ELVIS: Local Volume Simulations

• ELVIS is a high-resolution dissipationless simulation suite modeling Local Group halos in paired (MW–M31-like) and isolated configurations.
• The controlled design compares subhalo abundance, kinematics, and environmental impacts over volumes spanning 2–5 Mpc with fine resolution.
• It refines galaxy–halo mappings to predict the census of dwarf galaxies and HI-rich systems, informing observational searches in the Local Volume.

to=arxiv_search.search 大发彩票快三 string_query="ELVIS Exploring the Local Volume in Simulations (Garrison-Kimmel et al., 2013)" max_results=5 【อ่านข้อความเต็มjson {"results":[{"arxiv_id":"(Garrison-Kimmel et al., 2013)","title":"ELVIS: Exploring the Local Volume in Simulations","authors":["Michael Boylan-Kolchin","James S. Bullock","Shea Garrison-Kimmel","Evan N. Kirby","Andrey V. Kravtsov"],"abstract":"We introduce a set of high-resolution dissipationless simulations that model the Local Group (LG) in a cosmological context: Exploring the Local Volume in Simulations (ELVIS). The suite contains 48 Galaxy-size halos, each within high-resolution volumes that span 2-5 Mpc in size, and each resolving thousands of systems with masses below the atomic cooling limit. Half of the ELVIS galaxy halos are in paired configurations similar to the Milky Way (MW) and M31; the other half are isolated, mass-matched analogs. We find no difference in the abundance or kinematics of substructure within the virial radii of isolated versus paired hosts. On Mpc scales, however, LG-like pairs average almost twice as many companions and the velocity field is kinematically hotter and more complex. We present a refined abundance matching relation between stellar mass and halo mass that reproduces the observed satellite stellar mass functions of the MW and M31 down to the regime where incompleteness is an issue, Mstar~5x10^5 Msun. Within a larger region spanning approximately 3 Mpc, the same relation predicts that there should be ~1000 galaxies with Mstar>10^3 Msun awaiting discovery. We show that up to 50% of halos within 1 Mpc of the MW or M31 could be systems that have previously been within the virial radius of either giant. By associating never-accreted halos with gas-rich dwarfs, we show that there are plausibly 50 undiscovered dwarf galaxies with HI masses > 10^5 Msun within the Local Volume. The radial velocity distribution of these predicted gas-rich dwarfs can be used to inform follow-up searches based on ultra-compact high-velocity clouds found in the ALFALFA survey.","categories":["astro-ph.CO","astro-ph.GA"],"published":"2013-10-24","pdf_url":"http://arxiv.org/pdf/([1310.6746](/papers/1310.6746))v1","abs_url":"https://arxiv.org/abs/([1310.6746](/papers/1310.6746))v1"}]} to=arxiv_search.search 买天天中彩票 string_query="ELVIS dwarf mergers (Deason et al., 2014) Phat ELVIS (Kelley et al., 2018) low-mass satellite quenching ELVIS (Fillingham et al., 2015)" max_results=10 【อ่านข้อความเต็มjson {"results":[{"arxiv_id":"(Kelley et al., 2018)","title":"Phat ELVIS: The inevitable effect of the Milky Way's disk on its dark matter subhaloes","authors":["Andrew B. Kelley","Manodeep Sinha","Michael Boylan-Kolchin","James S. Bullock","Kristine Spekkens","Shea Garrison-Kimmel"],"abstract":"We introduce an extension of the ELVIS project to account for the effects of the Milky Way galaxy on its subhalo population. Our simulation suite, Phat ELVIS, consists of twelve high-resolution cosmological dark matter-only (DMO) zoom simulations of Milky Way-size LambdaCDM haloes (Mv = 0.7-2 × 10^12 Msun) along with twelve re-runs with embedded galaxy potentials grown to match the observed Milky Way disk and bulge today. The central galaxy potential destroys subhalos on orbits with small pericenters in every halo, regardless of the ratio of galaxy mass to halo mass. This has several important implications. 1) Most of the Disk runs have no subhaloes larger than Vmax = 4.5 km s−1 within 20 kpc and a significant lack of substructure going back ∼ 8 Gyr, suggesting that local stream-heating signals from dark substructure will be rare. 2) The pericenter distributions of Milky Way satellites derived from Gaia data are remarkably similar to the pericenter distributions of subhaloes in the Disk runs, while the DMO runs drastically over-predict galaxies with pericenters smaller than 20 kpc. 3) The enhanced destruction produces a tension opposite to that of the classic `missing satellites' problem: in order to account for ultra-faint galaxies known within 30 kpc of the Galaxy, we must populate haloes with Vpeak ≃ 7 km s−1 (M ≃ 3 × 10^7 Msun at infall), well below the atomic cooling limit of Vpeak ≃ 16 km s−1 (M ≃ 5 × 10^8 Msun at infall). 4) If such tiny haloes do host ultra-faint dwarfs, this implies the existence of ∼ 1000 satellite galaxies within 300 kpc of the Milky Way.","categories":["astro-ph.GA","astro-ph.CO"],"published":"2018-11-29","pdf_url":"http://arxiv.org/pdf/([1811.12413](/papers/1811.12413))v1","abs_url":"https://arxiv.org/abs/([1811.12413](/papers/1811.12413))v1"},{"arxiv_id":"([1406.3344](/papers/1406.3344))","title":"Satellite Dwarf Galaxies in a Hierarchical Universe: The Prevalence of Dwarf-Dwarf Major Mergers","authors":["Devin S. N. Deason","Michael Wetzel","James S. Bullock","Louis E. Strigari","Markus Hausammann","Shea Garrison-Kimmel"],"abstract":"Mergers are a common phenomenon in hierarchical structure formation, especially for massive galaxies and clusters, but their importance for dwarf galaxies in the Local Group remains poorly understood. We investigate the frequency of major mergers between dwarf galaxies in the Local Group using the ELVIS suite of cosmological zoom-in dissipationless simulations of Milky Way- and M31-like host halos. We find that ~10% of satellite dwarf galaxies with M_star > 10^6 M_sun that are within the host virial radius experienced a major merger of stellar mass ratio closer than 0.1 since z = 1, with a lower fraction for lower mass dwarf galaxies. Recent merger remnants are biased towards larger radial distance and more recent virial infall times, because most recent mergers occurred shortly before crossing within the virial radius of the host halo. Satellite-satellite mergers also occur within the host halo after virial infall, catalyzed by the large fraction of dwarf galaxies that fell in as part of a group. The merger fraction doubles for dwarf galaxies outside of the host virial radius, so the most distant dwarf galaxies in the Local Group are the most likely to have experienced a recent major merger. We discuss the implications of these results on observable dwarf merger remnants, their star formation histories, the gas content of mergers, and massive black holes in dwarf galaxies.","categories":["astro-ph.GA"],"published":"2014-06-12","pdf_url":"http://arxiv.org/pdf/([1406.3344](/papers/1406.3344))v1","abs_url":"https://arxiv.org/abs/([1406.3344](/papers/1406.3344))v1"},{"arxiv_id":"([1503.06803](/papers/1503.06803))","title":"Taking Care of Business in a Flash: Constraining the Timescale for Low-Mass Satellite Quenching with ELVIS","authors":["Marla Geha","Michael Boylan-Kolchin","James S. Bullock","Manodeep Sinha","Evan N. Kirby","S. R. Weisz"],"abstract":"The vast majority of dwarf satellites orbiting the Milky Way and M31 are quenched, while comparable galaxies in the field are gas-rich and star-forming. Assuming that this dichotomy is driven by environmental quenching, we use the ELVIS suite of N-body simulations to constrain the characteristic timescale upon which satellites must quench following infall into the virial volumes of their hosts. The high satellite quenched fraction observed in the Local Group demands an extremely short quenching timescale (~2 Gyr) for dwarf satellites in the mass range Mstar ~ 10^6-10^8 Msun. This quenching timescale is significantly shorter than that required to explain the quenched fraction of more massive satellites (~8 Gyr), both in the Local Group and in more massive host halos, suggesting a dramatic change in the dominant satellite quenching mechanism at Mstar < 10^8 Msun. Combining our work with the results of complementary analyses in the literature, we conclude that the suppression of star formation in massive satellites (Mstar ~ 10^8-10^11 Msun) is broadly consistent with being driven by starvation, such that the satellite quenching timescale corresponds to the cold gas depletion time. Below a critical stellar mass scale of ~10^8 Msun, however, the required quenching times are much shorter than the expected cold gas depletion times. Instead, quenching must act on a timescale comparable to the dynamical time of the host halo. We posit that ram-pressure stripping can naturally explain this behavior, with the critical mass (of Mstar ~10^8 Msun) corresponding to halos with gravitational restoring forces that are too weak to overcome the drag force encountered when moving through an extended, hot circumgalactic medium.","categories":["astro-ph.GA"],"published":"2015-03-23","pdf_url":"http://arxiv.org/pdf/([1503.06803](/papers/1503.06803))v1","abs_url":"https://arxiv.org/abs/([1503.06803](/papers/1503.06803))v1"}]} ELVIS, “Exploring the Local Volume in Simulations,” is a suite of high-resolution dissipationless cosmological zoom simulations constructed to model the Local Group in a cosmological context. The suite contains 48 Galaxy-size halos, each within high-resolution volumes that span 2–5 Mpc in size, with half of the halos arranged in Milky Way–M31-like paired configurations and the other half as isolated, mass-matched analogs. Its central purpose is to isolate which properties of Local Group structure depend on the paired environment and to connect the resolved halo population to the observed and predicted dwarf-galaxy content of the Local Volume (Garrison-Kimmel et al., 2013).

1. Scope and host-halo construction

ELVIS was designed around a controlled comparison between paired and isolated galaxy-size halos. The paired sample consists of 12 Local Group analog pairs, or 24 hosts, while the control sample consists of 24 isolated halos matched in mass to the paired hosts. This paired-versus-isolated design is the defining methodological feature of the suite, because it permits direct tests of whether the Milky Way’s non-isolated environment materially alters subhalo abundance, kinematics, and Local Volume demographics.

The paired systems were selected to resemble the Milky Way and M31. Each host satisfies

$$10^{12} \leq M_{\mathrm v} \leq 3\times 10^{12}\,M_\odot,$$

with pair total mass

$$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$

separation

$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$

and radial velocity

$V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$

The selection also imposed environmental isolation: no halos with $M_{\mathrm v} \geq M_{\mathrm{v,1}}$ within 2.8 Mpc of either host center, and no halos with $M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$ within 7 Mpc of either host. The isolated control halos were required to be mass-matched to the pair members and to have no halo more massive than $M_{\rm v}/2$ within 2.8 Mpc.

The suite is therefore not merely a collection of Milky Way analogs. It is a Local Group experiment in which the paired geometry, large uncontaminated zoom region, and matched isolated controls are all part of the scientific design.

2. Numerical realization and resolved halo population

ELVIS adopts a WMAP-7 $\Lambda$CDM cosmology,

$$\sigma_8 = 0.801,\qquad \Omega_m = 0.266,\qquad \Omega_\Lambda = 0.734,\qquad n_s = 0.963,\qquad h = 0.71,$$

with most zooms initialized at $z=125$. Virial quantities use the Bryan & Norman definition, with virial overdensity $$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$0 relative to the critical density at $$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$1.

The parent simulations used for target selection had side length 70.4 Mpc, particle mass

$$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$2

and force softening 1.4 kpc comoving. The production zooms were generated with MUSIC and run with GADGET-3 and GADGET-2. Their high-resolution regions have particle mass

$$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$3

and Plummer-equivalent force softening

$$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$4

physical after $$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$5. Three isolated halos were also resimulated at higher resolution with

$$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$6

Haloes and subhaloes were identified with Rockstar, and merger trees were built with Consistent-Trees. ELVIS makes systematic use of historical halo quantities, especially $$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$7, $$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$8, and $$2\times 10^{12} \leq M_{\mathrm{v,1}} + M_{\mathrm{v,2}} \leq 5\times 10^{12}\,M_\odot,$$9, because present-day subhalo masses can be strongly reduced by stripping. The fiducial suite is complete down to

$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$0

A concise summary of the numerical design is useful.

Component	Value
Total hosts	48
Paired hosts	24 hosts in 12 pairs
Isolated controls	24
High-resolution volume size	2–5 Mpc
Fiducial particle mass	$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$1
Fiducial force softening	$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$2 pc
HiRes particle mass	$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$3
HiRes force softening	$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$4 pc

Because the simulations are dissipationless, ELVIS directly predicts only the dark-matter halo population. Any statement about stellar masses, gas masses, or observability is therefore a post-processing inference, typically through abundance matching or empirical gas-mass assignments.

3. Internal substructure and the effect of the paired Local Group environment

A principal ELVIS result is negative in an important way: within the virial radii of Milky Way-mass halos, paired and isolated hosts are statistically indistinguishable in the abundance and kinematics of substructure. The suite finds no meaningful difference in subhalo abundance within $0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$5, in the $0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$6 function, or in basic host concentration and formation-time distributions between paired and isolated hosts. This implies that many earlier isolated-host calculations remain applicable for questions restricted to the Milky Way or M31 virial regions.

Within $0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$7, the cumulative subhalo $0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$8 function is fit by

$0.6 \leq \Delta R \leq 1\,\mathrm{Mpc},$9

while the present-day bound-mass function is

$V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$0

Appendix results further give the cumulative circular-velocity function

$V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$1

On Mpc scales, however, the paired Local Group environment is demonstrably distinct. In the Local Field, defined as $V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$2 from a host while excluding the inner 300 kpc of the other giant, paired hosts have substantially more companions than isolated hosts. The Local Field cumulative $V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$3 function is

$V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$4

with $V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$5 for isolated hosts and $V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$6 for paired hosts. Even after excluding two somewhat atypical pairs with a third large nearby companion, the paired normalization remains $V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$7. This indicates that LG-like pairs have a significantly richer halo population beyond the virial radius.

The velocity field is likewise altered. At distances of $V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$8-$V_{\mathrm{rad}} \leq 0\ {\rm km\,s^{-1}}.$9 Mpc, paired systems show a broader tangential-velocity distribution and an excess of positive radial velocities relative to isolated hosts. The Local Group is therefore not only denser on Mpc scales but also dynamically hotter and more complex.

4. Galaxy–halo mapping and the predicted Local Volume dwarf census

To convert the resolved halo population into predicted galaxy populations, ELVIS introduces a refined low-mass abundance-matching relation. The original Behroozi et al. relation was found to overpredict the number of low-mass satellites, so the suite adopts a modified low-mass scaling that reproduces the observed Milky Way and M31 satellite stellar-mass functions down to the regime where incompleteness becomes important,

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$0

For

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$1

the adopted relation is

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$2

This is applied to $M_{\mathrm v} \geq M_{\mathrm{v,1}}$3, not present-day bound mass, because subhalos can be heavily stripped after infall.

Under this mapping, ELVIS predicts a large undiscovered dwarf population. Within 300 kpc of the Milky Way or M31, the suite predicts roughly $M_{\mathrm v} \geq M_{\mathrm{v,1}}$4-$M_{\mathrm v} \geq M_{\mathrm{v,1}}$5 galaxies with

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$6

Within the pair-defined Local Volume, the same relation predicts approximately

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$7

galaxies with

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$8

This prediction is the basis for the conclusion that the Local Volume should still contain a substantial undiscovered low-luminosity galaxy population (Garrison-Kimmel et al., 2013).

ELVIS also extends the inference to neutral gas. The adopted empirical relation is

$M_{\mathrm v} \geq M_{\mathrm{v,1}}$9

Combined with the environmental criterion that never-accreted halos may remain gas-rich, this yields a prediction of approximately 50 undiscovered dwarf galaxies with

$M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$0

within the Local Volume. The model further suggests roughly 300 systems with

$M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$1

This galaxy–halo mapping is an extrapolation, and ELVIS is explicit about that. The underlying simulations are dissipationless, and the gas assignment has no intrinsic scatter in the main analysis. Even so, the framework provides a quantitatively coherent Local Group census model anchored to the resolved dark halo population.

5. Backsplash systems, environmental processing, and observational implications

One of the most consequential ELVIS findings is the large population of halos that presently lie outside the virial radius but were previously inside it. These are backsplash systems, and they matter because they may have been environmentally processed despite their current field-like positions.

The differential backsplash fraction reaches about 70% at $M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$2-$M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$3 and can reach 80% in some realizations. Cumulatively, within the Local Volume around paired hosts, the fraction of halos that have previously passed through the virial radius ranges from 30% to 52%. This is the basis for the statement that up to 50% of halos within 1 Mpc of the Milky Way or M31 may have previously been inside the virial radius of one of the giants (Garrison-Kimmel et al., 2013).

Backsplash halos are not only numerous; they are kinematically distinctive. In the $M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$4-$M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$5 kpc shell they are preferentially more outflowing in radial velocity and occupy lower tangential velocities than never-accreted halos. This suggests that some gas-poor dwarfs beyond the nominal virial radius, such as Cetus and Tucana, are natural backsplash candidates.

These results directly inform HI-selected searches. ELVIS argues that ultra-compact high-velocity clouds from ALFALFA cannot all be nearby minihalos. The radial-velocity distribution is especially restrictive: candidates with

$M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$6

are highly unlikely to correspond to low-mass halos within $M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$7 Mpc of the Milky Way, while follow-up should preferentially target systems with

$M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$8

The suite further concludes that it is highly unlikely that more than $M_{\mathrm v} \geq 7\times 10^{13}\,M_\odot$9 of the ALFALFA UCHVC candidates are true minihalos. In this respect, ELVIS serves not only as a cosmological simulation suite but also as an observational prior for Local Volume dwarf-galaxy surveys.

6. Legacy, follow-up studies, and baryonic reinterpretation

ELVIS rapidly became a standard numerical platform for Local Group dwarf-galaxy studies. One important application was the frequency of dwarf–dwarf mergers. Using the ELVIS suite, later work found that about 10% of present-day satellite dwarf galaxies with $M_{\rm v}/2$0 and located within the host virial radius experienced a major merger since $M_{\rm v}/2$1, with the merger fraction roughly doubling for dwarfs outside the virial radius (Deason et al., 2014). This extended ELVIS from static census work to environmentally structured assembly histories.

A second application concerned environmental quenching. By combining observed Local Group quenched fractions with ELVIS infall-time distributions, later analysis inferred that dwarf satellites with $M_{\rm v}/2$2 must quench within roughly $M_{\rm v}/2$3-$M_{\rm v}/2$4 Gyr of infall, much more rapidly than more massive satellites (Fillingham et al., 2015). In that use case, ELVIS functioned as an infall-history prior rather than purely as a subhalo catalog.

The most important revision of the original framework came from the recognition that ELVIS is dissipationless. “Phat ELVIS” was introduced as an extension in which ELVIS-style Milky Way-mass zooms were re-run with an embedded Milky Way disk+bulge potential. That work showed that a central galaxy destroys subhalos on small-pericenter orbits, with the strongest depletion for

$M_{\rm v}/2$5

and that most Disk runs contain no surviving subhaloes larger than

$M_{\rm v}/2$6

within 20 kpc (Kelley et al., 2018). A plausible implication is that original ELVIS predictions are robustest for questions dominated by outer-halo and Local Volume structure, whereas inner-halo substructure requires explicit baryonic corrections.

Taken together, these later studies define the legacy of ELVIS. The original suite established a controlled Local Group baseline: paired and isolated hosts are similar inside their virial radii, but the paired environment strongly reshapes Local Volume demographics, kinematics, and environmental histories. Subsequent work retained ELVIS as that baseline while adding merger statistics, quenching constraints, and, eventually, baryonic corrections to the inner-halo substructure problem.