 9776, 97761G(2016).

[15] Amano T, Watanabe H, Abe T. Phase defect detection signal analysis: dependence of defect size variation[J]. Journal of Micro/Nanolithography, MEMS, and MOEMS, 14, 013502(2015).

[16] Xu D B, Evanschitzky P, Erdmann A. Extreme ultraviolet multilayer defect analysis and geometry reconstruction[J]. Journal of Micro/Nanolithography, MEMS, and MOEMS, 15, 014002(2016).

[17] Chen Y, Lin Y B, Chen R et al. EUV multilayer defect characterization via cycle-consistent learning[J]. Optics Express, 28, 18493-18506(2020).

[18] Cheng W, Li S K, Wang X Z et al. Extreme ultraviolet phase defect characterization based on complex amplitudes of the aerial images[J]. Applied Optics, 60, 5208-5219(2021).

[19] Gu J X, Wang Z H, Kuen J et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 77, 354-377(2018).

[20] Gardner M W, Dorling S R. Artificial neural networks (the multilayer perceptron): a review of applications in the atmospheric sciences[J]. Atmospheric Environment, 32, 2627-2636(1998).

[21] Upadhyaya M, Jindal V, Basavalingappa A et al. Evaluating printability of buried native EUV mask phase defects through a modeling and simulation approach[J]. Proceedings of SPIE, 9422, 94220Q(2015).

[22] Zhang H, Li S K, Wang X Z et al. Fast optimization of defect compensation and optical proximity correction for extreme ultraviolet lithography mask[J]. Optics Communications, 452, 169-180(2019).

[23] Rumpf R C. Improved formulation of scattering matrices for semi-analytical methods that is consistent with convention[J]. Progress in Electromagnetics Research B, 35, 241-261(2011).

[24] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C], 448-456(2015).

[25] Capelli R, Hellweg D, Dietzel M et al. Aerial image based metrology of EUV masks: recent achievements, status, and outlook for the AIMS EUV platform[J]. Proceedings of SPIE, 10583, 1058311(2018).

[26] Paszke A, Gross S, Massa F et al. PyTorch: an imperative style, high-performance deep learning library[EB/OL]. https://arxiv.org/abs/1912.01703

[27] Harris-Jones J, Jindal V, Kearney P et al. Smoothing of substrate pits using ion beam deposition for EUV lithography[J]. Proceedings of SPIE, 8322, 83221S(2012).

[28] Kingma D P, Ba J. Adam: a method for stochastic optimization[EB/OL]. https://arxiv.org/abs/1412.6980