Fault Detection for Vaccine Refrigeration via Convolutional Neural Networks Trained on Simulated Datasets.

In low-and middle-income countries, the cold chain that supports vaccine storage and distribution is vulnerable due to insufficient infrastructure and interoperable data. To bolster these networks, we developed a convolutional neural network-based fault detection method for vaccine refrigerators using datasets synthetically generated by thermodynamic modelling. We demonstrate that these thermodynamic models can be calibrated to real cooling systems in order to identify system-specific faults under a diverse range of operating conditions. If implemented on a large scale, this portable, flexible approach has the potential to increase the fidelity and lower the cost of vaccine distribution in remote communities.

Hybrid exciton-plasmon-polaritons in van der Waals semiconductor gratings.

Van der Waals materials and heterostructures that manifest strongly bound exciton states at room temperature also exhibit emergent physical phenomena and are of great promise for optoelectronic applications. Here, we demonstrate that nanostructured, multilayer transition metal dichalcogenides (TMDCs) by themselves provide an ideal platform for excitation and control of excitonic modes, paving the way to exciton-photonics. Hence, we show that by patterning the TMDCs into nanoresonators, strong dispersion and avoided crossing of exciton, cavity photons and plasmon polaritons with effective separation energy exceeding 410 meV can be controlled with great precision. We further observe that inherently strong TMDC exciton absorption resonances may be completely suppressed due to excitation of hybrid light-matter states and their interference. Our work paves the way to the next generation of integrated exciton optoelectronic nano-devices and applications in light generation, computing, and sensing.