Efficient Creation of Jettability Diagrams Using Active Machine Learning.

The ability to jet a wide variety of materials consistently from print heads remains a key technical challenge for inkjet-based additive manufacturing processes. Drop watching is the most direct method for testing new inks and print head designs but such experiments are also resource consuming. In this work, a data-efficient machine learning technique called active learning is used to construct detailed jettability diagrams that identify complex regions corresponding to "no jetting," "jetting," and "desired jetting," rather than only individually sampled points. Crucially, our active learning method has resolved challenges with model selection that previously limited the accuracy of active learning in practical settings with very small experimental budgets. In addition, the key "desired jetting" zone may be quite small which is a challenge for initializing active learning. We leverage the physical intuition that the "desired jetting" zone tends to exist between the "jetting" and "no jetting" zone, to improve the performance of this highly imbalanced classification problem by performing two binary classifications in sequence. The first binary classification aims to map out the "jetting" zone versus the "no jetting" zone, while the second binary classification targets identifying the "desired jetting" zone with primary drops only. Our experiments use a stroboscopic drop watcher to visualize the jetting behavior of two fluids from a piezoelectric print head with different jetting waveforms. The results obtained from active learning were compared to a grid search method, which involves running more than 200 experiments for each fluid. The active learning method significantly reduces the number of experiments by 80% while achieving a test accuracy of more than 95% in the "jetting" zone prediction for the test fluids. The ability to construct these jettability diagrams will further accelerate new ink and print head developments.

In Silico Evolution of High-Performing Metal Organic Frameworks for Methane Adsorption.

The increased use of transition fuels, such as natural gas, and the resulting increase in methane emissions have resulted in a need for novel methane storage materials. Metal-organic frameworks (MOFs) have shown promise as efficient storage materials. A virtually limitless number of potential MOFs can be hypothesized, which exhibit a wide variety of different structural and chemical characteristics. Because of the numerous possibilities, identification of the best MOF for methane storage can be a potentially challenging problem. In this work, determination of the best such MOF was cast as an inverse function problem. The function, a random forest (RF) model using 12 structural and chemical descriptors, was trained on 10% of a data set consisting of 130 398 hypothetical MOFs (hMOFs) to predict simulated methane uptake. The RF model was tested on the remaining 90% of the data. After validation, a genetic algorithm (GA) was used to evolve in silico the best MOFs for methane adsorption. The RF model was imbedded into the GA as the fitness function to predict the methane uptake of the evolved MOFs (eMOFs). The best 15 eMOFs matched hMOFs found in the top 1% of the database. Nine of the 15 eMOFs were found in the top 0.1%. More impressively, two of the eMOFs matched the top two hypothetical MOFs with the highest methane uptake values out of the entire database of 130 398 MOFs. Further, by leveraging the ensemble nature of the GA, it was possible to characterize the importance of the different material properties for methane adsorption, providing fundamental insight for future material design strategies.

Energy-Geometry Dependency of Molecular Structures: A Multistep Machine Learning Approach.

There is growing interest in estimating quantum observables while circumventing expensive computational overhead for facile in silico materials screening. Machine learning (ML) methods are implemented to perform such calculations in shorter times. Here, we introduce a multistep method based on machine learning algorithms to estimate total energy on the basis of spatial coordinates and charges for various chemical structures, including organic molecules, inorganic molecules, and ions. This method quickly calculates total energy with 0.76 au in root-mean-square error (RMSE) and 1.5% in mean absolute percent error (MAPE) when tested on a database of optimized and unoptimized structures. Using similar molecular representations, experimental thermochemical properties were estimated, with MAPE as low as 6% and RMSE of 8 cal/mol·K for heat capacity in a 10-fold cross-validation.

Trends in Solid Adsorbent Materials Development for CO2 Capture.

A recent report from the United Nations has warned about the excessive CO2 emissions and the necessity of making efforts to keep the increase in global temperature below 2 °C. Current CO2 capture technologies are inadequate for reaching that goal, and effective mitigation strategies must be pursued. In this work, we summarize trends in materials development for CO2 adsorption with focus on recent studies. We put adsorbent materials into four main groups: (I) carbon-based materials, (II) silica/alumina/zeolites, (III) porous crystalline solids, and (IV) metal oxides. Trends in computational investigations along with experimental findings are covered to find promising candidates in light of practical challenges imposed by process economics.

Machine Learning Using Combined Structural and Chemical Descriptors for Prediction of Methane Adsorption Performance of Metal Organic Frameworks (MOFs).

Using molecular simulation for adsorbent screening is computationally expensive and thus prohibitive to materials discovery. Machine learning (ML) algorithms trained on fundamental material properties can potentially provide quick and accurate methods for screening purposes. Prior efforts have focused on structural descriptors for use with ML. In this work, the use of chemical descriptors, in addition to structural descriptors, was introduced for adsorption analysis. Evaluation of structural and chemical descriptors coupled with various ML algorithms, including decision tree, Poisson regression, support vector machine and random forest, were carried out to predict methane uptake on hypothetical metal organic frameworks. To highlight their predictive capabilities, ML models were trained on 8% of a data set consisting of 130,398 MOFs and then tested on the remaining 92% to predict methane adsorption capacities. When structural and chemical descriptors were jointly used as ML input, the random forest model with 10-fold cross validation proved to be superior to the other ML approaches, with an R2 of 0.98 and a mean absolute percent error of about 7%. The training and prediction using the random forest algorithm for adsorption capacity estimation of all 130,398 MOFs took approximately 2 h on a single personal computer, several orders of magnitude faster than actual molecular simulations on high-performance computing clusters.