Multitask deep learning for the emulation and calibration of an agent-based malaria transmission model

Abstract Agent-based models of malaria transmission are useful tools for understanding disease dynamics and planning interventions, but they can be computationally intensive to calibrate. We present a multitask deep learning approach for emulating and calibrating a complex agent-based model of malaria transmission. Our neural network emulator was trained on a large suite of simulations from the EMOD malaria model, an agent-based model of malaria transmission dynamics, capturing relationships between immunological parameters and epidemiological outcomes such as age-stratified incidence and prevalence across eight sub-Saharan African study sites. We then use the trained emulator in conjunction with parameter estimation techniques to calibrate the underlying model to reference data. Taken together, this analysis shows the potential of machine learning-guided emulator design for complex scientific processes and their comparison to field data. Author summary Mathematical models can help understand and design interventions for infectious diseases such as malaria, but they can be complex and time-consuming to work with. In this study, we developed a machine learning approach to create a fast and accurate emulator for a detailed malaria transmission model. Our emulator can quickly predict various disease outcomes based on different immune system parameters. We trained it using a large set of simulations created using the EMOD malaria model and tested it against real-world data from multiple African countries. The emulator not only matches the original model’s predictions closely, but can also be used to efficiently find the best parameter values to match field observations. We hope that this work can serve as a demonstration of machine learning tools to link complex models of disease transmission to field data.