Litcius/Paper detail

Spatial and Spatiotemporal Interpolation / Prediction using Ensemble Machine Learning

T. Hengl, L. Parente, C. Bonannella

2022Zenodo (CERN European Organization for Nuclear Research)15 citationsDOIOpen Access PDF

Abstract

This R tutorial explains step-by-step how to use Ensemble Machine Learning to generate predictions (maps) from 2D, 3D, 2D+T training (point) datasets. We show functionality to do automated benchmarking for spatial/spatiotemporal prediction problems, and for which we use primarily the mlr framework and spatial packages terra, rgdal and similar. In addition, we explain how to plot spatial/spatiotemporal prediction inputs and outputs, including how to do accuracy plots and predictograms. We focus engineering the predictive mapping around three main areas: (a) accuracy performance, (b) computing time, (c) robustness of the algorithms (sensitivity to noise, artifacts etc). Online version of the book is available at: <strong>https://opengeohub.github.io/spatial-prediction-eml/</strong>

Topics & Concepts

Multivariate interpolationEnsemble learningComputer scienceInterpolation (computer graphics)Artificial intelligenceMachine learningPattern recognition (psychology)Computer visionBilinear interpolationImage (mathematics)Remote Sensing and LiDAR Applications
Spatial and Spatiotemporal Interpolation / Prediction using Ensemble Machine Learning | Litcius