On the generalization of $g$-circulant MDS matrices

A matrix $M$ over the finite field $\mathbb{F}_q$ is called \emph{maximum distance separable} (MDS) if all of its square submatrices are non-singular. These MDS matrices are very important in cryptography and coding theory because they provide strong data protection and help spread information efficiently. In this paper, we introduce a new type of matrix called a \emph{consta-$g$-circulant matrix}, which extends the idea of $g$-circulant matrices. These matrices come from a linear transformation defined by the polynomial $h(x) = x^m - \lambda + \sum_{i=0}^{m-1} h_i x^i$ over $\mathbb{F}_q$. We find the upper bound of such matrices exist and give conditions to check when they are invertible. This helps us know when they are MDS matrices. If the polynomial $x^m - \lambda$ factors as $x^m - \lambda = \prod_{i=1}^{t} f_i(x)^{e_i},$ where each $f_i(x)$ is irreducible, then the number of invertible consta-$g$-circulant matrices is $N \cdot \prod_{i=1}^{t} \left( q^{\deg f_i} - 1 \right),$ where $r$ is the multiplicative order of $\lambda$, and $N$ is the number of integers $k$ such that $0 \leq k < \left\lfloor \frac{m - 1}{r} \right\rfloor + 1 \quad \text{and} \quad \gcd(1 + rk, m) = 1.$ This formula help us to reduce the number of cases to check whether such matrices is MDS. Moreover, we give complete characterization of $g$-circulant MDS matrices of order 3 and 4. Additionally, inspired by skew polynomial rings, we construct a new variant of $g$-circulant matrix. In the last, we provide some examples related to our findings.