Machine learning (ML) is now used in many areas of astrophysics, from detecting exoplanets in Kepler transit signals to removing telescope systematics. Recent work demonstrated the potential of using ML algorithms for atmospheric retrieval by implementing a random forest (RF) to perform retrievals in seconds that are consistent with the traditional, computationally expensive nested-sampling retrieval method. We expand upon their approach by presenting a new ML model, plan-net, based on an ensemble of Bayesian neural networks (BNNs) that yields more accurate inferences than the RF for the same data set of synthetic transmission spectra. We demonstrate that an ensemble provides greater accuracy and more robust uncertainties than a single model. In addition to being the first to use BNNs for atmospheric retrieval, we also introduce a new loss function for BNNs that learns correlations between the model outputs. Importantly, we show that designing ML models to explicitly incorporate domain-specific knowledge both improves performance and provides additional insight by inferring the covariance of the retrieved atmospheric parameters. We apply plan-net to the Hubble Space Telescope Wide Field Camera 3 transmission spectrum for WASP-12b and retrieve an isothermal temperature and water abundance consistent with the literature. We highlight that our method is flexible and can be expanded to higher-resolution spectra and a larger number of atmospheric parameters.

Anthropogenic climate change has the potential to alter many facets of Earth's freshwater resources, especially lacustrine ecosystems. The effects of anthropogenic changes in Lake Superior, which is Earth's largest freshwater lake by area, are not well documented (spatially or temporally) and predicted future states in response to climate change vary. Here we show that Lake Superior experienced a slow, steady increase in production throughout the Holocene using (paleo)productivity proxies in lacustrine sediments to reconstruct past changes in primary production. Furthermore, data from the last century indicate a rapid increase in primary production, which we attribute to increasing surface water temperatures and longer seasonal stratification related to longer ice-free periods in Lake Superior due to anthropogenic climate warming. These observations demonstrate that anthropogenic effects have become a prominent influence on one of Earth's largest, most pristine lacustrine ecosystems.

Atmospheric retrieval determines the properties of an atmosphere based on its measured spectrum. The low signal-to-noise ratios of exoplanet observations require a Bayesian approach to determine posterior probability distributions of each model parameter, given observed spectra. This inference is computationally expensive, as it requires many executions of a costly radiative transfer (RT) simulation for each set of sampled model parameters. Machine learning (ML) has recently been shown to provide a significant reduction in runtime for retrievals, mainly by training inverse ML models that predict parameter distributions, given observed spectra, albeit with reduced posterior accuracy. Here we present a novel approach to retrieval by training a forward ML surrogate model that predicts spectra given model parameters, providing a fast approximate RT simulation that can be used in a conventional Bayesian retrieval framework without significant loss of accuracy. We demonstrate our method on the emission spectrum of HD 189733 b and find good agreement with a traditional retrieval from the Bayesian Atmospheric Radiative Transfer (BART) code (Bhattacharyya coefficients of 0.9843–0.9972, with a mean of 0.9925, between 1D marginalized posteriors). This accuracy comes while still offering significant speed enhancements over traditional RT, albeit not as much as ML methods with lower posterior accuracy. Our method is ∼9× faster per parallel chain than BART when run on an AMD EPYC 7402P central processing unit (CPU). Neural-network computation using an NVIDIA Titan Xp graphics processing unit is 90×–180× faster per chain than BART on that CPU.

No abstract