Twentieth century warming of the tropical Atlantic captured by Sr‐U paleothermometry

Abstract

Coral skeletons are valuable archives of past ocean conditions. However, interpretation of coral paleotemperature records is confounded by uncertainties associated with single‐element ratio thermometers, including Sr/Ca. A new approach, Sr‐U, uses U/Ca to constrain the influence of Rayleigh fractionation on Sr/Ca. Here we build on the initial Pacific Porites Sr‐U calibration to include multiple Atlantic and Pacific coral genera from multiple coral reef locations spanning a temperature range of 23.15–30.12°C. Accounting for the wintertime growth cessation of one Bermuda coral, we show that Sr‐U is strongly correlated with the average water temperature at each location (r2 = 0.91, P < 0.001, n = 19). We applied the multispecies spatial calibration between Sr‐U and temperature to reconstruct a 96 year long temperature record at Mona Island, Puerto Rico, using a coral not included in the calibration. Average Sr‐U derived temperature for the period 1900–1996 is within 0.12°C of the average instrumental temperature at this site and captures the twentieth century warming trend of 0.06°C per decade. Sr‐U also captures the timing of multiyear variability but with higher amplitude than implied by the instrumental data. Mean Sr‐U temperatures and patterns of multiyear variability were replicated in a second coral in the same grid box. Conversely, Sr/Ca records from the same two corals were inconsistent with each other and failed to capture absolute sea temperatures, timing of multiyear variability, or the twentieth century warming trend. Our results suggest that coral Sr‐U paleothermometry is a promising new tool for reconstruction of past ocean temperatures.

Calibration of Sr/Ca, Li/Mg and Sr‐U Paleothermometry in Branching and Foliose Corals

“…Our work supports previous studies that have shown that Sr‐U may be a useful alternative to reconstructing mean annual temperatures given that it uses Sr/Ca to isolate the effects of temperature by separating them from the effects of coral biomineralization using U/Ca (Alpert et al, ; DeCarlo et al, ). The utility of Sr‐U at seasonal timescales has not previously been tested, but our study demonstrates that its performance does not improve upon Sr/Ca on these short timescales.…”

“…The multispecies relationship for Sr‐U and temperature that was fitted to the seasonally resolved data gave the relationship: Sr‐U = −0.036T + 8.95 with 63% of the variation explained by temperature ( r 2 = 0.63; Figure c and supporting information Table S6). The model selection of the new calibration for Sr‐U combining the means of multiple species data from this study with the literature (Alpert et al, ; DeCarlo et al, ) was based on AIC values and variance explained by the model. The AIC and r 2 values were −170.09 and 0.95 for the polynomial (quadratic) model versus −129.01 and 0.89 for the linear model.…”

“…Temperature calibrations for this study combined with the literature for (a) Li/Mg (see Fowell et al, ; Hathorne, Felis, et al, ; Montagna et al, ), (b) Sr/Ca (see supporting information Table S1 for regression equations; note that the literature compilation encompasses various species and timescales and originates from different laboratories), and (c) Sr‐U (D16 and A17 refer to data from DeCarlo et al, and Alpert et al, , respectively) for corals at seawater temperatures between 15 and 30 °C. Also shown are the abiogenic relationships for Li/Mg (for a calcifying fluid [CO 3 2− ] of 1,000 μmol/kg) and Sr/Ca.…”

“…Sr‐U showed a linear relationship with temperature across relatively narrower temperature ranges of ~6 °C in the first two Sr‐U studies (Alpert et al, ; DeCarlo et al, ). However, when combining the results from these two previous studies with our new results to investigate the multispecies relationship between Sr‐U and temperature across a wider temperature range of ~14 °C, the relationship no longer appears linear, which may be due to a change in sensitivity (inflection point) at temperatures below ~25 °C, or potentially the minimal overlap between the data sets for temperatures between 24 and 26 °C (Figure c).…”

“…Similar to Li/Mg, the Sr‐U paleothermometer works by isolating the temperature component on the basis that Sr/Ca is sensitive to both temperature and Rayleigh fractionation, while U/Ca is sensitive only to Rayleigh fractionation and [CO 3 2‐ ] cf but not temperature (DeCarlo et al, , ). For instance, Alpert et al () demonstrated that Sr‐U greatly improved the accuracy of a twentieth century temperature reconstruction relative to using Sr/Ca alone. However, the precision of this new thermometer to date has only been applied at annual resolution and not yet been tested for a range of different Indo‐Pacific coral genera, timescales (i.e., seasonal), and temperatures below 23 °C.…”