Climate Dynamics

, Volume 21, Issue 3–4, pp 257–272 | Cite as

Probabilistic climate change projections using neural networks

  • R. Knutti
  • T. F. Stocker
  • F. Joos
  • G.-K. Plattner


Anticipated future warming of the climate system increases the need for accurate climate projections. A central problem are the large uncertainties associated with these model projections, and that uncertainty estimates are often based on expert judgment rather than objective quantitative methods. Further, important climate model parameters are still given as poorly constrained ranges that are partly inconsistent with the observed warming during the industrial period. Here we present a neural network based climate model substitute that increases the efficiency of large climate model ensembles by at least an order of magnitude. Using the observed surface warming over the industrial period and estimates of global ocean heat uptake as constraints for the ensemble, this method estimates ranges for climate sensitivity and radiative forcing that are consistent with observations. In particular, negative values for the uncertain indirect aerosol forcing exceeding –1.2 Wm–2 can be excluded with high confidence. A parameterization to account for the uncertainty in the future carbon cycle is introduced, derived separately from a carbon cycle model. This allows us to quantify the effect of the feedback between oceanic and terrestrial carbon uptake and global warming on global temperature projections. Finally, probability density functions for the surface warming until year 2100 for two illustrative emission scenarios are calculated, taking into account uncertainties in the carbon cycle, radiative forcing, climate sensitivity, model parameters and the observed temperature records. We find that warming exceeds the surface warming range projected by IPCC for almost half of the ensemble members. Projection uncertainties are only consistent with IPCC if a model-derived upper limit of about 5 K is assumed for climate sensitivity.


Climate Sensitivity Internal Variability Ensemble Method SRES Scenario Future Warming 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



We thank T. Crowley for providing the volcanic and solar radiative forcing reconstructions and S. Levitus for compiling the time series of ocean heat uptake. We enjoyed discussions with S. Gerber, N. Edwards and J. Flückiger. This work was supported by the Swiss National Foundation.


  1. Allen MR, Gillett NP, Kettleborough JA, Hegerl G, Schnur R, Stott PA, Boer G, Covey C, Delworth TL, Jones GS, Mitchell JFB, Barnett TP (2002) Quantifying anthropogenic influence on recent near-surface temperature change. Surv Geophys (In press)Google Scholar
  2. Allen MR, Stott PA, Mitchell JFB, Schnur R, Delworth TL (2000) Quantifying the uncertainty in forecasts of anthropogenic climate change. Nature 407: 617–620PubMedGoogle Scholar
  3. Andronova N, Schlesinger ME (2001) Objective estimation of the probability distribution for climate sensitivity. J Geophys Res 106: 22,605–22,612Google Scholar
  4. Barnett TR, Pierce DW, Schnur R (2001) Detection of anthropogenic climate changes in the World's oceans. Science 292: 270–274CrossRefPubMedGoogle Scholar
  5. Boucher O, Haywood J (2001) On summing the components of radiative forcing of climate change. Clim Dyn 18: 297–302CrossRefGoogle Scholar
  6. Church JA, Gregory JM (2001) Changes in sea level. Climate change 2001: the scientific basis. In: Houghton JT et al. (eds) Contribution of Working Group I to the Third Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge University Press, Cambridge, UK, pp 639–693Google Scholar
  7. Corti S, Molteni F, Palmer TN (1999) Signature of recent climate change in frequency of natural atmospheric circulation regimes. Nature 398: 799–802Google Scholar
  8. Cox P, Betts R, Jones C, Spall S, Totterdell I (2000) Acceleration of global warming due to carbon-cycle feedbacks in a coupled climate model. Nature 408: 184–187PubMedGoogle Scholar
  9. Crowley TJ (2000) Causes of climate change over the past 1000 years. Science 289: 270–277PubMedGoogle Scholar
  10. Delworth TL, Dixon KW (2000) Implications of the recent trend in the Arctic/North Atlantic Oscillation for the North Atlantic thermohaline circulation. J Clim 13: 3721–3727CrossRefGoogle Scholar
  11. Forest CE, Stone PH, Sokolov AP, Allen MR, Webster MD (2002) Quantifying uncertainties in climate system properties with the use of recent climate observations. Science 295: 113–117CrossRefPubMedGoogle Scholar
  12. Friedlingstein P, Bopp L, Ciais P, Fairhead JLDL, LeTreut H, Monfray P, Orr J (2000) Positive feedback of the carbon cycle on future climate change. Tech Rep 19, Note du Pole de Modelisation, Institute Pierre Simon Laplace, FranceGoogle Scholar
  13. Gent PR (2001) Will the North Atlantic Ocean thermohaline circulation weaken during the 21st century? Geophys Res Lett 28: 1023–1026Google Scholar
  14. Gent PR, McWilliams JC (1990) Isopycnal mixing in ocean circulation models. J Phys Oceanogr 20: 150–155CrossRefGoogle Scholar
  15. Gent PR, Willebrand J, McDougall TJ, McWilliams JC (1995) Parameterizing eddy-induced tracer transports in ocean circulation models. J Phys Oceanogr 25: 463–474CrossRefGoogle Scholar
  16. Gerber S, Joos F, Brügger P, Stocker TF, Mann ME, Sitch S, Scholze M (2003) Constraining temperature variations over the last millennium by comparing simulated and observed atmospheric CO2. Clim Dyn 20: 281–299, doi: 10.1007/s00382-002-0270-8Google Scholar
  17. Gregory JM, Stouffer RJ, Raper SCB, Stott PA, Rayner NA (2002) An observationally based estimate of the climate sensitivity. J Clim 15: 3117–3121CrossRefGoogle Scholar
  18. Hagan MT, Menhaj M (1994) Training feedforward networks with the Marquart algorithm. IEEE Trans Neural Networks 5: 989–993CrossRefGoogle Scholar
  19. Hagan MT, Demuth HB, Beale MH (1996) Neural Network Design. PWS Publishing, Boston, USAGoogle Scholar
  20. Hansen JE, Sato M, Lacis A, Ruedy R, Tegen I, Matthews E (1998) Climate forcings in the Industrial era. Proc US Natl Acad Sci 95: 12,753–12,758Google Scholar
  21. Hegerl GC, Stott PA, Allen MR, Mitchell JFB, Tett SFB, Cubasch U (2000) Optimal detection and attribution of climate change: sensitivity of results to climate model differences. Clim Dyn 16: 737–754CrossRefGoogle Scholar
  22. Hooss G, Voss R, Hasselmann K, Maier-Reimer E, Joos F (2001) A nonlinear impulse response model of the coupled carbon cycle-climate system (NICCS). Clim Dyn 18: 189–202CrossRefGoogle Scholar
  23. IPCC (2001) Climate change 2001: the scientific basis. In: Houghton JT et al. (eds) Contribution of Working Group I to the Third Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge University Press, Cambridge, UK, pp 881Google Scholar
  24. Jones PD, New M, Parker DE, Martin S, Rigor I (1999) Surface air temperature and its changes over the past 150 years. Rev Geophys 37: 173–199CrossRefGoogle Scholar
  25. Joos F, Bruno M (1996) Pulse response functions are cost-efficient tools to model the link between carbon emissions, atmospheric CO2 and global warming. Phys Chem Earth 21: 471–476CrossRefGoogle Scholar
  26. Joos F, Bruno M, Fink R, Stocker TF, Siegenthaler U, Le Quéré C, Sarmiento JL (1996) An efficient and accurate representation of complex oceanic and biospheric models of anthropogenic carbon uptake. Tellus Ser B 48: 397–417CrossRefGoogle Scholar
  27. Joos F, Plattner GK, Stocker TF, Marchal O, Schmittner A (1999) Global warming and marine carbon cycle feedbacks on future atmospheric CO2. Science 284: 464–467Google Scholar
  28. Joos F, Prentice IC, Sitch S, Meyer R, Hooss G, Plattner GK, Gerber S, Hasselmann K (2001) Global warming feedbacks on terrestrial carbon uptake under the IPCC emission scenarios. Global Biogeochem Cyc 15: 891–907Google Scholar
  29. Knutti R, Stocker TF (2000) Influence of the thermohaline circulation on projected sea level rise. J Clim 13: 1997–2001CrossRefGoogle Scholar
  30. Knutti R, Stocker TF (2002) Limited predictability of the future thermohaline circulation close to an instability threshold. J Clim 15: 179–186CrossRefGoogle Scholar
  31. Knutti R, Stocker TF, Wright DG (2000) The effects of subgrid-scale parameterizations in a zonally averaged ocean model. J Phys Oceanogr 30: 2738–2752CrossRefGoogle Scholar
  32. Knutti R, Stocker TF, Joos F, Plattner GK (2002) Constraints on radiative forcing and future climate change from observations and climate model ensembles. Nature 416: 719–723Google Scholar
  33. Latif M, Roeckner E, Mikolajewicz U, Voss R (2000) Tropical stabilization of the thermohaline circulation in a greenhouse warming simulation. J Clim 13: 1809–1813CrossRefGoogle Scholar
  34. Legget J, Pepper WJ, Swart RJ (1992) Climate change 1992. The Supplementary Report to the IPCC Scientific Assessment, Ch Emissions Scenarios for IPCC: an Update. Cambridge University Press, Cambridge, UK, pp 69–95Google Scholar
  35. Levitus S, Antonov JI, Boyer TP, Stephens C (2000) Warming of the World Ocean. Science 287: 2225–2229CrossRefGoogle Scholar
  36. Levitus S, Antonov JI, Wang J, Delworth TL, Dixon KW, Broccoli AJ (2001) Anthropogenic warming of Earth's climate system. Science 292: 267–270PubMedGoogle Scholar
  37. Manabe S, Stouffer RJ (1993) Century-scale effects of increased atmospheric CO2 on the ocean–atmosphere system. Nature 364: 215–218Google Scholar
  38. McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5: 115–133Google Scholar
  39. Meyer R, Joos F, Esser G, Heimann M, Kohlmaier GHG, Sauf W, Voss R, Wittenberg U (1999) The substitution of high-resolution terrestrial biosphere models and carbon sequestration in response to changing CO2 and climate. Global Biogeochem Cyc 13: 785–802Google Scholar
  40. Minsky M, Papert S (1969) Perceptrons: an introduction to computational geometry. MIT Press, USAGoogle Scholar
  41. Myhre G, Highwood EJ, Shine KP, Stordal F (1998) New estimates of radiative forcing due to well mixed greenhouse gases. Geophys Res Lett 25: 2715–2718Google Scholar
  42. Nakićenović et al (2000) Special Report on Emission Scenarios. Intergovernmental Panel on Climate Change, Cambridge University Press, Cambridge, UK, pp 599Google Scholar
  43. Plattner GK, Joos F, Stocker TF, Marchal O (2001) Feedback mechanisms and sensitivities of ocean carbon uptake under global warming. Tellus 53B: 564–592Google Scholar
  44. Rahmstorf S (1999) Shifting seas in the greenhouse? Nature 399: 523–524Google Scholar
  45. Reichert BK, Schnur R, Bengtsson L (2002) Global ocean warming tied to anthropogenic forcing. Geophys Res Lett 29: 690–691CrossRefGoogle Scholar
  46. Rosenblatt R (1962) Principles of neurodynamics. Spartan Books, New York, USAGoogle Scholar
  47. Santer BD, Taylor KE, Wigley TML, Johns TC, Jones PD, Karoly DJ, Mitchell JFB, Oort AH, Penner JE, Ramaswamy V, Schwarzkopf MD, Stouffer RJ, Tett S (1996) A search for human influences on the thermal structure of the atmosphere. Nature 382: 39–46Google Scholar
  48. Sarmiento JL, Le Quéré C (1996) Oceanic carbon dioxide uptake in a model of century-scale global warming. Science 274: 1346–1350CrossRefPubMedGoogle Scholar
  49. Schmittner A, Stocker TF (1999) The stability of the thermohaline circulation in global warming experiments. J Clim 12: 1117–1133CrossRefGoogle Scholar
  50. Schmittner A, Stocker TF (2001) A seasonally forced ew model for paleoclimate studies. J Clim 14: 1055–1068CrossRefGoogle Scholar
  51. Schmittner A, Appenzeller C, Stocker TF (2000) Enhanced Atlantic freshwater export during El Niño. Geophys Res Lett 27: 1163–1166CrossRefGoogle Scholar
  52. Schneider SH (2001) What is 'dangerous' in climate change? Nature 411: 17–19Google Scholar
  53. Shine KP, Derwent RG, Wuebbles DJ, Morcrette JJ (1995) Radiative forcing of climate. In: Houghton JY, Jenkins GJ, Ephraums JJ (eds) Climate change, the IPCC scientific assessment, Cambridge University Press, Cambridge, UKGoogle Scholar
  54. Siegenthaler U, Joos F (1992) Use of a simple model for studying oceanic tracer distributions and the global carbon cycle. Tellus Ser B 44: 186–207CrossRefGoogle Scholar
  55. Sitch S, Smith B, Prentice IC, Arneth A, Bondeau A, Cramer W, Kaplan J, Levis S, Lucht W, Sykes M, Thonicke K, Venevsky S (2002) Evaluation of ecosystem dynamics, plant geography and terrestrial carbon cycling in the LPJ Dynamic Global Vegetation Model. Global Change Biol (submitted)Google Scholar
  56. Stocker TF, Schmittner A (1997) Influence of CO2 emission rates on the stability of the thermohaline circulation. Nature 388: 862–865Google Scholar
  57. Stocker TF, Wright DG (1991) A zonally averaged model for the thermohaline circulation. Part II: interocean exchanges in the Pacific-Atlantic basin system. J Phys Oceanogr 21: 1725–1739CrossRefGoogle Scholar
  58. Stocker TF, Wright DG, Mysak LA (1992) A zonally averaged, coupled ocean–atmosphere model for paleoclimate studies. J Clim 5: 773–797CrossRefGoogle Scholar
  59. Stocker TF, Knutti R, Plattner GK (2001) The future of the thermohaline circulation – a perspective. In: Seidov D, Haupt BJ, Maslin M (eds), The oceans and rapid climate change: past, present, and future, vol. 126 of Geophysical Monograph, American Geophysical Union, Washington D.C., USAGoogle Scholar
  60. Stott PA, Kettleborough JA (2002) Origins and estimates of uncertainty in predictions of twenty-first century temperature rise. Nature 416: 723–726CrossRefPubMedGoogle Scholar
  61. Stott PA, Tett SFB, Jones GS, Allen MR, Mitchell JFB, Jenkins GJ (2000) External control of 20th century temperature by natural and anthropogenic forcing. Science 290: 2133–2137PubMedGoogle Scholar
  62. Stott PA, Tett SFB, Jones GS, Allen MR, Ingram WJ, Mitchell JFB (2001) Attribution of twentieth century temperature change to natural and anthropogenic causes. Clim Dyn 17: 1–21Google Scholar
  63. Stouffer RJ, Hegerl G, Tett S (2000) A comparison of surface air temperature variability in three 1000-yr coupled ocean–atmosphere model integrations. J Clim 13: 513–537CrossRefGoogle Scholar
  64. Tett SFB, Stott PA, Allen MR, Ingram WJ, Mitchell JFB (1999) Causes of twentieth-century temperature change near the Earth's surface. Nature 399: 569–572Google Scholar
  65. Timmermann A, Oberhuber J, Bacher A, Esch M, Latif M, Roeckner E (1999) Increased El Niño frequency in a climate model forced by future greenhouse warming. Nature 398: 694–697Google Scholar
  66. Tziperman E (2000) Proximity of the present-day thermohaline circulation to an instability threshold. J Phys Oceanogr 30: 90–104CrossRefGoogle Scholar
  67. Voss R, Mikolajewicz U (2001) Long-term climate changes due to increased CO2 concentration in the coupled atmosphere–ocean general circulation model ECHAM3/LSG. Clim Dyn 17: 45–60Google Scholar
  68. Wigley TML, Raper SCB (2001) Interpretation of high projections for global-mean warming. Science 293: 451–454CrossRefPubMedGoogle Scholar
  69. Wright DG, Stocker TF (1991) A zonally averaged ocean model for the thermohaline circulation, Part I: model development and flow dynamics. J Phys Oceanogr 21: 1713–1724CrossRefGoogle Scholar
  70. Zwiers FA (2002) The 20-year forecast. Nature 416: 690–691CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag 2003

Authors and Affiliations

  • R. Knutti
    • 1
  • T. F. Stocker
    • 1
  • F. Joos
    • 1
  • G.-K. Plattner
    • 1
  1. 1.Climate and Environmental Physics, Physics Institute University of BernBern

Personalised recommendations