Blog
About

3
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal. This paper presents a random forest for spatial predictions framework (RFsp) where buffer distances from observation points are used as explanatory variables, thus incorporating geographical proximity effects into the prediction process. The RFsp framework is illustrated with examples that use textbook datasets and apply spatial and spatio-temporal prediction to numeric, binary, categorical, multivariate and spatiotemporal variables. Performance of the RFsp framework is compared with the state-of-the-art kriging techniques using fivefold cross-validation with refitting. The results show that RFsp can obtain equally accurate and unbiased predictions as different versions of kriging. Advantages of using RFsp over kriging are that it needs no rigid statistical assumptions about the distribution and stationarity of the target variable, it is more flexible towards incorporating, combining and extending covariates of different types, and it possibly yields more informative maps characterizing the prediction error. RFsp appears to be especially attractive for building multivariate spatial prediction models that can be used as “knowledge engines” in various geoscience fields. Some disadvantages of RFsp are the exponentially growing computational intensity with increase of calibration data and covariates and the high sensitivity of predictions to input data quality. The key to the success of the RFsp framework might be the training data quality—especially quality of spatial sampling (to minimize extrapolation problems and any type of bias in data), and quality of model validation (to ensure that accuracy is not effected by overfitting). For many data sets, especially those with lower number of points and covariates and close-to-linear relationships, model-based geostatistics can still lead to more accurate predictions than RFsp.

          Related collections

          Most cited references 67

          • Record: found
          • Abstract: not found
          • Article: not found

          Random Forests

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            RANDOM FORESTS FOR CLASSIFICATION IN ECOLOGY

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Multivariable geostatistics in S: the gstat package

               Edzer Pebesma (2004)
                Bookmark

                Author and article information

                Contributors
                Journal
                PeerJ
                PeerJ
                peerj
                peerj
                PeerJ
                PeerJ Inc. (San Francisco, USA )
                2167-8359
                29 August 2018
                2018
                : 6
                Affiliations
                [1 ]Envirometrix Ltd. , Wageningen, Gelderland, Netherlands
                [2 ]School of Agricultural, Forest and Food Sciences HAFL, Bern University of Applied Sciences BFH , Bern, Switzerland
                [3 ]Leibniz Institute for Prevention Research and Epidemiology—BIPS , Bremen, Germany
                [4 ]Soil Geography and Landscape group, Wageningen Agricultural University , Wageningen, Gelderland, Netherlands
                [5 ]52° North Initiative for Geospatial Open Source Software GmbH , Muenster, Germany
                5518
                10.7717/peerj.5518
                6119462
                ©2018 Hengl et al.

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.

                Funding
                Funded by: German Federal Ministry for Economic Affairs and Energy
                Award ID: 50EE1715C
                The contributions by Benedikt Gräler have been funded by the German Federal Ministry for Economic Affairs and Energy under grant agreement number 50EE1715C. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Biogeography
                Soil Science
                Computational Science
                Data Mining and Machine Learning
                Spatial and Geographic Information Science

                Comments

                Comment on this article