The Ricci tensor can be characterized by measurement of how a shape is deformed as one moves along geodesics in the space. In general relativity, which involves the pseudo-Riemannian setting, this is reflected by the presence of the Ricci tensor in the Raychaudhuri equation. Partly for this reason, the Einstein field equations propose that spacetime can be described by a pseudo-Riemannian metric, with a strikingly simple relationship between the Ricci tensor and the matter content of the universe.
Like the metric tensor, the Ricci tensor assigns to each tangent space of the manifold a symmetric bilinear form (Besse 1987, p. 43). Broadly, one could analogize the role of the Ricci curvature in Riemannian geometry to that of the Laplacian in the analysis of functions; in this analogy, the Riemann curvature tensor, of which the Ricci curvature is a natural by-product, would correspond to the full matrix of second derivatives of a function. However, there are other ways to draw the same analogy.
In differential geometry, lower bounds on the Ricci tensor on a Riemannian manifold allow one to extract global geometric and topological information by comparison (cf. comparison theorem) with the geometry of a constant curvature space form. This is since lower bounds on the Ricci tensor can be successfully used in studying the length functional in Riemannian geometry, as first shown in 1941 via Myers's theorem.
One common source of the Ricci tensor is that it arises whenever one commutes the covariant derivative with the tensor Laplacian. This, for instance, explains its presence in the Bochner formula, which is used ubiquitously in Riemannian geometry. For example, this formula explains why the gradient estimates due to Shing-Tung Yau (and their developments such as the Cheng-Yau and Li-Yau inequalities) nearly always depend on a lower bound for the Ricci curvature.
The first subsection here is meant as an indication of the definition of the Ricci tensor for readers who are comfortable with linear algebra and multivariable calculus. The later subsections use more sophisticated terminology.
Introduction and local definition
Let U be an open subset of Rn, and for each pair of numbers i and j between 1 and n, let gij : U → R be a smooth function, subject to the condition that, for each p in U, the matrix
is symmetric and invertible. For each p in U, let [gij(p)] be the inverse of the above matrix [gij(p)]. The functions Rij are defined explicitly by the following formulae:
where xi is the ith coordinate of Rn.
It can be seen directly from inspection of this formula that Rij must equal Rji for any i and j. So one can view the functions Rij as associating to any point p of U a symmetric n × n matrix. This matrix-valued map on U is called the Ricci curvature associated to the collection of functions gij.
As presented, there is nothing intuitive or natural about the definition of Ricci curvature. It is singled out as an object for study only because it satisfies the following remarkable property. Let V ⊂ Rn be another open set and let y : V → U be a smooth map whose matrix of first derivatives
is invertible for any choice of q ∈ V. Define gij : V → R by the matrix product
and let [Rij(q)] be the Ricci curvature associated with [gij(q)]. Then one can compute, using the product rule and the chain rule, the following relationship between the Ricci curvature of the collection of functions gij and the Ricci curvature of the collection of functions gij: for any q in V, one has
This is quite unexpected since, directly plugging the formula which defines gij into the formula defining Rij, one sees that one will have to consider up to third derivatives of y, arising when the second derivatives in the first four terms of the definition of Rij act upon the components of J. The "miracle" is that the imposing collection of first derivatives, second derivatives, and inverses comprising the definition of the Ricci curvature is perfectly set up so that all of these higher derivatives of y cancel out, and one is left with the remarkably clean matrix formula above which relates Rij and Rij. It is even more remarkable that this cancellation of terms is such that the matrix formula relating Rij to Rij is identical to the matrix formula relating gij to gij.
With the use of some sophisticated terminology, the definition of Ricci curvature can be summarized as saying:
Let U be an open subset of Rn. Given a smooth mapping g on U which is valued in the space of invertible symmetric n × n matrices, one can define (by a complicated formula involving various partial derivatives of the components of g) the Ricci curvature of g to be a smooth mapping from U into the space of symmetric n × n matrices.
The remarkable and unexpected property of Ricci curvature can be summarized as:
Let J denote the Jacobian matrix of a diffeomorphism y from some other open set V to U. The Ricci curvature of the matrix-valued function given by the matrix product JT(g∘y)J is given by the matrix product JT(R∘y)J, where R denotes the Ricci curvature of g.
In mathematics, this property is referred to by saying that the Ricci curvature is a "tensorial quantity", and marks the formula defining Ricci curvature, complicated though it may be, as of outstanding significance in the field of differential geometry. In physical terms, this property is a manifestation of "general covariance" and is a primary reason that Albert Einstein made use of the formula defining Rij when formulating general relativity. In this context, the possibility of choosing the mapping y amounts to the possibility of choosing between reference frames; the "unexpected property" of the Ricci curvature is a reflection of the broad principle that the equations of physics do not depend on reference frame.
This is discussed from the perspective of differentiable manifolds in the following subsection, although the underlying content is virtually identical to that of this subsection.
Definition via local coordinates on a smooth manifold
Let (M, g) be a smooth Riemannian or pseudo-Riemannian n-manifold. Given a smooth chart (U,
) one then has functions gij :
(U) → R and gij :
(U) → R for each i and j between 1 and n which satisfy
for all x in
(U). The functions gij are defined by evaluating g on coordinate vector fields, while the functions gij are defined so that, as a matrix-valued function, they provide an inverse to the matrix-valued function x ↦ gij(x).
Now define, for each a, b, c, i, and j between 1 and n, the functions
(U) → R.
Now let (U,
) and (V, ψ) be two smooth charts for which U and V have nonempty intersection. Let Rij :
(U) → R be the functions computed as above via the chart (U,
) and let rij : ψ(V) → R be the functions computed as above via the chart (V, ψ). Then one can check by a calculation with the chain rule and the product rule that
This shows that the following definition does not depend on the choice of (U,
). For any p in U, define a bilinear map Ricp : TpM × TpM → R by
where X1, ..., Xn and Y1, ..., Yn are the components of X and Y relative to the coordinate vector fields of (U,
It is common to abbreviate the above formal presentation in the following style:
Let M be a smooth manifold, and let g be a Riemannian or pseudo-Riemannian metric. In local smooth coordinates, define the Christoffel symbols
It can be directly checked that
so that Rij define a (0,2)-tensor field on M. In particular, if X and Y are vector fields on M then relative to any smooth coordinates one has
The final line includes the demonstration that the bilinear map Ric is well-defined, which is much easier to write out with the informal notation.
on vector fieldsX, Y, Z. The crucial property of this mapping is that if X, Y, Z and X', Y', and Z' are smooth vector fields such that X and X' define the same element of some tangent space TpM, and Y and Y' also define the same element of TpM, and Z and Z' also define the same element of TpM, then the vector fields R(X,Y)Z and R(X′,Y′)Z′ also define the same element of TpM.
The implication is that the Riemann curvature, which is a priori a mapping with vector field inputs and a vector field output, can actually be viewed as a mapping with tangent vector inputs and a tangent vector output. That is, it defines for each p in M a (multilinear) map
Define for each p in M the map by
That is, having fixed Y and Z, then for any basis v1, ..., vn of the vector space TpM, one defines
where for any fixed i the numbers ci1, ..., cin are the coordinates of Rmp(vi,Y,Z) relative to the basis v1, ..., vn. It is a standard exercise of (multi)linear algebra to verify that this definition does not depend on the choice of the basis v1, ..., vn.
Sign conventions. Note that some sources define to be what would here be called they would then define as Although sign conventions differ about the Riemann tensor, they do not differ about the Ricci tensor.
Comparison of the definitions
The two above definitions are identical. The formulas defining and in the coordinate approach have an exact parallel in the formulas defining the Levi-Civita connection, and the Riemann curvature via the Levi-Civita connection. Arguably, the definitions directly using local coordinates are preferable, since the "crucial property" of the Riemann tensor mentioned above requires to be Hausdorff in order to hold. By contrast, the local coordinate approach only requires a smooth atlas. It is also somewhat easier to connect the "invariance" philosophy underlying the local approach with the methods of constructing more exotic geometric objects, such as spinor fields.
The complicated formula defining in the introductory section is the same as that in the following section. The only difference is that terms have been grouped so that it is easy to see that
for all It thus follows linear-algebraically that the Ricci tensor is completely determined by knowing the quantity Ric(X,X) for all vectors X of unit length. This function on the set of unit tangent vectors is often also called the Ricci curvature, since knowing it is equivalent to knowing the Ricci curvature tensor.
The Ricci curvature is determined by the sectional curvatures of a Riemannian manifold, but generally contains less information. Indeed, if ξ is a vector of unit length on a Riemannian n-manifold, then Ric(ξ,ξ) is precisely (n − 1) times the average value of the sectional curvature, taken over all the 2-planes containing ξ. There is an (n − 2)-dimensional family of such 2-planes, and so only in dimensions 2 and 3 does the Ricci tensor determine the full curvature tensor. A notable exception is when the manifold is given a priori as a hypersurface of Euclidean space. The second fundamental form, which determines the full curvature via the Gauss–Codazzi equation, is itself determined by the Ricci tensor and the principal directions of the hypersurface are also the eigendirections of the Ricci tensor. The tensor was introduced by Ricci for this reason.
As can be seen from the second Bianchi identity, one has
where is the scalar curvature, defined in local coordinates as This is often called the contracted second Bianchi identity.
The Ricci curvature is sometimes thought of as (a negative multiple of) the Laplacian of the metric tensor (Chow & Knopf 2004, Lemma 3.32). Specifically, in harmonic local coordinates the components satisfy
Near any point p in a Riemannian manifold (M, g), one can define preferred local coordinates, called geodesic normal coordinates. These are adapted to the metric so that geodesics through p correspond to straight lines through the origin, in such a manner that the geodesic distance from p corresponds to the Euclidean distance from the origin. In these coordinates, the metric tensor is well-approximated by the Euclidean metric, in the precise sense that
In fact, by taking the Taylor expansion of the metric applied to a Jacobi field along a radial geodesic in the normal coordinate system, one has
In these coordinates, the metric volume element then has the following expansion at p:
which follows by expanding the square root of the determinant of the metric.
Thus, if the Ricci curvature Ric(ξ,ξ) is positive in the direction of a vector ξ, the conical region in M swept out by a tightly focused family of geodesic segments of length emanating from p, with initial velocity inside a small cone about ξ, will
have smaller volume than the corresponding conical region in Euclidean space, at least provided that is sufficiently small. Similarly, if the Ricci curvature is negative in the direction of a given vector ξ, such a conical region in the manifold will instead have larger volume than it would in Euclidean space.
The Ricci curvature is essentially an average of curvatures in the planes including ξ. Thus if a cone emitted with an initially circular (or spherical) cross-section becomes distorted into an ellipse (ellipsoid), it is possible for the volume distortion to vanish if the distortions along the principal axes counteract one another. The Ricci curvature would then vanish along ξ. In physical applications, the presence of a nonvanishing sectional curvature does not necessarily indicate the presence of any mass locally; if an initially circular cross-section of a cone of worldlines later becomes elliptical, without changing its volume, then this is due to tidal effects from a mass at some other location.
Ricci curvature also appears in the Ricci flow equation, where certain one-parameter families of Riemannian metrics are singled out as solutions of a geometrically-defined partial differential equation. This system of equations can be thought of as a geometric analog of the heat equation, and was first introduced by Richard S. Hamilton in 1982. Since heat tends to spread through a solid until the body reaches an equilibrium state of constant temperature, if one is given a manifold, the Ricci flow may be hoped to produce an 'equilibrium' Riemannian metric which is Einstein or of constant curvature. However, such a clean "convergence" picture cannot be achieved since many manifolds cannot support such metrics. A detailed study of the nature of solutions of the Ricci flow, due principally to Hamilton and Grigori Perelman, shows that the types of "singularities" that occur along a Ricci flow, corresponding to the failure of convergence, encodes deep information about 3-dimensional topology. The culmination of this work was a proof of the geometrization conjecture first proposed by William Thurston in the 1970s, which can be thought of as a classification of compact 3-manifolds.
On a Kähler manifold, the Ricci curvature determines the first Chern class of the manifold (mod torsion). However, the Ricci curvature has no analogous topological interpretation on a generic Riemannian manifold.
Global geometry and topology
Here is a short list of global results concerning manifolds with positive Ricci curvature; see also classical theorems of Riemannian geometry. Briefly, positive Ricci curvature of a Riemannian manifold has strong topological consequences, while (for dimension at least 3), negative Ricci curvature has no topological implications. (The Ricci curvature is said to be positive if the Ricci curvature function Ric(ξ,ξ) is positive on the set of non-zero tangent vectors ξ.) Some results are also known for pseudo-Riemannian manifolds.
Myers' theorem (1941) states that if the Ricci curvature is bounded from below on a complete Riemannian n-manifold by (n − 1)k > 0, then the manifold has diameter ≤ π/√k. By a covering-space argument, it follows that any compact manifold of positive Ricci curvature must have finite fundamental group. Cheng (1975) showed that, in this setting, equality in the diameter inequality occurs if only if the manifold is isometric to a sphere of a constant curvature k.
The Bishop–Gromov inequality states that if a complete n-dimensional Riemannian manifold has non-negative Ricci curvature, then the volume of a geodesic ball is less than or equal to the volume of a geodesic ball of the same radius in Euclidean n-space. Moreover, if vp(R) denotes the volume of the ball with center p and radius R in the manifold and V(R) = cnRn denotes the volume of the ball of radius R in Euclidean n-space then the function vp(R)/V(R) is nonincreasing. This can be generalized to any lower bound on the Ricci curvature (not just nonnegativity), and is the key point in the proof of Gromov's compactness theorem.)
The Cheeger–Gromoll splitting theorem states that if a complete Riemannian manifold (M,g) with Ric ≥ 0 contains a line, meaning a geodesic such that d(γ(u),γ(v)) = |u − v| for all u, v ∈ R, then it is isometric to a product space R × L. Consequently, a complete manifold of positive Ricci curvature can have at most one topological end. The theorem is also true under some additional hypotheses for complete Lorentzian manifolds (of metric signature (+ − − ...)) with non-negative Ricci tensor (Galloway 2000).
Hamilton's first convergence theorem for Ricci flow has, as a corollary, that the only compact 3-manifolds which have Riemannian metrics of positive Ricci curvature are the quotients of the 3-sphere by discrete subgroups of SO(4) which act properly discontinuously. He later extended this to allow for nonnegative Ricci curvature. In particular, the only simply-connected possibility is the 3-sphere itself.
These results, particularly Myers' and Hamilton's, show that positive Ricci curvature has strong topological consequences. By contrast, excluding the case of surfaces, negative
Ricci curvature is now known to have no topological implications; Lohkamp (1994) has shown that any manifold of dimension greater than two admits a complete Riemannian metric of negative Ricci curvature. In the case of two-dimensional manifolds, negativity of the Ricci curvature is synonymous with negativity of the Gaussian curvature, which has very clear topological implications. There are very few two-dimensional manifolds which fail to admit Riemannian metrics of negative Gaussian curvature.
Behavior under conformal rescaling
If the metric g is changed by multiplying it by a conformal factor e2f, the Ricci tensor of the new, conformally-related metric g̃ = e2fg is given (Besse 1987, p. 59) by
where Δ = d*d is the (positive spectrum) Hodge Laplacian, i.e., the opposite of the usual trace of the Hessian.
In particular, given a point p in a Riemannian manifold, it is always possible to find metrics conformal to the given metric g for which the Ricci tensor vanishes at p. Note, however, that this is only pointwise assertion; it is usually impossible to make the Ricci curvature vanish identically on the entire manifold by a conformal rescaling.
For two dimensional manifolds, the above formula shows that if f is a harmonic function, then the conformal scaling g ↦ e2fg does not change the Ricci tensor (although it still changes its trace with respect to the metric unless f = 0).
where Ric and R denote the Ricci curvature and scalar curvature of g. The name of this object reflects the fact that its trace automatically vanishes: However, it is quite an important tensor since it reflects an "orthogonal decomposition" of the Ricci tensor.
The orthogonal decomposition of the Ricci tensor
Trivially, one has
It is less immediately obvious that the two terms on the right hand side are orthogonal to each other:
An identity which is intimately connected with this (but which could be proved directly) is that
The trace-free Ricci tensor and Einstein metrics
By taking a divergence, and using the contracted Bianchi identity, one sees that implies So, provided that n ≥ 3 and is connected, the vanishing of implies that the scalar curvature is constant. One can then see that the following are equivalent:
for some number
In the Riemannian setting, the above orthogonal decomposition shows that is also equivalent to these conditions. In the pseudo-Riemmannian setting, by contrast, the condition does not necessarily imply so the most that one can say is that these conditions imply
The Levi-Civita connection corresponding to the metric on X gives rise to a connection on κ. The curvature of this connection is the two form defined by
where J is the complex structure map on the tangent bundle determined by the structure of the Kähler manifold. The Ricci form is a closed 2-form. Its cohomology class is, up to a real constant factor, the first Chern class of the canonical bundle, and is therefore a topological invariant of X (for compact X) in the sense that it depends only on the topology of X and the homotopy class of the complex structure.
Conversely, the Ricci form determines the Ricci tensor by
In local holomorphic coordinates zα, the Ricci form is given by
If the Ricci tensor vanishes, then the canonical bundle is flat, so the structure group can be locally reduced to a subgroup of the special linear group SL(n,C). However, Kähler manifolds already possess holonomy in U(n), and so the (restricted) holonomy of a Ricci-flat Kähler manifold is contained in SU(n). Conversely, if the (restricted) holonomy of a 2n-dimensional Riemannian manifold is contained in SU(n), then the manifold is a Ricci-flat Kähler manifold (Kobayashi & Nomizu 1996, IX, §4).
Generalization to affine connections
The Ricci tensor can also be generalized to arbitrary affine connections, where it is an invariant that plays an especially important role in the study of projective geometry (geometry associated to unparameterized geodesics) (Nomizu & Sasaki 1994). If ∇ denotes an affine connection, then the curvature tensor R is the (1,3)-tensor defined by
for any vector fields X, Y, Z. The Ricci tensor is defined to be the trace:
In this more general situation, the Ricci tensor is symmetric if and only if there exist locally a parallel volume form for the connection.
Discrete Ricci curvature
Notions of Ricci curvature on discrete manifolds have been defined on graphs and networks, where they quantify local divergence properties of edges. Olliver's Ricci curvature is defined using optimal transport theory. A different (and earlier) notion, Forman's Ricci curvature, is based on topological arguments.
^Lott, John; Villani, Cedric (2006-06-23). "Ricci curvature for metric-measure spaces via optimal transport". arXiv:math/0412127.
^To be precise, there are many tensorial quantities in differential geometry. What makes the Ricci curvature (as well as other curvature quantities such as the Riemann curvature tensor) special is not the collection of functions of functions Rij itself, which is in principle "just one of many tensors," but is rather the automatic passage from one tensorial quantity (the collection of functions g) to a new tensorial quantity (the collection of functions R).