Quantitative reconstruction of past salinity variations in African lakes: assessment of chironomid-based inference models (Insecta: Diptera) in space and time

Faunal records of 20 common midge species (Diptera: Chironomidae) in 32 African surface waters with salinities ranging from 20 to 41 000 µS·cm –1 were used to develop inference models for quantitative reconstruction of past salinity variations from larval chironomid fossils preserved in lake sediments. Weighted-averaging regression and calibration models using presence–absence data (P/A) and presence–absence data with tolerance down-weighting (P/A tol ) produced bootstrapped coefficients of determination (r 2 ) of 0.78 and 0.81, respectively, and root mean squared errors (RMSE) of prediction of 0.42 and 0.39 log conductivity units. Historical conductivity data from African lakes are scarce. Therefore, model performance was tested in time by comparing chironomid-inferred conductivity estimates with the corresponding diatom-inferred estimates in sediment records of two fluctuating lakes in the Rift Valley of Kenya. A hybrid procedure in which presence–absence calibration models were applied to abundance-weighted fossil data yielded significantly higher correlation between chironomid- and diatom-inferred time series (Lake Oloidien AD 1880–1991, r 2  = 0.76–0.78; Crescent Island Crater AD 900–1993, r 2  = 0.56–0.61) than by applying the same models to presence–absence fossil data (r 2  = 0.47–0.56 and 0.26–0.42, respectively). Overall, model performance confirms that Chironomidae are valuable bioindicators for natural and man-made changes in the water balance of African lakes.