Numerical simulation and machine learning represent opposite approaches to computational analysis of the real world, deductive vs. inductive. However, both methods suffer from various uncertainties and even their combination often fails to link theory and reality. Focusing on GaN-based light-emitting diode (LED) design optimization, this paper evaluates examples of simulation-based machine learning from a physics point of view. Strategies are suggested for achieving more realistic predictions.
Main TextComputer simulations embed theoretical models into a practical environment (Piprek 2017). This enables a realistic test of such models by comparing calculated results to measurements. Simulations can thereby help explain experimental results that would otherwise be hard to understand. Simulations also allow for performance predictions for novel devices. However, it is well known that initial simulation results hardly ever agree with measurements. In other words, computer simulations often fail to represent the real world and create a virtual reality instead in which arti cial effects may happen (Fig. 1). This is not surprising as mathematical models always simplify reality. There are different levels of simpli cation, from short analytical formulas to complex systems of equations, which are all based on speci c assumptions about relevant physical processes. Certain assumptions may be inappropriate in a practical situation. Contradicting assumptions may even deliver almost identical results (Piprek 2015). Another problem is the employment of unrealistic material parameters. Published values of such parameters often vary substantially (Müller et al. 2014. Careful adjustments of computer simulations are required to nd agreement between theory and reality (Piprek et al. 2002, Wasmer et al. 2017).Machine learning, on the other hand, usually collects data in the real world and performs statistical analyses (Fig. 1). This is especially valuable when the amount of data is very large and hard to digest. Deep learning is currently the most popular machine learning method (LeCunn et al. 2015) and it is based on multi-layered arti cial neural networks (ANNs). Many data sets are needed to train an ANN. Due to scarcity and scatter of real-world data, experimental data collection is often replaced by computer simulations based on established theories. Such physics-based machine learning methods are increasingly utilized in materials science (Schmidt et al. 2019). Various semiconductor material systems are explored and optimized for applications in optoelectronics (Lu et al. 2019, Luo et al. 2020. Simulation-based machine learning is also popular with photonic devices (Molesky et al. 2018, Genty et al. 2020) utilizing solutions to Maxwell's equations that involve only few material parameters. Compared to photonics, optoelectronic devices are much more complex as they combine optical, electronic, and thermal processes. As indicated above, computer simulations of such devices not only involve various modeling approximations in need ...