Crater counting on the Moon and other bodies is crucial to constrain the dynamical history of the Solar System. This has traditionally been done by visual inspection of images, thus limiting the scope, efficiency, and/or accuracy of retrieval. In this paper we demonstrate the viability of using convolutional neural networks (CNNs) to determine the positions and sizes of craters from Lunar digital elevation maps (DEMs). We recover 92% of craters from the human-generated test set and almost double the total number of crater detections. Of these new craters, 15% are smaller in diameter than the minimum crater size in the ground-truth dataset. Our median fractional longitude, latitude and radius errors are 11% or less, representing good agreement with the human-generated datasets. From a manual inspection of 361 new craters we estimate the false positive rate of new craters to be 11%. Moreover, our Moon-trained CNN performs well when tested on DEM images of Mercury, detecting a large fraction of craters in each map. Our results suggest that deep learning will be a useful tool for rapidly and automatically extracting craters on various Solar System bodies. We make our code and data publicly available at https://github.com/ silburt/DeepMoon.git and https://doi.org/10.5281/zenodo.1133969.

The C-to-O ratio is a crucial determinant of the chemical properties of planets. The recent observation of WASP 12b, a giant planet with a C/O value larger than that estimated for its host star, poses a conundrum for understanding the origin of this elemental ratio in any given planetary system. In this paper, we propose a mechanism for enhancing the value of C/O in the disk through the transport and distribution of volatiles. We construct a model that computes the abundances of major C and O bearing volatiles under the influence of gas drag, sublimation, vapor diffusion, condensation and coagulation in a multi-iceline 1+1D protoplanetary disk. We find a gradual depletion in water and carbon monoxide vapors inside the water's iceline with carbon monoxide depleting slower than water. This effect increases the gaseous C/O and decreases the C/H ratio in this region to values similar to those found in WASP 12b's day side atmosphere. Giant planets whose envelopes were accreted inside the water's iceline should then display C/O values larger than those of their parent stars, making them members of the class of so-called "carbon-rich planets".

ABSTRACT.We review the reservoirs of methane clathrates that may exist in the different bodies of the Solar System. Methane was formed in the interstellar medium prior to having been embedded in the protosolar nebula gas phase. This molecule was subsequently trapped in clathrates that formed from crystalline water ice during the cooling of the disk and incorporated in this form in the building blocks of comets, icy bodies, and giant planets. Methane clathrates may play an important role in the evolution of planetary atmospheres. On Earth, the production of methane in clathrates is essentially biological, and these compounds are mostly found in permafrost regions or in the sediments of continental shelves. On Mars, methane would more likely derive from hydrothermal reactions with olivine-rich material. If they do exist, martian methane clathrates would be stable only at depth in the cryosphere and sporadically release some methane into the atmosphere via mechanisms that remain to be determined. In the case of Titan, most of its methane probably originates from the protosolar nebula, where it would have been trapped in the clathrates agglomerated by the satellite's building blocks.Methane clathrates are still believed to play an important role in the present state of Titan.Their presence is invoked in the satellite's subsurface as a means of replenishing its atmosphere with methane via outgassing episodes. The internal oceans of Enceladus and Europa also provide appropriate thermodynamic conditions that allow formation of methane clathrates. In turn, these clathrates might influence the composition of these liquid reservoirs. Finally, comets and Kuiper Belt Objects might have formed from the agglomeration of clathrates and pure ices in the nebula. The methane observed in comets would then result from the destabilization of clathrate layers in the nuclei concurrent with their approach to perihelion.Thermodynamic equilibrium calculations show that methane-rich clathrate layers may exist on Pluto as well.

The formation mechanisms of the ice giants Uranus and Neptune, and the origin of their elemental and isotopic compositions, have long been debated. The density of solids in the outer protosolar nebula is too low to explain their formation, and spectroscopic observations show that both planets are highly enriched in carbon, very poor in nitrogen, and the ices from which they originally formed might had deuterium-to-hydrogen ratios lower than the predicted cometary value, unexplained properties observed in no other planets. Here we show that all these properties can be explained naturally if Uranus and Neptune both formed at the carbon monoxide iceline. Due to the diffusive redistribution of vapors, this outer region of the protosolar nebula intrinsically has enough surface density to form both planets from carbon-rich solids but nitrogen-depleted gas, in abundances consistent with their observed values. Water rich interiors originating mostly from transformed CO ices reconcile the D/H value of Uranus and Neptune's building blocks with the cometary value. Finally, Our scenario generalizes a well known hypothesis that Jupiter formed on an iceline (water snowline) for the two ice giants, and might be a first step towards generalizing this mechanism for other giant planets.

The requirement that planetary systems be dynamically stable is often used to vet new discoveries or set limits on unconstrained masses or orbital elements. This is typically carried out via computationally expensive N-body simulations. We show that characterizing the complicated and multidimensional stability boundary of tightly packed systems is amenable to machine learning methods. We find that training an XGBoost machine learning algorithm on physically motivated features yields an accurate classifier of stability in packed systems. On the stability timescale investigated (10 7 orbits), it is 3 orders of magnitude faster than direct N-body simulations. Optimized machine learning classifiers for dynamical stability may thus prove useful across the discipline, e.g., to characterize the exoplanet sample discovered by the upcoming Transiting Exoplanet Survey Satellite (TESS). This proof of concept motivates investing computational resources to train algorithms capable of predicting stability over longer timescales and over broader regions of phase space.

In single star systems like our own Solar system, comets dominate the mass budget of bodies that are ejected into interstellar space, since they form further away and are less tightly bound. However 1I/'Oumuamua, the first interstellar object detected, appears asteroidal in its spectra and in its lack of detectable activity. We argue that the galactic budget of interstellar objects like 1I/'Oumuamua should be dominated by planetesimal material ejected during planet formation in circumbinary systems, rather than in single star systems or widely separated binaries. We further show that in circumbinary systems, rocky bodies should be ejected in comparable numbers to icy ones. This suggests that a substantial fraction of additional interstellar objects discovered in the future should display an active coma. We find that the rocky population, of which 1I/'Oumuamua seems to be a member, should be predominantly sourced from A-type and late B-star binaries.

The nature of the icy material accreted by comets during their formation in the outer regions of the protosolar nebula is a major open question in planetary science. Some scenarios of comet formation predict that these bodies agglomerated from crystalline ices condensed in the protosolar nebula. Concurrently, alternative scenarios suggest that comets accreted amorphous ice originating from the interstellar cloud or from the very distant regions of the protosolar nebula. On the basis of existing laboratory and modeling data, we find that the N 2 /CO and Ar/CO ratios measured in the coma of the Jupiter family comet 67P/Churyumov-Gerasimenko by the ROSINA instrument aboard the European Space Agency's Rosetta spacecraft match those predicted for gases trapped in clathrates. If these measurements are representative of the bulk N 2 /CO and Ar/CO ratios in 67P/Churyumov-Gerasimenko, it implies that the ices accreted by the comet formed in the nebula and do not originate from the interstellar medium, supporting the idea that the building blocks of outer solar system bodies have been formed from clathrates and possibly from pure crystalline ices.Moreover, because 67P/Churyumov-Gerasimenko is impoverished in Ar and N 2 , the volatile enrichments observed in Jupiter's atmosphere cannot be explained solely via the accretion of building blocks with similar compositions and require an additional delivery source. A potential source may be the accretion of gas from the nebula that has been progressively enriched in heavy elements due to photoevaporation.

Conditions in the protosolar nebula have left their mark in the composition of cometary volatiles, thought to be some of the most pristine material in the solar system. Cometary compositions represent the end point of processing that began in the parent molecular cloud core and continued through the collapse of that core to form the protosun and the solar nebula, and finally during the evolution of the solar nebula itself as the cometary bodies were accreting. Disentangling the effects of the various epochs on the final composition of a comet is complicated. But comets are not the only source of information about the solar nebula. Protostellar disks around young stars similar to the protosun provide a way of investigating the evolution of disks similar to the solar nebula while they are in the process of evolving to form their own solar systems. In this way we can learn about the physical and chemical conditions under which comets formed, and about the types of dynamical processing that shaped the solar system we see today.This paper summarizes some recent contributions to our understanding of both cometary volatiles and the composition, structure and evolution of protostellar disks.