The parameter space of CNT forest synthesis is vastand multidimensional, making experimental and/or numericalexploration of the synthesis prohibitive. We propose a morepractical approach to explore the synthesis-process relationshipsof CNT forests using machine learning (ML) algorithms toinfer the underlying complex physical processes. Currently, nosuch ML model linking CNT forest morphology to synthesisparameters has been demonstrated. In the current work, weuse a physics-based numerical model to generate CNT forestmorphology images with known synthesis parameters to trainsuch a ML algorithm. The CNT forest synthesis variablesof CNT diameter and CNT number densities are varied togenerate a total of 12 distinct CNT forest classes. Images of theresultant CNT forests at different time steps during the growthand self-assembly process are then used as the training dataset.Based on the CNT forest structural morphology, multiplesingle and combined histogram-based texture descriptors areused as features to build a random forest (RF) classifier topredict class labels based on correlation of CNT forest physicalattributes with the growth parameters. The machine learningmodel achieved an accuracy of up to 83.5% on predicting thesynthesis conditions of CNT number density and diameter.These results are the first step towards rapidly characterizingCNT forest attributes using machine learning. Identifying therelevant process-structure interactions for the CNT forests usingphysics-based simulations and machine learning could rapidlyadvance the design, development, and adoption of CNT forestapplications with varied morphologies and properties.

The parameter space of CNT forest synthesis is vast and multidimensional, making experimental and/or numerical exploration of the synthesis prohibitive. We propose a more practical approach to explore the synthesis-process relationships of CNT forests using machine learning (ML) algorithms to infer the underlying complex physical processes. Currently, no such ML model linking CNT forest morphology to synthesis parameters has been demonstrated. In the current work, we use a physics-based numerical model to generate CNT forest morphology images with known synthesis parameters to train such a ML algorithm. The CNT forest synthesis variables of CNT diameter and CNT number densities are varied to generate a total of 12 distinct CNT forest classes. Images of the resultant CNT forests at different time steps during the growth and self-assembly process are then used as the training dataset. Based on the CNT forest structural morphology, multiple single and combined histogram-based texture descriptors are used as features to build a random forest (RF) classifier to predict class labels based on correlation of CNT forest physical attributes with the growth parameters. The machine learning model achieved an accuracy of up to 83.5% on predicting the synthesis conditions of CNT number density and diameter. These results are the first step towards rapidly characterizing CNT forest attributes using machine learning. Identifying the relevant process-structure interactions for the CNT forests using physics-based simulations and machine learning could rapidly advance the design, development, and adoption of CNT forest applications with varied morphologies and properties.

While the physical properties of carbon nanotubes (CNTs) are often superior to conventional engineering materials, their widespread adoption into many applications is limited by scaling the properties of individual CNTs to macroscale CNT assemblies known as CNT forests. The self-assembly mechanics of CNT forests that determine their morphology and ensemble properties remain poorly understood. Few experimental techniques exist to characterize and observe the growth and self-assembly processes in situ. Here we introduce the use of in-situ scanning electron microscope (SEM) synthesis based on chemical vapor deposition (CVD) processing. In this preliminary report, we share best practices for in-situ SEM CVD processing and initial CNT forest synthesis results. Image analysis techniques are developed to identify and track the movement of catalyst nanoparticles during synthesis conditions. Finally, a perspective is provided in which in-situ SEM observations represent one component of a larger system in which numerical simulation, machine learning, and digital control of experiments reduces the role of humans and human error in the exploration of CNT forest process-structure-property relationships.

No abstract

No abstract