Climate uncertainty and asset pricing decisions: A machine learning analysis

Shuhua Zhang; Tong Wang; Ning Ye; Xinyu Wang; Rui Wang; Shuhua Zhang; Tong Wang; Ning Ye; Xinyu Wang; Rui Wang

doi:10.3934/jimo.2026124

Journal of Industrial and Management Optimization

2026, Volume 22, Issue 7: 3386-3418. doi: 10.3934/jimo.2026124

Previous Article Next Article

Research article

Climate uncertainty and asset pricing decisions: A machine learning analysis

1.
Coordinated Innovation Center for Computable Modelling in Management Science Tianjin University of Finance and Economics, Tianjin 300222, China
2.
Zhujiang College, South China Agricultural University, Guangzhou 510900, China
3.
School of Law, Tianjin University of Finance and Economics, Tianjin 300222, China

Received: 15 March 2026 Revised: 08 June 2026 Accepted: 15 June 2026 Published: 25 June 2026
91G80, 93E20, 60J75, 49L20

Climate change and climate-model uncertainty have important implications for macroeconomic allocation, carbon policy, and asset pricing. This paper develops a multi-sector Dynamic Stochastic General Equilibrium (DSGE) model with temperature dynamics, climate damages, carbon accumulation, productivity shocks, and ambiguity-averse preferences. Methodologically, we integrate climate-model uncertainty, ambiguity aversion, DSGE modeling, and the Deep Galerkin Method (DGM) into a unified computational framework. This approach enables us to solve a high-dimensional equilibrium system and examine resource allocation, carbon taxation, and asset-pricing responses under uncertainty. The framework extends conventional climate-economy and carbon-pricing studies by jointly analyzing macroeconomic and financial effects in the presence of climate-model uncertainty. The numerical results show that uncertainty accelerates the reallocation from brown inputs to green inputs, raises the model-implied carbon tax, and affects the equilibrium risk-free rate and price of risk. These findings provide a model-based benchmark for carbon-pricing design, sustainable investment, and climate-related risk management by policymakers, regulators, and financial market participants.
- climate change,
- model uncertainty,
- machine learning,
- production-based carbon tax
Citation: Shuhua Zhang, Tong Wang, Ning Ye, Xinyu Wang, Rui Wang. Climate uncertainty and asset pricing decisions: A machine learning analysis[J]. Journal of Industrial and Management Optimization, 2026, 22(7): 3386-3418. doi: 10.3934/jimo.2026124

Related Papers:

Abstract

Climate change and climate-model uncertainty have important implications for macroeconomic allocation, carbon policy, and asset pricing. This paper develops a multi-sector Dynamic Stochastic General Equilibrium (DSGE) model with temperature dynamics, climate damages, carbon accumulation, productivity shocks, and ambiguity-averse preferences. Methodologically, we integrate climate-model uncertainty, ambiguity aversion, DSGE modeling, and the Deep Galerkin Method (DGM) into a unified computational framework. This approach enables us to solve a high-dimensional equilibrium system and examine resource allocation, carbon taxation, and asset-pricing responses under uncertainty. The framework extends conventional climate-economy and carbon-pricing studies by jointly analyzing macroeconomic and financial effects in the presence of climate-model uncertainty. The numerical results show that uncertainty accelerates the reallocation from brown inputs to green inputs, raises the model-implied carbon tax, and affects the equilibrium risk-free rate and price of risk. These findings provide a model-based benchmark for carbon-pricing design, sustainable investment, and climate-related risk management by policymakers, regulators, and financial market participants.

References

[1]	H. D. Matthews, N. P. Gillett, P. A. Stott, K. Zickfeld, The proportionality of global warming to cumulative carbon emissions, Nature, 459 (2009), 829–832. https://doi.org/10.1038/nature08047 doi: 10.1038/nature08047
[2]	L. Berger, M. Marinacci, Model uncertainty in climate change economics: A review and proposed framework for future research: L. berger, m. marinacci, Environ. Resour. Econ., 77 (2020), 475–501. https://doi.org/10.1007/s10640-020-00503-3 doi: 10.1007/s10640-020-00503-3
[3]	R. S. Pindyck, The climate policy dilemma, Rev. Environ. Econ. Policy, 7 (2013), 219–237. https://doi.org/10.1093/reep/ret007 doi: 10.1093/reep/ret007
[4]	M. Burke, S. M. Hsiang, E. Miguel, Global non-linear effect of temperature on economic production, Nature, 527 (2015), 235–239. https://doi.org/10.1038/nature15725 doi: 10.1038/nature15725
[5]	F. Joos, R. Roth, J. S. Fuglestvedt, G. P. Peters, I. G. Enting, W. V. Bloh, et al., Carbon dioxide and climate impulse response functions for the computation of greenhouse gas metrics: a multi-model analysis, Atmos. Chem. Phys., 13 (2013), 2793–2825. https://doi.org/10.5194/acp-13-2793-2013 doi: 10.5194/acp-13-2793-2013
[6]	B. Kalaycı, A. Özmen, G. W. Weber, Mutual relevance of investor sentiment and finance by modeling coupled stochastic systems with mars, Ann. Oper. Res., 295 (2020), 183–206. https://doi.org/10.1007/s10479-020-03757-8 doi: 10.1007/s10479-020-03757-8
[7]	B. Z. Temoçin, G. W. Weber, Optimal control of stochastic hybrid system with jumps: a numerical approximation, J. Comput. Appl. Math., 259 (2014), 443–451. https://doi.org/10.1016/j.cam.2013.10.021 doi: 10.1016/j.cam.2013.10.021
[8]	İ. Özcan, S. Z. A. Gök, G. W. Weber, Peer group situations and games with fuzzy uncertainty, J. Ind. Manag. Optim., 20 (2024), 428–438. https://doi.org/10.3934/jimo.2023084 doi: 10.3934/jimo.2023084
[9]	M. Ferreira, D. Pinheiro, S. Pinheiro, Two-player zero-sum stochastic differential games with markov-switching jump-diffusion dynamics, J. Dyn. Games, 15 (2025), 1–35. https://doi.org/10.3934/jdg.2025028 doi: 10.3934/jdg.2025028
[10]	N. Azevedo, D. Pinheiro, S. Pinheiro, Dynamic programming for semi-markov modulated sdes, Optimization, 71 (2022), 2315–2342. https://doi.org/10.1080/02331934.2020.1839072 doi: 10.1080/02331934.2020.1839072
[11]	M. Ferreira, D. Pinheiro, S. Pinheiro, Two-player zero-sum stochastic differential games with random horizon, Adv. Appl. Probab., 51 (2019), 1209–1235. https://doi.org/10.1017/apr.2019.47 doi: 10.1017/apr.2019.47
[12]	C. Hambel, H. Kraft, E. Schwartz, Optimal carbon abatement in a stochastic equilibrium model with climate change, Eur. Econ. Rev., 132 (2021), 103642. https://doi.org/10.1016/j.euroecorev.2020.103642 doi: 10.1016/j.euroecorev.2020.103642
[13]	T. V. D. Bremer, F. V. D. Ploeg, Pricing carbon under economic and climactic risks: leading-order results from asymptotic analysis, 2018. Available from: https://ideas.repec.org/p/cpr/ceprdp/12642.html.
[14]	S. Olijslagers, S. V. Wijnbergen, Discounting the future: On climate change, ambiguity aversion and epstein–zin preferences: S. olijslagers, s. van wijnbergen, Environ. Resour. Econ., 87 (2024), 683–730. https://doi.org/10.1007/s10640-023-00832-z doi: 10.1007/s10640-023-00832-z
[15]	K. D. Daniel, R. B. Litterman, G. Wagner, Declining CO₂ price paths, Proc. Natl. Acad. Sci. U.S.A., 116 (2019), 20886–20891. https://doi.org/10.1073/pnas.1817444116 doi: 10.1073/pnas.1817444116
[16]	W. Brock, A. Xepapadeas, Regional climate policy under deep uncertainty: robust control and distributional concerns, Environ. Dev. Econ., 26 (2021), 211–238. https://doi.org/10.1017/S1355770X20000248 doi: 10.1017/S1355770X20000248
[17]	E. Savku, G. W. Weber, A stochastic maximum principle for a markov regime-switching jump-diffusion model with delay and an application to finance, J. Optim. Theory Appl., 179 (2018), 696–721. https://doi.org/10.1007/s10957-017-1159-3 doi: 10.1007/s10957-017-1159-3
[18]	N. Azevedo, D. Pinheiro, G. W. Weber, Dynamic programming for a markov-switching jump–diffusion, J. Comput. Appl. Math., 267 (2014), 1–19. https://doi.org/10.1016/j.cam.2014.01.021 doi: 10.1016/j.cam.2014.01.021
[19]	E. Savku, G. W. Weber, Stochastic differential games for optimal investment problems in a markov regime-switching jump-diffusion market, Ann. Oper. Res., 312 (2022), 1171–1196. https://doi.org/10.1007/s10479-020-03768-5 doi: 10.1007/s10479-020-03768-5
[20]	M. Barnett, Climate change and uncertainty: An asset pricing perspective, Manag. Sci., 69 (2023), 7562–7584. https://doi.org/10.1287/mnsc.2022.4635 doi: 10.1287/mnsc.2022.4635
[21]	D. Lemoine, C. Traeger, Watch your step: Optimal policy in a tipping climate, Am. Econ. J. Econ. Policy, 6 (2014), 137–66. https://doi.org/10.1257/pol.6.1.137 doi: 10.1257/pol.6.1.137
[22]	M. Aengenheyster, Q. Y. Feng, F. V. D. Ploeg, H. A. Dijkstra, The point of no return for climate action: Effects of climate uncertainty and risk tolerance, Earth Syst. Dynam., 9 (2018), 1085–1095. https://doi.org/10.5194/esd-9-1085-2018 doi: 10.5194/esd-9-1085-2018
[23]	S. Hsiang, R. Kopp, A. Jina, J. Rising, M. Delgado, S. Mohan, et al., Estimating economic damage from climate change in the united states, Science, 356 (2017), 1362–1369. https://doi.org/10.1126/science.aal4369 doi: 10.1126/science.aal4369
[24]	R. G. Newell, B. C. Prest, S. E. Sexton, The gdp-temperature relationship: implications for climate change damages, J. Environ. Econ. Manag., 108 (2021), 102445. https://doi.org/10.1016/j.jeem.2021.102445 doi: 10.1016/j.jeem.2021.102445
[25]	M. Golosov, J. Hassler, P. Krusell, A. Tsyvinski, Optimal taxes on fossil fuel in general equilibrium, Econometrica, 82 (2014), 41–88. https://doi.org/10.3982/ECTA10217 doi: 10.3982/ECTA10217
[26]	S. Olijslagers, F. V. D. Ploeg, S. V. Wijnbergen, On current and future carbon prices in a risky world, J. Econ. Dyn. Control, 146 (2023), 104569. https://doi.org/10.1016/j.jedc.2022.104569 doi: 10.1016/j.jedc.2022.104569
[27]	Y. Cai, T. S. Lontzek, The social cost of carbon with economic and climate risks, J. Polit. Econ., 127 (2019), 2684–2734. https://doi.org/10.1086/701890 doi: 10.1086/701890
[28]	T. S. V. D. Bremer, F. V. D. Ploeg, The risk-adjusted carbon price, Am. Econ. Rev., 111 (2021), 2782–2810. https://doi.org/10.1257/aer.20180517 doi: 10.1257/aer.20180517
[29]	M. Donadelli, P. Grüning, S. Hitzemann, Understanding macro and asset price dynamics during the climate transition, SSRN Electron. J., 2019. Available from: https://EconPapers.repec.org/RePEc: lie: dpaper: 18.
[30]	H. Ai, D. Kiku, Volatility risks and growth options, Manag. Sci., 62 (2016), 741–763. https://doi.org/10.1287/mnsc.2014.2129 doi: 10.1287/mnsc.2014.2129
[31]	F. Ackerman, E. A. Stanton, Climate risks and carbon prices: Revising the social cost of carbon, Economics, 6 (2012), 1–25. https://doi.org/10.5018/economics-ejournal.ja.2012-10 doi: 10.5018/economics-ejournal.ja.2012-10
[32]	S. Dietz, N. Stern, Endogenous growth, convexity of damage and climate risk: How nordhaus' framework supports deep cuts in carbon emissions, Econ. J., 125 (2015), 574–620. https://doi.org/10.1111/ecoj.12188 doi: 10.1111/ecoj.12188
[33]	D. L. Kelly, C. D. Kolstad, Bayesian learning, growth, and pollution, J. Econ. Dyn. Control, 23 (1999), 491–518. https://doi.org/10.1016/S0165-1889(98)00034-7 doi: 10.1016/S0165-1889(98)00034-7
[34]	W. A. Pizer, The optimal choice of climate change policy in the presence of uncertainty, Resour. Energy Econ., 21 (1999), 255–287. https://doi.org/10.1016/S0928-7655(99)00005-6 doi: 10.1016/S0928-7655(99)00005-6
[35]	B. Crost, C. P. Traeger, Optimal climate policy: Uncertainty versus monte carlo, Econ. Lett., 120 (2013), 552–558. https://doi.org/10.1016/j.econlet.2013.05.019 doi: 10.1016/j.econlet.2013.05.019
[36]	F. Yılmaz, H. Ö. Bakan, G. W. Weber, Strong-order conditions of runge-kutta method for stochastic optimal control problems, Appl. Numer. Math., 157 (2020), 470–489. https://doi.org/10.1016/j.apnum.2020.07.002 doi: 10.1016/j.apnum.2020.07.002
[37]	F. Yılmaz, H. Ö. Bakan, G. W. Weber, Weak second-order conditions of runge–kutta method for stochastic optimal control problems, J. Optim. Theory Appl., 202 (2024), 497–517. https://doi.org/10.1007/s10957-023-02324-y doi: 10.1007/s10957-023-02324-y
[38]	R. Knutti, D. Frame, M. Allen, Greenhousegas emission targets for limiting global warming to 2 ℃, Nature, 458 (2009), 1158–1162. https://doi.org/ 10.1038/nature00817
[39]	M. Collins, R. Knutti, Long-term climate change: projections, commitments and irreversibility, University Press, 2013. https://doi.org/10.1017/CBO9781107415324.024
[40]	P. Goodwin, R. Williams, A. Ridgwell, Sensitivity of climate to cumulative carbon emissions due to compensation of ocean heat and carbon uptake, Nat. Geosci., 8 (2014), 29–34. https://doi.org/10.1038/ngeo2304 doi: 10.1038/ngeo2304
[41]	A. H. MacDougall, N. C. Swart, R. Knutti, The uncertainty in the transient climate response to cumulative CO₂ emissions arising from the uncertainty in physical climate parameters, J. Climate, 30 (2017), 813–827. https://doi.org/10.1175/JCLI-D-16-0205.1 doi: 10.1175/JCLI-D-16-0205.1
[42]	D. Ehlert, K. Zickfeld, M. Eby, N. Gillett, The sensitivity of the proportionality between temperature change and cumulative CO₂ emissions to ocean mixing, J. Climate, 30 (2017), 2921–2935. https://doi.org/10.1175/JCLI-D-16-0247.1 doi: 10.1175/JCLI-D-16-0247.1
[43]	C. D. Jones, P. Friedlingstein, Quantifying process-level uncertainty contributions to tcre and carbon budgets for meeting paris agreement climate targets, Environ. Res. Lett., 15 (2020), 74019. https://doi.org/10.1088/1748-9326/ab858a doi: 10.1088/1748-9326/ab858a
[44]	R. Millar, P. Friedlingstein, The utility of the historical record for assessing the transient climate response to cumulative emissions, Philos. Trans. R. Soc. A Math. Phys. Eng. Sci., 376 (2018), 20160449. https://doi.org/10.1098/rsta.2016.0449 doi: 10.1098/rsta.2016.0449
[45]	L. Drouet, V. Bosetti, M. Tavoni, Selection of climate policies under the uncertainties in the fifth assessment report of the ipcc, Nat. Clim. Change, 5 (2015), 937–940. https://doi.org/10.1038/nclimate2721 doi: 10.1038/nclimate2721
[46]	M. Barnett, W. Brock, L. P. Hansen, Pricing uncertainty induced by climate change, Rev. Financ. Stud., 33 (2020), 1024–1066. https://doi.org/10.1093/rfs/hhz144 doi: 10.1093/rfs/hhz144
[47]	R. Bansal, M. Ochoa, D. Kiku, Climate change and growth risks, Working Paper, 2016. https://doi.org/10.3386/w23009
[48]	M. Weitzman, On modeling and interpreting the economics of catastrophic climate change, Rev. Econ. Stat., 91 (2009), 1–19. https://doi.org/10.1162/rest.91.1.1 doi: 10.1162/rest.91.1.1
[49]	W. Nordhaus, Estimates of the social cost of carbon: concepts and results from the dice-2013r model and alternative approaches, J. Assoc. Environ. Resour. Econ., 1 (2014), 273–312. https://doi.org/10.1086/676035 doi: 10.1086/676035
[50]	E. Anderson, L. Hansen, T. Sargent, A quartet of semigroups for model specification, robustness, prices of risk, and model detection, J. Eur. Econ. Assoc., 1 (2003), 68–123. https://doi.org/10.1162/154247603322256774 doi: 10.1162/154247603322256774
[51]	J. Sirignano, K. Spiliopoulos, Dgm: A deep learning algorithm for solving partial differential equations, J. Comput. Phys., 375 (2018), 1339–1364. https://doi.org/10.1016/j.jcp.2018.08.029 doi: 10.1016/j.jcp.2018.08.029
[52]	D. Acemoglu, U. Akcigit, D. Hanley, W. Kerr, Transition to clean technology, J. Polit. Econ., 124 (2016), 52–104. https://doi.org/10.1086/684511 doi: 10.1086/684511
[53]	S. Basu, J. G. Fernald, M. S. Kimball, Are technology improvements contractionary? Am. Econ. Rev., 96 (2006), 1418–1448. https://doi.org/10.1257/aer.96.5.1418 doi: 10.1257/aer.96.5.1418
[54]	M. G. Finn, Variance properties of solow's productivity residual and their cyclical implications, J. Econ. Dyn. Control, 19 (1995), 1249–1281. https://doi.org/10.1016/0165-1889(94)00826-4 doi: 10.1016/0165-1889(94)00826-4
[55]	D. Acemoglu, P. Aghion, L. Bursztyn, D. Hemous, The environment and directed technical change, Am. Econ. Rev., 102 (2012), 131–166. https://doi.org/10.1257/aer.102.1.131 doi: 10.1257/aer.102.1.131
[56]	A. Vissing-Jørgensen, Limited asset market participation and the elasticity of intertemporal substitution, J. Polit. Econ., 110 (2002), 825–853. https://doi.org/10.3386/w8896 doi: 10.3386/w8896

jimo-22-07-124-s001.pdf

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)