Neural Decision Tree: A New Tool for Building Forecast Models for Plasmasphere Dynamics.

The Neural Decision Tree (NDT) is a hybrid supervised machine‐learning algorithm that combines the self‐limiting property of a decision tree (Classification and Regression Tree [CART]) algorithm with the artificial neural network. We demonstrate the use of NDT for a regression problem of building a prediction model for the plasmasphere electron density with solar and geomagnetic measurements as inputs. Our work replicates the work by Zhelavskaya et al. reported in their 2017 article (I. S. Zhelavskaya et al., 2017, https://doi.org/10.1002/2017JA024406) to show that NDT makes available sophisticated network layout for building a predictive model, thus taking advantage of deep‐learning potential of the neural network. We also demonstrate that with the ability to automatically select an appropriate network layout, as well as, effective initialization, the NDT algorithm allows research scientists in space weather to focus more of their attention on physically and statistically relevant aspects of using machine‐learning techniques. In fact, our example highlights the fact that the basic assumptions of standard supervise machine‐learning problems are often unsatisfied in real‐world space weather applications. Greater attention to these fundamental issues may create significantly different solutions to space weather forecast problems. Plain Language Summary: Machine learning techniques are widely applicable and have numerous breakthrough results in the space weather community. Decision Trees and Artificial Neural Networks are two of the most popular machine learning methods. We demonstrate the use of the technique called Neural Decision Tree (NDT), which is a hybrid method combining decision trees and neural networks, to predict plasmasphere electron density with solar and geomagnetic measurements as inputs. Our work replicates the work by Zhelavskaya et al. reported in their 2017 article to show that NDT makes available model layouts and takes advantage of both neural networks and decision trees. We provide a machine learning method to automatically construct a network‐based model. Such automation allows scientists to focus more on the physical and statistical aspects. Our example highlights the fact that the basic assumptions of standard supervise machine‐learning problems are often unsatisfied in real‐world space weather applications. Greater attention to these fundamental issues may create significantly different solutions to space weather forecast problems. Key Points: Neural Decision Tree (NDT) is an effective tool for building space weather forecast modelsMore elaborate neural network structure initialized using NDT can provide higher performance and training efficiencyPhysics‐based model constraints with statistical assumptions can have a significant impact on designing machine‐learning techniques [ABSTRACT FROM AUTHOR]