From: A machine learning approach for mapping the very shallow theoretical geothermal potential

Symbol | Unit | Description |
---|---|---|

\(\varphi\) | (–) | Generic predictive function learned from training process |

B | (–) | Number of trees in a Random Forest |

d | (–) | Number of features (predictors) in the training data for an ML task |

\(E_{{\text{R}}}\) | (–) | Root Mean Square Error |

\(E_{{\text{NR}}}\) | (–) | Normalized Root Mean Square Error |

K | (–) | Number of folds consider in fold cross-validation |

m | (–) | Number of variables to consider to split a node v in a decision tree |

N | (–) | Number of training points (size of training data) |

\(N_{{\text{test}}}\) | (–) | Number of testing point (size of testing data) |

\({\mathbb {R}}\) | (–) | Set of real numbers |

\({\mathbf {x}}\) | (var. unit) | Generic input vector (realization of \(X_{1},...,X_{d}\)) |

\(X_{1},...,X_{d}\) | (var. unit) | Generic input variables |

y | (var. unit) | Generic output value (label, realization of Y) |

Y | (var. unit) | Generic output variable |