Using Google's cloud-based platform for digital soil mapping

A digital soil mapping exercise over a large extent and at a high resolution is a computationally expensive procedure. It may take days or weeks to obtain the final maps and to visually evaluate the prediction models when using a desktop workstation. To increase the speed of time-consuming procedures, the use of supercomputers is a common practice. GoogleTM has developed a product specifically designed for mapping purposes (Earth Engine), allowing users to take advantage of its computing power and the mobility of a cloud-based solution. In this work, we explore the feasibility of using this platform for digital soil mapping by presenting two soil mapping examples over the contiguous United States. We also discuss the advantages and limitations of this platform at its current development stage, and potential improvements towards a fully functional cloud-based soil mapping platform. HighlightsIt is possible to include the platform as part of a digital soil mapping workflow.Map generation is 40-100 times faster compared with traditional digital soil mapping.To be a complete solution, implementation of geostatistical methodologies is needed.We encourage researches to participate during the beta-testing period to improve it.

[1]  Irina Rish,et al.  An empirical study of the naive Bayes classifier , 2001 .

[2]  Bruce W. Pengra,et al.  Distribution and dynamics of mangrove forests of South Asia. , 2015, Journal of environmental management.

[3]  Alex B. McBratney,et al.  Spatial prediction of soil properties from landform attributes derived from a digital elevation model , 1994 .

[4]  Siani Pearson,et al.  Privacy, Security and Trust Issues Arising from Cloud Computing , 2010, 2010 IEEE Second International Conference on Cloud Computing Technology and Science.

[5]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[6]  Budiman Minasny,et al.  Analysis and prediction of soil properties using local regression-kriging , 2012 .

[7]  D. Böhning.  Multinomial logistic regression algorithm , 1992 .

[8]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[9]  Dean B. Gesch,et al.  TECHNIQUES FOR DEVELOPMENT OF GLOBAL I-KILOMETER DIGITAL ELEVATION MODELS , 2003 .

[10]  G. Heuvelink,et al.  Implications of digital soil mapping for soil information systems , 2010 .

[11]  Amir AghaKouchak,et al.  A satellite-based global landslide model , 2013 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  R. Tibshirani,et al.  An Introduction to the Bootstrap , 1995 .

[14]  Budiman Minasny,et al.  On digital soil mapping , 2003 .

[15]  R. Webster,et al.  Optimal interpolation and isarithmic mapping of soil properties: I The semi‐variogram and punctual kriging , 1980, European Journal of Soil Science.

[16]  Budiman Minasny,et al.  The evolving methodology for global soil mapping , 2014 .

[17]  G. Heuvelink,et al.  SoilGrids1km — Global Soil Information Based on Automated Mapping , 2014, PloS one.

[18]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[19]  M. Ek,et al.  Continental‐scale water and energy flux analysis and validation for North American Land Data Assimilation System project phase 2 (NLDAS‐2): 2. Validation of model‐simulated streamflow , 2012 .

[20]  K. Mo,et al.  Continental-scale water and energy flux analysis and validation for the North American Land Data Assimilation System project phase 2 (NLDAS-2): 1. Intercomparison and application of model products , 2012 .

[21]  Huseyin Polat,et al.  Privacy-preserving kriging interpolation on partitioned data , 2014, Knowl. Based Syst..

[22]  Chris Clifton,et al.  Defining Privacy for Data Mining , 2002 .

[23]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[24]  Budiman Minasny,et al.  Estimating Pedotransfer Function Prediction Limits Using Fuzzy k-Means with Extragrades , 2010 .

[25]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[26]  W. Jetz,et al.  Systematic land cover bias in Collection 5 MODIS cloud mask and derived products — A global overview , 2014 .

[27]  Subhransu Maji,et al.  Classification using intersection kernel support vector machines is efficient , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Koby Crammer,et al.  Online Passive-Aggressive Algorithms , 2003, J. Mach. Learn. Res..

[29]  C. Kwak,et al.  Multinomial Logistic Regression , 2002, Nursing research.

[30]  Nicholas R. Chrisman,et al.  History of GIS , 2016 .

[31]  B. Henderson,et al.  Australia-wide predictions of soil properties using decision trees , 2005 .

[32]  T. C. W. Landgrebe,et al.  Relationships between palaeogeography and opal occurrence in Australia: A data-mining approach , 2013, Comput. Geosci..

[33]  R. Webster,et al.  Optimal interpolation and isarithmic mapping of soil properties. II. Block kriging. , 1980 .

[34]  Alex B. McBratney,et al.  Modelling soil attribute depth functions with equal-area quadratic smoothing splines , 1999 .

[35]  T. M. Burgess,et al.  Optimal interpolation and isarithmic mapping of soil properties. III. Changing drift and universal kriging. , 1980 .

[36]  K. Verdin,et al.  New Global Hydrography Derived From Spaceborne Elevation Data , 2008 .

[37]  Andrew Jarvis,et al.  Hole-filled SRTM for the globe Version 4 , 2008 .

[38]  Michael J. Oimoen,et al.  The National Elevation Dataset , 2002 .

[39]  J. Abatzoglou.  Development of gridded surface meteorological data for ecological applications and modelling , 2013 .

[40]  Ashbindu Singh,et al.  Status and distribution of mangrove forests of the world using earth observation satellite data , 2011 .

[41]  Budiman Minasny,et al.  Constructing a soil class map of Denmark based on the FAO legend using digital techniques , 2014 .