Bayesian codes are routinely used to fit observed photometries with underlying models of star formation, evolution, and dust attenuation. However, results based on hydrodynamical simulations have exposed biases in these methods at a factor of a few in the derived physical properties. Furthermore, Bayesian fitting is an intrinsically compute-intensive task, often requiring access to expensive hardware for long periods of time. To overcome these shortcomings, we have developed mirkwood: a user-friendly tool comprising of an ensemble of supervised machine learning-based models capable of non-linearly mapping galaxy fluxes to their properties. By stacking multiple models, we marginalize against any individual model’s poor performance in a given region of the parameter space. We demonstrate mirkwood’s superior performance by training it on a combined data set of mock photometry from z=0 and z=2 galaxies from the Simba, Eagle and IllustrisTNG simulations, and comparing the derived results with those obtained from traditional SED fitting techniques. mirkwood is also able to account for uncertainties arising both from missing observations in informative bands and intrinsic noise in observations, and from finite training data and incorrect modeling assumptions. To increase the added value to the observational community, we use Shapley value explanations (SHAP) to fairly evaluate the relative importance of different bands to understand why particular predictions were reached. We envisage mirkwood to be an evolving, open-source framework that will provide highly accurate physical properties from observations of galaxies as compared to traditional SED fitting.