A recent article introduces a streaming sparse Cholesky method designed to improve derivative-informed Gaussian process surrogate models within digital twin applications. Digital twins are computational models that simulate the behavior of physical assets, enabling real-time prediction of their future states. By employing this new method, the accuracy of these surrogate models is enhanced, facilitating more precise forecasting. This advancement is particularly relevant for industries that depend on accurate and timely predictions of asset behavior. The method’s focus on streaming and sparsity addresses computational challenges, making it suitable for real-time applications. The article’s findings align with connected research emphasizing the importance of Gaussian process models in digital twin contexts. Overall, this development represents a promising step toward more effective and efficient digital twin implementations.