Machine-learning-aided discovery of methanol-to-olefins zeolite catalysts with ultra-high initial selectivity

doi:10.1016/S1872-2067(25)64903-5

Abstract

Abstract:

With the continuous advancement of the industrialized methanol-to-olefins (MTO) process and a profound understanding of its mechanism, designing MTO catalysts to enhance light olefin yields and flexibly regulate product distribution has emerged as a significant challenge. Data-driven modeling allows chemists to anticipate reaction trends and outcomes. However, for models to be instructive for specific chemical issues, chemists must collect experimental data, encode the relevant variables and retrain specialized models. In this work, we demonstrate how to use a machine learning (ML) workflow to discover a potential MTO zeolite catalyst. An MTO database was built, on which over 20 types of ML models were trained, followed by their evaluation and experimental validation. The decision rules for high selectivity were extracted, facilitating the targeting of potential MTO catalysts and the understanding of MTO reaction mechanism. A rapid prediction of optimal MTO evaluation conditions and results for a given zeolite catalyst was also realized, greatly saving the cost of trial and error. In particular, a special MTO catalyst with high initial ethene selectivity over 60% was found, demonstrating the effectiveness and capability of ML techniques.

Key words: Methanol to olefins, Zeolite catalyst, Machine learning, Rational design and synthesis, Prediction

Xinyi Wang, Chaoqi Wang, Miao Yang, Xiaoguang Wang, Yuezhong Zuo, Zhuangzhuang Zhang, Yimo Wu, Jingfeng Han, Bing Li, Wei Huang, Limin Ren, Yingxu Wei, Xinmei Liu, Peng Tian, Zhongmin Liu. Machine-learning-aided discovery of methanol-to-olefins zeolite catalysts with ultra-high initial selectivity[J]. Chinese Journal of Catalysis, 2026, 81: 124-135.

×
share this article

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.cjcatal.com/EN/10.1016/S1872-2067(25)64903-5

https://www.cjcatal.com/EN/Y2026/V81/I2/124

Figures/Tables 9

Fig. 1. Schematic for curating the datasets: extracting structural parameters of zeolites from the IZA database, searching for MTO catalytic results of different zeolites from published papers, downloading the papers, and mining text, tables and graphs for reaction conditions and catalytic results.

Table 1 The type, name and range of the variables in the MTO database.

Variables		Name of variables/units	Range/counts
Input variables	catalyst property	Mod.	0/5463
		Mod.	1/1273
		AS	0 (SAPO)/1959
		AS	1 (zeolite)/4777
		A/T	0-1
		FD_Si/T/1000Å [3]	12.80-19.70
		LRS	8-MR/4159
			10-MR/1843
			12-MR/712
			18-MR/22
		MD_a/Å	1.27-7.35
		MD_b/Å	1.49-7.35
		MD_c/Å	1.53-11.20
		MD_i/Å	5.25-11.74
		CD	1D/436
			2D/1421
			3D/4879
		CS/µm	0.02-5.00
	reaction conditions	RT/°C	270-700
		WHSV/h^‒1	0.35-48.00
		TOS/min	0-30156.92
Output variables		methanol conversion/%	0.00-100.00
		S_ethene/%	0.00-68.61
		S_propene/%	0.00-68.90
		S_C2=+C3=/%	0.00-92.21
		P/E	0.00-37.37

Fig. 2. (a) Illustration of some inputs including AS (acid strength): 0 for SAPO and 1 for aluminosilicate; A/T (acid density): Si/T for SAPO and Al/T for aluminosilicate (T refers to the sum of framework atoms [T atoms]); Mod.: 1 for modified and 0 for unmodified. (b) The correlation heatmap of all inputs in the MTO dataset.

Fig. 3. Summary of the AUC for each ML algorithm for classification of methanol conversion. The inset is the performance of classification on the whole dataset given by the stacking classifier.

Fig. 4. Feature importance heuristic given by the DT classifier for methanol conversion and visual structure of the DT. Some of the typical leave notes mentioned have been highlighted with bule solid (with more “low” points) and red dotted line (with more “high” points) circles.

Fig. 5. The performance of 23 ML methods for SC2=+C3= (a) and P/E (b) respectively. Four metrics, MAE, RMSE, R2, and RMSLE were used to evaluate these methods. The ML methods before the gray line are better. The training and test sets of SC2=+C3= (c) and P/E (d) by Stacking Regressor.

Fig. 6. (a) The visual structure of the DT. The numbers below the points are the average values of SC2=+C3=. (b) The feature importance heuristic given by the DT Regressor for SC2=+C3=. (c) SHAP analysis for SC2=+C3=. A color gradient, ranging from blue solid line (low feature values) to pink/red dotted line (high feature values), helps visualize the correlation between feature values and their SHAP values.

Table 2 Lists of the information on materials belonging to the seven topologies.

Topology	SAPOs	A/T	Zeolites	A/T	CD
AEI	SAPO-18 [64]	0‒0.1	SSZ-39 [65]	0.1	3
AWW	AlPO-22 [66] AlPO-CJB1 [67]	0	none	—	1
AFT	AlPO-52 [68]	0	SSZ-112 [69]	~0.13	3
AFX	SAPO-56 [70,71]	0.15‒0.2	SSZ-16 [72]	0.14	3
CHA	SAPO-34 [73]	0.05‒0.2	SSZ-13 [74-76]	0.02‒0.2, 0	3
DDR	none	—	ZSM-58 [77,78]	0.01‒0.02, 0	2
SFW	none	—	SSZ-52 [79]	0.11	3

Fig. 7. (a) MTO catalytic performance of SSZ-13s with different Si/Al ratios at 450 °C, WHSV of 1.0 h−1. (b) The experimental (solid symbols) and predicted (hollow symbols) MTO catalytic performance of STT-100 at 450 °C and WHSV of 1.0 h−1. The predicted lifetime is labeled by the gray dotted line.

References

[1]	G. W. Huber, S. Iborra, A. Corma, Chem. Rev., 2006, 106, 4044-4098.
[2]	B. Yilmaz, U. Müller, Top. Catal., 2009, 52, 888-895.
[3]	J. Liang, H. Li, S. Zhao, W. Guo, R. Wang, M. Ying, Appl. Catal., 1990, 64, 31-40.
[4]	M. Stöcker, Microporous Mesoporous Mater., 1999, 29, 3-48.
[5]	P. Tian, Y. Wei, M. Ye, Z. Liu, ACS Catal., 2015, 5, 1922-1938.
[6]	M. Yang, D. Fan, Y. Wei, P. Tian, Z. Liu, Adv. Mater., 2019, 31, 1902181.
[7]	X. Jiang, X. Nie, X. Guo, C. Song, J. G. Chen, Chem. Rev., 2020, 120, 7984-8034.
[8]	U. Olsbye, S. Svelle, M. Bjørgen, P. Beato, T. V. W. Janssens, F. Joensen, S. Bordiga, K. P. Lillerud, Angew. Chem. Int. Ed., 2012, 51, 5810-5831.
[9]	J. H. Kang, F. H. Alshafei, S. I. Zones, M. E. Davis, ACS Catal., 2019, 9, 6012-6019.
[10]	P. Ferri, C. Li, C. Paris, A. Vidal-Moya, M. Moliner, M. Boronat, A. Corma, ACS Catal., 2020, 9, 11542-11551.
[11]	S. Standl, O. Hinrichsen, Catalysts, 2018, 8, 626.
[12]	Q. Zhang, G. Chen, Y. Wang, M. Chen, G. Guo, J. Shi, J. Luo, J. Yu, Chem. Mater., 2018, 30, 2750-2758.
[13]	Y. Wu, J. Han, W. Zhang, Z. Yu, K. Wang, X. Fang, Y. Wei, Z. Liu, J. Am. Chem. Soc., 2024, 146, 8086-8097.
[14]	X. Zhao, L. Wang, J. Li, S. Xu, W. Zhang, Y. Wei, X. Guo, P. Tian, Z. Liu, Catal. Sci. Technol., 2017, 7, 5882-5892.
[15]	X. Zhao, L. Wang, P. Guo, N. Yan, T. Sun, S. Lin, X. Guo, P. Tian, Z. Liu, Catal. Sci. Technol., 2018, 8, 2966-2974.
[16]	M. Yoshioka, T. Yokoi, T. Tatsumi, ACS Catal., 2015, 5, 4268-4275.
[17]	Q. Sun, Z. Xie, J. Yu, Natl. Sci. Rev., 2018, 5, 542-558.
[18]	R. Martínez-Franco, Z. Li, J. Martínez-Triguero, M. Moliner, A. Corma, Catal. Sci. Technol., 2016, 6, 2796-2806.
[19]	M. Dusselier, M. E. Davis, Chem. Rev., 2018, 118, 5265-5329.
[20]	I. Pinilla-Herrero, U. Olsbye, C. Márquez-Álvarez, E. Sastre, J. Catal., 2017, 352, 191-207.
[21]	W. Song, A. H. Fu, J. F. Haw, J. Am. Chem. Soc., 2001, 123, 4749-4754.
[22]	J. F. Haw, W. Song, D. M. Marcus, J. B. Nicholas, Acc. Chem. Res., 2003, 36, 317-326.
[23]	J. Li, Y. Wei, J. Chen, P. Tian, X. Su, S. Xu, Y. Qi, Q. Wang, Y. Zhou, Y. He, Z. Liu, J. Am. Chem. Soc., 2012, 134, 836-839.
[24]	J. Li, Y. Wei, J. Chen, S. Xu, P. Tian, X. Yang, B. Li, J. Wang, Z. Liu, ACS Catal., 2015, 5, 661-665.
[25]	S. Lin, Y. Zhi, W. Chen, H. Li, W. Zhang, C. Lou, X. Wu, S. Zeng, S. Xu, J. Xiao, A. Zheng, Y. Wei, Z. Liu, J. Am. Chem. Soc., 2021, 143, 12038-12052.
[26]	M. Yang, B. Li, M. Gao, S. Lin, Y. Wang, S. Xu, X. Zhao, P. Guo, Y. Wei, M. Ye, P. Tian, Z. Liu, ACS Catal., 2020, 10, 3741-3749.
[27]	Y. Wang, J. Han, N. Wang, B. Li, M. Yang, Y. Wu, Z. Jiang, Y. Wei, P. Tian, Z. Liu, Chin. J. Catal., 2022, 43, 2259-2269.
[28]	S. Xu, Y. Zhi, J. Han, W. Zhang, X. Wu, T. Sun, Y. Wei, Z. Liu, Adv. Catal., 2017, 61, 37-122.
[29]	S. Lin, Y. Zhi, Z. Liu, J. Yuan, W. Liu, W. Zhang, Z. Xu, A. Zheng, Y. Wei, Z. Liu,, Natl. Sci. Rev., 2022, 9, nwac151.
[30]	S. Lin, Y. Zhi, W. Zhang, X. Yuan, C. Zhang, M. Ye, S. Xu, Y. Wei, Z. Liu, Chin. J. Catal., 2023, 46, 11-27.
[31]	Y. Li, H. Cao, J. Yu, ACS Nano, 2018, 12, 4096-4104.
[32]	S. Chen, L. Li, Y. Li, J. Yu, Chem. J. Chin. Univ., 2021, 42, 179-187.
[33]	M. Gao, H. Li, J. Yu, M. Ye, Z. Liu, AlChE. J., 2023, 69, e17881.
[34]	P. Raccuglia, K. C. Elbert, P. D. F. Adler, C. Falk, M. B. Wenny, A. Mollo, M. Zeller, S. A. Friedler, J. Schrier, A. J. Norquist, Nature, 2016, 533, 73-76.
[35]	K. T. Butler, D. W. Davies, H. Cartwright, O. Isayev, A. Walsh, Nature, 2018, 559, 547-555.
[36]	I. W. Davies, Nature, 2019, 570, 175-181.
[37]	O. Kononova, T. He, H. Huo, A. Trewartha, E. A. Olivetti, G. Ceder, iScience, 2021, 24, 102155.
[38]	A. F. Zahrt, J. J. Henle, B. T. Rose, Y. Wang, W. T. Darrow, S. E. Denmark, Science, 2019, 363, eaau5631.
[39]	T. Toyao, Z. Maeno, S. Takakusagi, T. Kamachi, I. Takigawa, K.-I. Shimizu, ACS Catal., 2020, 10, 2260-2297.
[40]	M. K. Nielsen, D. T. Ahneman, O. Riera, A. G. Doyle, J. Am. Chem. Soc., 2018, 140, 5004-5008.
[41]	R. Ding, R. Wang, Y. Ding, W. Yin, Y. Liu, J. Li, J. Liu, Angew. Chem. Int. Ed., 2020, 59, 19175-19183.
[42]	S. Bae, H. Lee, J. Shin, H. S. Kim, Y. Kim, D. H. Kim, J. M. Lee, Chem. Mater., 2022, 34, 7761-7773.
[43]	E. Kim, K. Huang, A. Tomala, S. Matthews, E. Strubell, A. Saunders, A. McCallum, E. Olivetti, Sci. Data, 2017, 4, 170127.
[44]	A. Nandy, C. Duan, H. J. Kulik, J. Am. Chem. Soc., 2021, 143, 17535-17547.
[45]	Z. Jensen, E. Kim, S. Kwon, T. Z. H. Gani, Y. Román-Leshkov, M. Moliner, A. Corma, E. Olivetti, ACS Cent. Sci., 2019, 5, 892-899.
[46]	Z. Jensen, S. Kwon, D. Schwalbe-Koda, C. Paris, R. Gómez-Bombarelli, Y. Román-Leshkov, A. Corma, M. Moliner, E. A. Olivetti, ACS Cent. Sci., 2021, 7, 858-867.
[47]	E. Pan, S. Kwon, Z. Jensen, M. Xie, R. Gómez-Bombarelli, M. Moliner, Y. Román-Leshkov, E. Olivetti, ACS Cent. Sci., 2024, 10, 729-743.
[48]	Z. Hajjar, A. Khodadadi, Y. Mortazavi, S. Tayyebi, S. Soltanali, Fuel, 2016, 179, 79-86.
[49]	www.iza-structure.org/databases.
[50]	Z.-M. Cui, Q. Liu, W. Song, L. Wan, Angew. Chem. Int. Ed., 2006, 45, 6512-6515.
[51]	X. Sun, S. Mueller, Y. Liu, H. Shi, G. L. Haller, M. Sanchez-Sanchez, A. C. van Veen, J. A. Lercher, J. Catal., 2014, 317, 185-197.
[52]	G. Yang, Y. Wei, S. Xu, J. Chen, J. Li, Z. Liu, J. Yu, R. Xu, J. Phys. Chem. C, 2013, 117, 8214-8222.
[53]	M. Yang, P. Tian, C. Wang, Y. Yuan, Y. Yang, S. Xu, Y. He, Z. Liu, Chem. Commun., 2014, 50, 1845.
[54]	Z. Li, M. T. Navarro, J. Martínez-Triguero, J. Yu, A. Corma, Catal. Sci. Technol., 2016, 6, 5856-5863.
[55]	P. Ferri, C. Li, R. Millán, J. Martínez-Triguero, M. Moliner, M. Boronat, A. Corma, Angew. Chem. Int. Ed., 2020, 59, 19708-19715.
[56]	W. Zhang, S. Lin, Y. Wei, P. Tian, M. Ye, Z. Liu, Natl. Sci. Rev., 2023, 10, nwad120.
[57]	C. Yuan, Y. Wei, J. Li, S. Xu, J. Chen, Y. Zhou, Q. Wang, L. Xu, Z. Liu, Chin. J. Catal., 2012, 33, 367-374.
[58]	E. M. Gallego, M. T. Portilla, C. Paris, A. León-Escamilla, M. Boronat, M. Moliner, A. Corma, Science, 2017, 355, 1051-1054.
[59]	D. Chen, K. Moljord, T. Fuglerud, A. Holmen, Microporous Mesoporous Mater., 1999, 29, 191-203.
[60]	D. Lesthaeghe, B. De Sterck, V. Van Speybroeck, G. Marin, M. Waroquier, Angew. Chem. Int. Ed., 2007, 46, 1311-1314.
[61]	J. Chen, J. Li, Y. Wei, C. Yuan, B. Li, S. Xu, Y. Zhou, J. Wang, M. Zhang, Z. Liu, Catal. Commun., 2014, 46, 36-40.
[62]	X. Li, Q. Sun, Y. Li, N. Wang, J. Lu, J. Yu, J. Phys. Chem. C, 2014, 118, 24935-24940.
[63]	G. E. P. Box, D. R. Cox, J. R. Stat. Soc. B, 1964, 26, 211-252.
[64]	J. Chen, J. M. Thomas, P. A. Wright, R. P. Townsend, Catal. Lett., 1994, 28, 241-248.
[65]	M. Dusselier, M. A. Deimund, J. E. Schmidt, M. E. Davis, ACS Catal., 2015, 5, 6078-6085.
[66]	N. Venkatathri, Indian J. Chem. A, 2002, 41, 2223-2230.
[67]	W. Yan, J. Yu, R. Xu, G. Zhu, F. Xiao, Y. Han, K. Sugiyama, O. Terasaki, Chem. Mater., 2000, 12, 2517-2519.
[68]	N. K. McGuire, C. A. Bateman, C. Scott Blackwell, S. T. Wilson, R. M. Kirchner, Zeolites, 1995, 15, 460-469.
[69]	D. Xie, Ind. Eng. Chem. Res., 2021, 60, 15403-15415.
[70]	P. Tian, L. Xu, Z. M. Liu, C. L. Sun, T. Huang, Chem. J. Chin. Univ., 2001, 22, 991-994.
[71]	D. Wang, M. Yang, W. Zhang, D. Fan, P. Tian, Z. Liu, CrystEngComm, 2016, 18, 1000-1008.
[72]	R. F. Lobo, S. I. Zones, R. C. Medrud, Chem. Mater., 1996, 8, 2409-2411.
[73]	M. Briend, R. Vomscheid, M. J. Peltre, P. P. Man, D. Barthomeuf, J. Phys. Chem., 1995, 99, 8270-8276.
[74]	S. I. Zones, US 4,544,538, 1985.
[75]	M.-J. Díaz-Cabañas, P. A. Barrett, Chem. Commun., 1998, 1881-1882.
[76]	L. Wang, D. Zhu, J. Wang, W. Cui, J. Han, B. Li, D. Fan, P. Tian, Z. Liu, J. Mater. Chem. A, 2021, 9, 15238-15245.
[77]	I. Yarulina, A. Dikhtiarenko, F. Kapteijn, J. Gascon, Catal. Sci. Technol., 2017, 7, 300-309.
[78]	I. Yarulina, J. Goetze, C. Gücüyener, L. van Thiel, A. Dikhtiarenko, J. Ruiz-Martinez, B. M. Weckhuysen, J. Gascon, F. Kapteijn, Catal. Sci. Technol., 2016, 6, 2663-2678.
[79]	D. Xie, L. B. McCusker, C. Baerlocher, S. I. Zones, W. Wan, X. Zou, J. Am. Chem. Soc., 2013, 135, 10519-10524.
[80]	S. Lin, H. Li, P. Tian, Y. Wei, M. Ye, Z. Liu, J. Am. Chem. Soc., 2025, 147, 11585-11607.
[81]	X. Wang, Y. Zuo, Z. Zhang, C. Wang, M. Yang, P. Tian, Z. Liu, software copyright 2024SR0082804, 2024.
[82]	X. Zhu, Y. Gao, M. Liu, Z. Yang, S. Li, H. Chen, B. Liu, W. Ma, E. J. M. Hensen, B. Shen, Microporous Mesoporous Mater., 2022, 345, 112260.
[83]	E. Borodina, F. Meirer, I. Lezcano-González, M. Mokhtar, A. M. Asiri, S. A. Al-Thabaiti, S. N. Basahel, J. Ruiz-Martinez, B. M. Weckhuysen, ACS Catal., 2015, 5, 992-1003.
[84]	X. Zhu, J. P. Hofmann, B. Mezari, N. Kosinov, L. Wu, Q. Qian, B. M. Weckhuysen, S. Asahina, J. Ruiz-Martínez, E. J. M. Hensen, ACS Catal., 2016, 6, 2163-2177.
[85]	Z. Xu, H. Ma, Y. Huang, W. Qian, H. Zhang, W. Ying, ACS Omega, 2020, 5, 24574-24583.
[86]	F. H. Alshafei, Y. Park, S. I. Zones, M. E. Davis, J. Catal., 2021, 404, 620-633.
[87]	J. Zhou, Y. Zhi, J. Zhang, Z. Liu, T. Zhang, Y. He, A. Zheng, M. Ye, Y. Wei, Z. Liu,, J. Catal., 2019, 377, 153-162.
[88]	C. Zhang, X. Wu, Y. Zhang, W. Zhang, S. Lin, C. Lou, S. Xu, D. He, L. Wang, Y. Wei, Z. Liu, Chem. Catal., 2024, 4, 101025.
[89]	W. Huang, H. Wu, X. Yan, J. Zhang, Z. Feng, M. Yang, P. Tian, X. Guo, L. Ren, Ind. Eng. Chem. Res., 2024, 63, 15438-15447.