- Bishop Hill blog

One of the posts I've been pleased with in recent months was the one on Climate sensitivity and the Stern report. This was based on the premise that economic assessments of the cost of carbon ought to be based on the existing empirical measurements of climate sensitivity rather than the hypothetical estimates from climate models.

I reviewed the climate sensitivity estimates of the Fourth Assessment Report and noted that only Forster and Gregory 2006 was free of the influence of models. I then observed that once one had replaced the IPCC's fiddled figure for the Forster and Gregory estimate with the value those authors had actually calculated one could see that the range of estimates used in the the PAGE model (the one used by Stern) did not even include the range of Forster and Gregory.

A bit of a shocker, I'm sure you'll agree.

At the end of the comment thread, however, there was an interesting wrinkle, which leads to another line of inquiry. It started when reader Lance Wallace chipped in with this:

Reading the Forster Gregory 2006 paper as Chris Hope suggested, I noted that they had said it would be good to use more of the scanning radiometer data. Since they used only 5 years worth (ending in 1996) I sent Forster an email this morning asking if they were planning on extending their coverage. Forster responded (in 8 minutes flat!) including a reference to a later paper (Murphy 2009) using another 9 years of data. In the email, however, Forster said they were moving away from considering lambda a good estimate of climate sensitivity. As I read the paper, they are thinking that the value of lambda based on short-term measurements is different from the long-term equilibrium value. This results in a rather weak upper limit of about 10 C per doubling of CO2. They also mention other work putting a more stringent lower limit near 2 C per doubling. They state "We adopt lambda = 1.25 ± 0.5 W/m2/K as an estimate for the response of net radiation to temperature variations between the [sic] 1950 and 2004." Later on, however, they state a range of 0.04 to 1.25 W which "does not exclude the inverse climate sensitivity of 0.37 W/m2/K for a 10C warming for doubled CO2." So if their new range is something like 2-10 C per doubling, they are now, as they state, generally consistent with the IPCC AR4.

An observationally based energy balance for the Earth since 1950
D. M. Murphy, S. Solomon, R. W. Portmann,1K. H. Rosenlof, P. M. Forster,
and T. Wong JOURNAL OF GEOPHYSICAL RESEARCH, VOL. 114, D17107, doi:10.1029/2009JD012105, 2009

Which is pretty interesting - suddenly we go from a low and well-constrained estimate of climate sensitivity of 1-4 degrees to a much, much higher and much less certain one of 2-10 degrees.

It's even more interesting when one notes Nic Lewis's subsequent comment:

I don't trust the 2009 Murphy paper that used a similar method and arrived at higher sensitivity - it gave completely different results from Forster & Gregory 2006 when apparently using almost the same data, with no explanation for the difference despite Forster being a co-author. A poor show IMO, as a result of which I have little confidence in the results of Murphy 2009 generally.

F&G 2006 using ERBE WFOV annual data for 1985-1996 excluding 1993 and obtained Y_net of 2.5 W/m^2/K with HadCRU temperature data. F&G 2006 excluded 1997 data since the GISS and HadCRU global temperature records for 1997 were very different, and excluded 1993 and 1998+ due to gaps in the ERBE data. I have been able to replicate, approximately, the F&G 2006 results using information in that paper.

Murphy 2009 using ERBE WFOV annual data for 1985-1998 excluding 1991-1993, with 1998 a created composite estimate, and obtained Y_net of 0.0 W/m^2/K with HadCRU temperature data.

Murphy 2009 restricted the surface temperature data to 60S-60N on the grounds that the ERBE WFOV sensor only covered that latitude range, but according to NASA the 126 degrees field of view of the WFOV sensor has a view of the entire earth disk at satellite altitude, so that looks dubious.* But the biggest factor may be the omission of 1991 and 1992 data, a key period for the regression due to the natural experiment represented by the eruption of Mount Pinatubo.

Nor does Murphy et al have an adequately detailed method description to replicate the study, and the auxiliary materials referred to in the paper do not appear to exist on the AGU's server.

I wouldn't read anything much into the non-experimentally derived comments in Murphy 2009 that you refer to, such as their new range being generally consistent with IPCC AR4 WG1. I note that Murphy works in the same department as Susan Solomon, overall lead author for AR4 WG1, who is also the second author of the paper. So there may have been an agenda behind the paper.

BTW, MIT professor Dick Lindzen argues that the F&G 2006 (and Murphy 2009) method is likely to overestimate climate sensitivity S due to an inability to distinguish between cloud changes acting as forcings from those constituting feedbacks. F&G also referred to this issue in their paper. Lindzen & Choi's papers based on similar methods argue for S < 1, but as they are based only on tropical data it is a bit difficult to interpret the results.

The lack of materials (presumably data and code) to enable replication is indeed disappointing. I wonder if I might prevail on Prof Forster (who follows me on Twitter) to have them made available, and also to explain to Nic Lewis why the results of the two papers are so different.

Since we are in prevailing mode, could commenters please be nice.

*Nic has subsequently noted that he was wrong here.