Chapter 1 Quiz: Introduction to ML in Geosciences

Chapter 1: Welcome — ML for Earth and Subsurface Data

Learning objectives

Test your understanding of ML concepts, forward/inverse problems, and Python basics

This quiz covers both the lecture material and lab exercises from Chapter 1.

ML Definition (Mitchell): A program learns from experience $E$ w.r.t. task $T$ and performance $P$ if $P$ on $T$ improves with $E$ .
Forward vs Inverse Problems: Forward: $d = G(m)$ (model $\to$ data). Inverse: $m = G^{-1}(d)$ (data $\to$ model). Inverse problems are typically ill-posed (existence, uniqueness, stability).
Supervised vs Unsupervised: Supervised uses labeled data for prediction; unsupervised discovers patterns in unlabeled data.
Semivariance: $\gamma(h) = \frac{1}{2N(h)}\sum[z(x_i) - z(x_i + h)]^2$ increases with lag $h$ and plateaus at the sill.
Python Basics: Slicing ( $x[1:4]$ excludes index 4), negative indexing ( $x[-1]$ = last element), range(a, b) excludes $b$ .

Bergen, K.J., Johnson, P.A., de Hoop, M.V., Beroza, G.C. (2019). Machine learning for data-driven discovery in solid Earth geoscience. Science 363, eaau0323.
Reichstein, M., Camps-Valls, G., Stevens, B., et al. (2019). Deep learning and process understanding for data-driven Earth-system science. Nature 566, 195–204.
Bishop, C.M. (2006). Pattern Recognition and Machine Learning, ch. 1. Springer.