Extended Data Fig. 7: CrIS cloud screening and ANN performance.

a, Function used for cloud screening CrIS L1B data before ΔT_b calculation. The black line shows the modelled clear-sky difference between the 900 cm⁻¹ brightness temperature and surface skin temperature, as a function of water vapour column density (calculated using LBLRTM^80,81). The solid red line is the linear approximation used here, and the dashed red line represents a less stringent threshold used to test the sensitivity of the results to our cloud screening approach. b, c, Sensitivity of the CrIS brightness temperature differences (b) and isoprene columns (c) to cloud screening. Data shown represent the median relative differences between the base-case results (derived using the solid red line in a) and those derived using the less stringent cloud screening threshold (dashed red line in a). d, e, Scatterplots of the predicted versus true isoprene columns for the six-predictor ANN (d) and an ANN in which ΔT_b is withheld as a predictor variable (e). Red dots show the mean of the ten ANN predictions, and blue error bars show the standard deviation across the predictions. f, The relative uncertainty (based on the difference between the mean ANN predicted value and the true value) for the six-predictor ANN, binned as a function of thermal contrast and isoprene column density.