Consequences of spatial structure in soil–geomorphic data on the results of machine learning models

References

• Abu-Mostafa YS, Magdon-Ismail M, Lin HT. 2012. Learning from data. United States: AMLBook.
   Google Scholar
• Angelini ME, Heuvelink GBM. 2018. Including spatial correlation in structural equation modelling of soil properties. Spatial Stat. 25:35–51. doi: 10.1016/j.spasta.2018.04.003.
   Web of Science ®Google Scholar
• Anselin L. 2002. Under the hood: issues in the specification and interpretation of spatial regression models. Agric Econ. 27(3):247–267. doi: 10.1111/j.1574-0862.2002.tb00120.x.
   Web of Science ®Google Scholar
• Behrens T, Schmidt K, MacMillan RA, Rossel RAV. 2018a. Multi-scale digital soil mapping with deep learning. Sci Rep. 8(1):15244. doi: 10.1038/s41598-018-33516-6.
   PubMedGoogle Scholar
• Behrens T, Schmidt K, Viscarra Rossel RA, Gries P, Scholten T, MacMillan R. 2018b. Spatial modelling with Euclidean distance fields and machine learning. Eur J Soil Sci. 69(5):757–770. doi: 10.1111/ejss.12687.
   Web of Science ®Google Scholar
• Behrens T, Schmidt K, MacMillan RA, Rossel RAV. 2018c. Multiscale contextual spatial modelling with the Gaussian scale space. Geoderma. 310:128–137. doi: 10.1016/j.geoderma.2017.09.015.
   Web of Science ®Google Scholar
• Bel L, Laurent JM, Bar-Hen A, Allard D, Cheddadi R. 2005. A spatial extension of CART: application to classification of ecological data. In: Renard P, Demougeot-Renard H, Froidevaux R, editors. Geostatistics for environmental applications. Berlin: Springer; p. 99–109.
   Google Scholar
• Bischl B, Lang M, Kotthoff L, Schiffner J, Richter J, Studerus E, Casalicchio G, Jones ZM. 2016. Mlr: Machine learning in R. J Mach Learn Res. 17:1–5.
   Web of Science ®Google Scholar
• Bivand RS, Pebesma E, Gómez-Rubio V. 2013. Applied spatial data analysis with R. New York, NY: Springer.
   Google Scholar
• Breiman L. 2001. Random forests. Mach Learn. 45(1):5–32. doi: 10.1023/A:1010933404324.
   Web of Science ®Google Scholar
• Brungard CW, Boettinger JL, Duniway MC, Wills SA, Edwards TC. 2015. Machine learning for predicting soil classes in three arid landscapes. Geoderma. 239–240:68–83. doi: 10.1016/j.geoderma.2014.09.019.
   Web of Science ®Google Scholar
• Burrough PA. 2001. GIS and geostatistics: essential partners for spatial analysis. Environ Ecol Stat. 8(4):361–377. doi: 10.1023/A:1012734519752.
   Web of Science ®Google Scholar
• Chang CC, Lin CJ. 2011. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2(3):1–27. doi: 10.1145/1961189.1961199.
   Web of Science ®Google Scholar
• Currit N. 2002. Inductive regression: overcoming OLS limitations with the general regression neural network. Comput Environ Urban Syst. 26(4):335–353. doi: 10.1016/S0198-9715(01)00045-X.
   Google Scholar
• Dormann CF, Elith J, Bacher S, Buchmann C, Carl G, Carré G, Marquéz JRG, Gruber B, Lafourcade B, Leitão PJ, et al. 2013. Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography. 36(1):27–46. doi: 10.1111/j.1600-0587.2012.07348.x.
   Web of Science ®Google Scholar
• Drucker H, Surges CJC, Kaufman L, Smola A, Vapnik V. 1997. Support vector regression machines. Adv Neural Inf Process Syst. 1:155–161.
   Google Scholar
• Ferraciolli MA, Bocca FF, Rodrigues LHA. 2019. Neglecting spatial autocorrelation causes underestimation of the error of sugarcane yield models. Comput Electron Agric. 161:233–240. doi: 10.1016/j.compag.2018.09.003.
   Web of Science ®Google Scholar
• Feurer M, Hutter F. 2019. Hyperparameter optimization. In: Hutter F, Kotthoff L, Vanschoren J, editors. Automated machine learning: methods, systems, challenges. The Springer series on challenges in machine learning. Cham: Springer International Publishing; p. 3–33. doi: 10.1007/978-3-030-05318-5_1.
   Google Scholar
• Fisher A, Rudin C, Dominici F. 2019. All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J Mach Learn Res. 20:1–81.
   Web of Science ®Google Scholar
• Gaspard G, Kim D, Chun Y. 2019. Residual spatial autocorrelation in macroecological and biogeographical modeling: a review. J Ecol Environ. 43:19. doi: 10.1186/s41610-019-0118-3.
   Google Scholar
• Georganos S, Grippa T, Niang Gadiaga A, Linard C, Lennert M, Vanhuysse S, Mboga N, Wolff E, Kalogirou S. 2021. Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling. Geocarto Int. 36(2):121–136. doi: 10.1080/10106049.2019.1595177.
   Web of Science ®Google Scholar
• Getis A, Griffith DA. 2002. Comparative spatial filtering in regression analysis. Geogr Anal. 34(2):130–140. doi: 10.1111/j.1538-4632.2002.tb01080.x.
   Web of Science ®Google Scholar
• Grekousis G. 2019. Artificial neural networks and deep learning in urban geography: a systematic review and meta-analysis. Comput Environ Urban Syst. 74:244–256. doi: 10.1016/j.compenvurbsys.2018.10.008.
   Web of Science ®Google Scholar
• Griffith DA. 2000. A linear regression solution to the spatial autocorrelation problem. J Geograph Syst. 2(2):141–156. doi: 10.1007/PL00011451.
   Google Scholar
• Griffith DA. 1996. Spatial autocorrelation and eigenfunctions of the geographic weights matrix accompanying geo-referenced data. Canadian Geographer. 40(4):351–367. doi: 10.1111/j.1541-0064.1996.tb00462.x.
   Web of Science ®Google Scholar
• Griffith DA. 2003. Spatial autocorrelation and spatial filtering: gaining understanding through theory and scientific visualization. Berlin: Springer-Verlag.
   Google Scholar
• Grömping U. 2009. Variable importance assessment in regression: linear regression versus random forest. Am Stat. 63(4):308–319. doi: 10.1198/tast.2009.08199.
   Web of Science ®Google Scholar
• Guo Z, Adhikari K, Chellasamy M, Greve MB, Owens PR, Greve MH. 2019. Selection of terrain attributes and its scale dependency on soil organic carbon prediction. Geoderma. 340:303–312. doi: 10.1016/j.geoderma.2019.01.023.
   Web of Science ®Google Scholar
• Gupta S, Lehmann P, Bonetti S, Papritz A, Or D. 2021. Global prediction of soil saturated hydraulic conductivity using random forest in a covariate-based geotransfer function (CoGTF) framework. J Adv Model Earth Syst. 13(4):e2020MS002242. doi: 10.1029/2020MS00224.
   Web of Science ®Google Scholar
• Guyon I, Weston J, Barnhill S, Vapnik V. 2002. Gene selection for cancer classification using support vector machines. Mach Learn. 46(1/3):389–422. doi: 10.1023/A:1012487302797.
   Web of Science ®Google Scholar
• Head ML, Holman L, Lanfear R, Kahn AT, Jennions MD. 2015. The extent and consequences of p-hacking in science. PLoS Biol. 13(3):e1002106. doi: 10.1371/journal.pbio.1002106.
   PubMed Web of Science ®Google Scholar
• Hengl T, Nussbaum M, Wright MN, Heuvelink GBM, Gräler B. 2018. Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ. 6:e5518. doi: 10.7717/peerj.5518.
   PubMed Web of Science ®Google Scholar
• Heung B, Ho HC, Zhang J, Knudby A, Bulmer CE, Schmidt MG. 2016. An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping. Geoderma. 265:62–77. doi: 10.1016/j.geoderma.2015.11.014.
   Web of Science ®Google Scholar
• Heuvelink GBM, Webster R. 2022. Spatial statistics and soil mapping: a blossoming partnership under pressure. Spatial Stat. 50:100639. doi: 10.1016/j.spasta.2022.100639.
   Web of Science ®Google Scholar
• Jiang Z, Li Y, Shekhar S, Rampi L, Knight J. 2017. Spatial ensemble learning for heterogeneous geographic data with class ambiguity: a summary of results. Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 23. p. 1–10. doi: 10.1145/3139958.3140044.
   Google Scholar
• Kanevski M, Timonin V, Pozdnukhov A. 2009. Machine learning for spatial environmental data: theory, applications, and software. Boca Raton: CRC Press LLC.
   Google Scholar
• Kaya F, Mishra G, Francaviglia R, Keshavarzi A. 2023. Combining digital covariates and machine learning models to predict the spatial variation of soil cation exchange capacity. Land. 12(4):819. doi: 10.3390/land12040819.
   Web of Science ®Google Scholar
• Khaledian Y, Miller BA. 2020. Selecting appropriate machine learning methods for digital soil mapping. Appl Math Modell. 81:401–418. doi: 10.1016/j.apm.2019.12.016.
   Web of Science ®Google Scholar
• Kim D. 2021. Predicting the magnitude of residual spatial autocorrelation in geographical ecology. Ecography. 44(7):1121–1130. doi: 10.1111/ecog.05403.
   Web of Science ®Google Scholar
• Kim D, Song I. 2021. Predicting model improvement by accounting for spatial autocorrelation: a socio-economic perspective. Prof Geogr. 73(1):131–149. doi: 10.1080/00330124.2020.1812408.
   Web of Science ®Google Scholar
• Kim D, Hirmas DR, McEwan RW, Mueller TG, Park SJ, Šamonil P, Thompson JA, Wendroth O. 2016. Predicting the influence of multi-scale spatial autocorrelation on soil–landform modeling. Soil Sci Soc Am J. 80(2):409–419. doi: 10.2136/sssaj2015.10.0370.
   Web of Science ®Google Scholar
• Kim D, Šamonil P, Jeong G, Tejnecký V, Drábek O, Hruška J, Park SJ. 2019. Incorporation of spatial autocorrelation improves soil–landform modeling at A and B horizons. Catena. 183:104226. doi: 10.1016/j.catena.2019.104226.
   Web of Science ®Google Scholar
• Kühn I, Dormann CF. 2012. Less than eight (and a half) misconceptions of spatial analysis. J Biogeogr. 39(5):995–998. doi: 10.1111/j.1365-2699.2012.02707.x.
   Web of Science ®Google Scholar
• Kuhn M, Johnson K. 2013. Applied predictive modeling. New York, NY: Springer.
   Google Scholar
• Lark RM. 2012. Towards soil geostatistics. Spatial Stat. 1:92–99. doi: 10.1016/j.spasta.2012.02.001.
   Web of Science ®Google Scholar
• Legendre P. 1993. Spatial autocorrelation: trouble or new paradigm? Ecology. 74(6):1659–1673. doi: 10.2307/1939924.
   Web of Science ®Google Scholar
• Makungwe M, Chabala LM, Chishala BH, Lark RM. 2021. Performance of linear mixed models and random forests for spatial prediction of soil pH. Geoderma. 397:115079. doi: 10.1016/j.geoderma.2021.115079.
   Web of Science ®Google Scholar
• Ma Y, Minasny B, Malone BP, McBratney AB. 2019. Pedology and digital soil mapping (DSM). Eur J Soil Sci. 70(2):216–235. doi: 10.1111/ejss.12790.
   Web of Science ®Google Scholar
• McBratney AB, Santos MLM, Minasny B. 2003. On digital soil mapping. Geoderma. 117(1–2):3–52. doi: 10.1016/S0016-7061(03)00223-4.
   Web of Science ®Google Scholar
• Miralha L, Kim D. 2018. Accounting for and predicting the influence of spatial autocorrelation in water quality modeling. IJGI. 7(2):64. doi: 10.3390/ijgi7020064.
   Google Scholar
• Molnar C. 2022. Interpretable machine learning. Lulu. com. Victoria, BC: Leanpub.
   Google Scholar
• Möller M, Zepp S, Wiesmeier M, Gerighausen H, Heiden U. 2022. Scale-specific prediction of topsoil organic carbon contents using terrain attributes and SCMaP soil reflectance composites. Remote Sens. 14(10):2295. doi: 10.3390/rs14102295.
   Google Scholar
• Montgomery DC, Peck EA, Vining GG. 2012. Introduction to linear regression analysis. Hoboken, NJ: Wiley.
   Google Scholar
• Nussbaum M, Spiess K, Baltensweiler A, Grob U, Keller A, Greiner L, Schaepman ME, Papritz A. 2018. Evaluation of digital soil mapping approaches with large sets of environmental covariates. Soil. 4(1):1–22. doi: 10.5194/soil-4-1-2018.
   Web of Science ®Google Scholar
• Nikparvar B, Thill JC. 2021. Machine learning of spatial data. IJGI. 10(9):600. doi: 10.3390/ijgi10090600.
   Google Scholar
• O’Callaghan JF, Mark DM. 1984. The extraction of drainage networks from digital elevation data. Comput Vision Graphics Image Process. 28(3):323–344. doi: 10.1016/S0734-189X(84)80011-0.
   Google Scholar
• R Core Team. 2021. R: the R Project for statistical computing.
   Google Scholar
• Schölkopf B, Smola AJ, Williamson RC, Bartlett PL. 2000. New support vector algorithms. Neural Comput. 12(5):1207–1245. doi: 10.1162/089976600300015565.
   PubMed Web of Science ®Google Scholar
• Schölkopf B, Smola AJ. 2001. Learning with kernels: support vector machines, regularization, optimization, and beyond. Cambridge, MA: MIT Press.
   Google Scholar
• Schratz P, Muenchow J, Iturritxa E, Richter J, Brenning A. 2019. Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data. Ecol Modell. 406:109–120. doi: 10.1016/j.ecolmodel.2019.06.002.
   Web of Science ®Google Scholar
• Sekulić A, Kilibarda M, Heuvelink GBM, Nikolić M, Bajat B. 2020. Random forest spatial interpolation. Remote Sens. 12(10):1687. doi: 10.3390/rs12101687.
   Google Scholar
• Sergeev AP, Buevich AG, Baglaeva EM, Shichkin AV. 2019. Combining spatial autocorrelation with machine learning increases prediction accuracy of soil heavy metals. Catena. 174:425–435. doi: 10.1016/j.catena.2018.11.037.
   Web of Science ®Google Scholar
• Shukla G, Garg RD, Srivastava HS, Garg PK. 2018. An effective implementation and assessment of a random forest classifier as a soil spatial predictive model. Int J Remote Sens. 39(8):2637–2669. doi: 10.1080/01431161.2018.1430399.
   Web of Science ®Google Scholar
• Sinha P, Gaughan AE, Stevens FR, Nieves JJ, Sorichetta A, Tatem AJ. 2019. Assessing the spatial sensitivity of a random forest model: application in gridded population modeling. Comput Environ Urban Syst. 75:132–145. doi: 10.1016/j.compenvurbsys.2019.01.006.
   Web of Science ®Google Scholar
• Svetnik V, Liaw A, Tong C, Wang T. 2004. Application of Breiman’s random forest to modeling structure-activity relationships of pharmaceutical molecules [series title: lecture notes in computer science]. In: T Kanade, J Kittler, JM Kleinberg, F Mattern, JC Mitchell, M Naor, O Nierstrasz, C Pandu Rangan, B Steffen, M Sudan, D Terzopoulos, D Tygar, MY Vardi, G Weikum, F Roli, J Kittler, T Windeatt, editors, Multiple classifier systems. Berlin Heidelberg: Springer; p. 334–343. doi: 10.1007/978-3-540-25966-4_33.
   Google Scholar
• Tiefelsdorf M, Griffith DA. 2007. Semiparametric filtering of spatial autocorrelation: the eigenvector approach. Environ Plan A. 39(5):1193–1221. doi: 10.1068/a37378.
   Web of Science ®Google Scholar
• van der Westhuizen S, Heuvelink GBM, Hofmeyr DP, Poggio L. 2022. Measurement error-filtered machine learning in digital soil mapping. Spatial Stat. 47:100572. doi: 10.1016/j.spasta.2021.100572.
   Web of Science ®Google Scholar
• Venables WN, Ripley BD. 2002. Modern applied statistics with S. New York, NY: Springer.
   Google Scholar
• Wadoux AMJC. 2019. Using deep learning for multivariate mapping of soil with quantified uncertainty. Geoderma. 351:59–70. doi: 10.1016/j.geoderma.2019.05.012.
   Web of Science ®Google Scholar
• Wadoux AMJC, Minasny B, McBratney AB. 2020. Machine learning for digital soil mapping: applications, challenges and suggested solutions. Earth-Sci Rev. 210:103359. doi: 10.1016/j.earscirev.2020.103359.
   Web of Science ®Google Scholar
• Wadoux AMJC, Padarian J, Minasny B. 2019. Multi-source data integration for soil mapping using deep learning. Soil. 5(1):107–119. doi: 10.5194/soil-5-107-2019.
   Web of Science ®Google Scholar
• Wright MN, Ziegler A. 2017. ranger: a fast implementation of random forests for high dimensional data in C++ and R. J Stat Soft. 77(1):17. doi: 10.18637/jss.v077.i01.
   Web of Science ®Google Scholar
• Zevenbergen LW, Thorne CR. 1987. Quantitative analysis of land surface topography. Earth Surf Process Landforms. 12(1):47–56. doi: 10.1002/esp.3290120107.
   Web of Science ®Google Scholar