Abstract: Computer-implemented methods may include accessing a predictive function. The predictive function may be configured to receive a partial or complete bond string and position (BSP) representation of a molecule of a reactant ionic liquid, where the representation identifies relative positions of atoms in the molecule. The predictive function may be configured to predict a reaction-characteristic value that characterizes a reaction between the ionic liquid and a particular polymer. The predictive function may be generated using training data corresponding to a set of molecules that were selected using Bayesian optimization, one or more previous versions of the predictive function, and experimentally derived reaction-characteristic values characterizing reactions between the molecules and the particular polymer. The method may also include identifying a particular ionic liquid as a prospect for depolymerizing the particular polymer based on the predictive function.

Abstract: Computer-implemented methods may include identifying a polymer for decomposition. The method may further include accessing, for an ionic liquid, one or more properties corresponding to the polymer. One or more properties may characterize a reaction between the polymer and the ionic liquid. The method may also include accessing a value of the property using a quantum-mechanical or thermodynamical method. The method may include determining a bond string and position (BSP) representation of a molecule of the ionic liquid. The method may further include determining an embedded representation of the ionic liquid based on the BSP representation. In addition, the method may include generating a relationship between BSP representations of molecules and the one or more properties. The method may also include identifying an ionic liquid as a prospect for depolymerizing the specific polymer based on the relationship. The method may include outputting an identification of the ionic liquid.

Abstract: Computer-implemented methods may include accessing a multi-dimensional embedding space that supports relating embeddings of molecules to predicted values of a given property of the molecules. The method may also include identifying one or more points of interest within the embedding space based on the predicted values. Each of the one or more points of interest may include a set of coordinate values within the multi-dimensional embedding space and may be associated with a corresponding predicted value of the given property. The method may further include generating, for each of the one or more points of interest, a structural representation of a molecule by transforming the set of coordinate values included in the point of interest using a decoder network. The method may include outputting a result that identifies, for each of the one or more points of interest, the structural representation of the molecule corresponding to the point of interest.

Abstract: Methods may include accessing a first data set that includes a plurality of first data elements. Each of the plurality of first data elements may characterize a depolymerization reaction. Each first data element may include an embedded representation of a structure of a reactant and a reaction-characteristic value that characterizes a reaction between the reactant and a polymer. The embedded representation may be identified as a set of coordinate values within an embedding space. The method may include constructing a predictive function to predict reaction-characteristic values from embedded representations. The method may also include evaluating a utility function that transforms a given point within the embedding space into a utility metric. The method may include identifying particular points as corresponding to high utility metrics. The method may also include outputting a result that identifies a reactant corresponding to the particular point or a reactant structure corresponding to the particular point.

Abstract: Methods and systems for using multiple hyperspectral cameras sensitive to different wavelengths to predict characteristics of objects for further processing, including recycling, are described. The multiple hyperspectral images can be used to predict higher resolution spectra by using a trained machine learning model. The higher resolution spectra may be more easily analyzed to sort plastics into a recyclability category. The hyperspectral images may also be used to identify and analyze dark or black plastics, which are challenging for SWIR, MWIR, and other wavelengths. The machine learning model may also predict the base polymers and contaminants of plastic objects for recycling. The hyperspectral images may be used to predict recyclability and other characteristics using a trained machine learning model.

Abstract: Image data is obtained that indicates an extent to which one or more objects reflect, scatter, or absorb light at each of multiple wavelength bands, where the image data was collected while a conveyor belt was moving the object(s). The image data is preprocessed by performing an analysis across frequencies and/or performing an analysis across a representation of a spatial dimension. A set of feature values is generated using the image preprocessed image data. A machine-learning model generates an output using to the feature values. A prediction of an identity of a chemical in the one or more objects or a level of one or more chemicals in the object(s) is generated using the output. Data is output indicating the prediction of the identity of the chemical in the object(s) or the level of the one or more chemicals in at least one of the one or more objects.