Designing and printing metamaterials with customizable architectures enables the realization of unprecedented mechanical behaviors that transcend those of their constituent materials. These behaviors are recorded in the form of response curves, with stress-strain curves describing their quasi-static footprint. However, existing inverse design approaches are yet matured to capture the full desired behaviors due to challenges stemmed from multiple design objectives, nonlinear behavior, and process-dependent manufacturing errors. Here, we report a rapid inverse design methodology, leveraging generative machine learning and desktop additive manufacturing, which enables the creation of nearly all possible uniaxial compressive stress‒strain curve cases while accounting for process-dependent errors from printing. Results show that mechanical behavior with full tailorability can be achieved with nearly 90% fidelity between target and experimentally measured results. Our approach represents a starting point to inverse design materials that meet prescribed yet complex behaviors and potentially bypasses iterative design-manufacturing cycles.

Machine learning (ML) regression methods are promising tools to develop models predicting the properties of materials by learning from existing databases. However, although ML models are usually good at interpolating data, they often do not offer reliable extrapolations and can violate the laws of physics. Here, to address the limitations of traditional ML, we introduce a “topology-informed ML” paradigm—wherein some features of the network topology (rather than traditional descriptors) are used as fingerprint for ML models—and apply this method to predict the forward (stage I) dissolution rate of a series of silicate glasses. We demonstrate that relying on a topological description of the atomic network (i) increases the accuracy of the predictions, (ii) enhances the simplicity and interpretability of the predictive models, (iii) reduces the need for large training sets, and (iv) improves the ability of the models to extrapolate predictions far from their training sets. As such, topology-informed ML can overcome the limitations facing traditional ML (e.g., accuracy vs. simplicity tradeoff) and offers a promising route to predict the properties of materials in a robust fashion.

Phospholipids and proteins were separately removed as the main non-rubber components to individually study their effect on the structure and properties of the rubber. Fourier Transform Infrared Spectroscopy (FTIR) and ¹H nuclear magnetic resonance spectroscopy (¹H-NMR) were used to characterize the chemical structure and the residual non-rubber component. A rheology study and stress relaxation measurements were used to study the role that non-rubber components play in natural networks. A rheological study showed that natural rubber (NR) and deproteinized natural rubber (DPNR) exhibited similar dynamic modulus at 170 °C. The lack of superposition in van Gurp–Palmen (vGP) curves at different temperatures for NR and DPNR, together with the shape of vGP curves, proved that long chain branching was mainly constructed by phospholipids. Stress relaxation measurements at room temperature were fitted with the Maxwell model and showed that the NR relaxation curve underwent a quick decrease and then came to an equilibrium stress retention of 58%, which is about 3 times higher than that of DPNR, indicating that proteins in NR contributed to the network structure at room temperature. Combining molecular dynamic studies, the interaction of proteins and phospholipids in non-rubber networks was proposed.