Sustainable production planning can be achieved by including several key factors along with production which affect the environment and economy. In the current competitive market scenario, it is highly essential to emphasize several objectives simultaneously. Planning for sustainable manufacturing must take crucial issues like carbon emissions, energy use, and production cost minimization into account. The methodology for creating a practical design space for manufacturing with capped carbon emissions, energy use, and production prices is proposed in this study. Data-driven machine learning approaches are implemented to classify feasible data points from the data set to create design space and a model which predicts feasible and not feasible data points. Algebraic equations are constructed using support vectors. Using the equation, whether the selected process path satisfies all of the established criteria can be determined. To demonstrate the practical applicability and goal of the suggested techniques, an example is provided. The models have achieved an accuracy of 90 % using SVM and 100 % accuracy using Random Forest.