Physics-informed machine learning for the COVID-19 pandemic: Adherence to social distancing and short-term predictions for eight countries

THz-TDS: extracting complex conductivity of two-dimensional materials via neural networks trained on synthetic and experimental data

Terahertz time-domain spectroscopy (TDS) has proved immensely useful for probing 2D materials such as graphene. Unlike in the visible regime, the optical properties at terahertz frequencies are highly dependant on charge carrier mobility and scattering time. However, extracting the material properties from the terahertz waveform is a non-trivial process, which can be prone to producing erroneous results. Artificial neural networks have recently been demonstrated as useful tools to extract complex refractive index from terahertz time domain data. Here, we propose the use of artificial neural networks to interpret terahertz spectra of graphene monolayers to extract the charge carrier mobility and scattering time. We demonstrate improved performance on out-of-distribution data by using a combination of synthetically generated spectra and experimental data during training.

Integrating artificial intelligence with mechanistic epidemiological modeling: a scoping review of opportunities and challenges

Integrating prior epidemiological knowledge embedded within mechanistic models with the data-mining capabilities of artificial intelligence (AI) offers transformative potential for epidemiological modeling. While the fusion of AI and traditional mechanistic approaches is rapidly advancing, efforts remain fragmented. This scoping review provides a comprehensive overview of emerging integrated models applied across the spectrum of infectious diseases. Through systematic search strategies, we identified 245 eligible studies from 15,460 records. Our review highlights the practical value of integrated models, including advances in disease forecasting, model parameterization, and calibration. However, key research gaps remain. These include the need for better incorporation of realistic decision-making considerations, expanded exploration of diverse datasets, and further investigation into biological and socio-behavioral mechanisms. Addressing these gaps will unlock the synergistic potential of AI and mechanistic modeling to enhance understanding of disease dynamics and support more effective public health planning and response.

A Modified PINN Approach for Identifiable Compartmental Models in Epidemiology with Application to COVID-19

Many approaches using compartmental models have been used to study the COVID-19 pandemic, with machine learning methods applied to these models having particularly notable success. We consider the Susceptible-Infected-Confirmed-Recovered-Deceased (SICRD) compartmental model, with the goal of estimating the unknown infected compartment I, and several unknown parameters. We apply a variation of a "Physics Informed Neural Network" (PINN), which uses knowledge of the system to aid learning. First, we ensure estimation is possible by verifying the model's identifiability. Then, we propose a wavelet transform to process data for the network training. Finally, our central result is a novel modification of the PINN's loss function to reduce the number of simultaneously considered unknowns. We find that our modified network is capable of stable, efficient, and accurate estimation, while the unmodified network consistently yields incorrect values. The modified network is also shown to be efficient enough to be applied to a model with time-varying parameters. We present an application of our model results for ranking states by their estimated relative testing efficiency. Our findings suggest the effectiveness of our modified PINN network, especially in the case of multiple unknown variables.