Non Kählerian surfaces with a cycle of rational curves

From MaRDI portal
Publication:2049045



Abstract: Let S be a compact complex surface in class VII0+ containing a cycle of rational curves C=sumDj. Let D=C+A be the maximal connected divisor containing C. If there is another connected component of curves C′ then C′ is a cycle of rational curves, A=0 and S is a Inoue-Hirzebruch surface. If there is only one connected component D then each connected component Ai of A is a chain of rational curves which intersects a curve Cj of the cycle and for each curve Cj of the cycle there at most one chain which meets Cj. In other words, we do not prove the existence of curves other those of the cycle C, but if some other curves exist the maximal divisor looks like the maximal divisor of a Kato surface with perhaps missing curves. The proof of this topological result is an application of Donaldson theorem on trivialization of the intersection form and of deformation theory. We apply this result to show that a twisted logarithmic 1-form has a trivial vanishing divisor.


A minimal compact complex surface \(S\) is said to be of the class \(VII_0\) of Kodaira if the first Betti number satisfies \(b_1(S)=1\) and Kodaira dimension satisfies \(\kappa(S)<0\). A surface \(S\) is of class \(VII^+_0\) if moreover \(n:=b_2(S)>0\); these surfaces admit no nonconstant meromorphic functions. In this paper it is assumed that \(S\) is a compact complex surface of class \(VII^+_0\) containing a cycle of rational curves \(C=\sum Dj\). Let \(D=C+A\) be the maximal connected divisor containing \(C\). If there is another connected component of curves \(C'\), then \(C'\) is a cycle of rational curves, \(A=0\) and \(S\) is a Inoue-Hirzebruch surface. If there is only one connected component \(D\), then each connected component \(A_i\) of \(A\) is a chain of rational curves which intersects a curve \(D_j\) of the cycle and for each curve \(D_j\) of the cycle there is at most one chain which meets \(D_j\). In other words, the author does not prove the existence of curves other those of the cycle \(C\), but if some other curves exist, the maximal divisor looks like the maximal divisor of a Kato surface with perhaps missing curves. The proof of this topological result is an application of the Donaldson theorem on trivialization of the intersection form and of deformation theory. The author applies this result to show that a twisted logarithmic \(1\)-form has a trivial vanishing divisor. The paper is organized as follows. Section 1 is an introduction to the subject. Section 2 is devoted to topological classes of curves and chains. Section 3 deals with the (co)homological class of the maximal divisor. Here the author shows that the class of the maximal divisor of a surface with a cycle of rational curves is of the same type as the class of a cycle. Moreover the maximal divisor looks like the one of a Kato surface: if there is one connected component there is a cycle and trees attached to different curves. Section 4 is devoted to connected components of the maximal divisor and Section 5 to surfaces with twisted logarithmic forms.











This page was built for publication: Non Kählerian surfaces with a cycle of rational curves

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2049045)