Gambling with randomness: the use of pseudo-random number generators in GIS

Analyses within the field of GIS are increasingly applying stochastic methods and systems that make use of pseudo-random number generators (PRNGs). Examples include Monte Carlo techniques, dynamic modelling, stochastic simulation, artificial life and simulated data development. PRNGs have inherent biases, and this will in turn bias any analyses using them. Therefore, the validity of stochastic analyses is reliant on the PRNG employed. Despite this, the effect of PRNGs in spatial analyses has never been completely explored, particularly a comparison of different PRNGs. Exacerbating the problem is that GIS articles applying Monte Carlo or other stochastic methods rarely report which PRNG is employed. It thus appears likely that GIS researchers rarely, if ever, check the suitability of the PRNG employed for their analyses or simulations. This paper presents a discussion of some of the characteristics of PRNGs and specific issues from a geospatial standpoint, including a demonstration of the differences in the results of a Monte Carlo analysis obtained using two different PRNGs. It then makes recommendations for the application of PRNGs in spatial analyses, including recommending specific PRNGs that have attributes appropriate for geospatial analysis. The paper concludes with a call for more research into the application of PRNGs to spatial analyses to fully understand the impact of biases, especially before they are routinely used in the wider spatial analysis community.

[1]  Pierre L'Ecuyer,et al.  Good Parameters and Implementations for Combined Multiple Recursive Random Number Generators , 1999, Oper. Res..

[2]  Jean-François Cordeau,et al.  Close-Point Spatial Tests and Their Application to Random Number Generators , 2000, Oper. Res..

[3]  A. De Matteis,et al.  Long-range correlations in linear and nonlinear random number generators , 1990, Parallel Comput..

[4]  T. Barry.  Recommendations on the Testing and Use of Pseudo‐Random Number Generators Used in Monte Carlo Analysis for Risk Assessment , 1995 .

[5]  Carter Bays,et al.  A review of portable random number generators , 1992 .

[6]  Karl Entacher,et al.  On the CRAY-System Random Number Generator , 1999, Simul..

[7]  William H. Press,et al.  Numerical Recipes in FORTRAN - The Art of Scientific Computing, 2nd Edition , 1987 .

[8]  J. Fairfield,et al.  Drainage networks from grid digital elevation models , 1991 .

[9]  Gerard B. M. Heuvelink,et al.  Error Propagation in Cartographic Modelling Using Boolean Logic and Continuous Classification , 1993, Int. J. Geogr. Inf. Sci..

[10]  David H. Douglas,et al.  Detection of Surface-Specific Points by Local Parallel Processing of Discrete Terrain Elevation Data , 1975 .

[11]  William H. Press,et al.  Book-Review - Numerical Recipes in Pascal - the Art of Scientific Computing , 1989 .

[12]  Peter A. Burrough,et al.  High-resolution landform classification using fuzzy k-means , 2000, Fuzzy Sets Syst..

[13]  Pierre Goovaerts,et al.  Estimation or simulation of soil properties? An optimization problem with conflicting criteria , 2000 .

[14]  P. Prescott,et al.  Monte Carlo Methods , 1964, Computational Statistical Physics.

[15]  R. Wikramaratna.  ACORN-A new method for generating sequences of uniformly distributed Pseudo-random Numbers , 1989 .

[16]  Erik Næset.  Effects of Delineation Errors in Forest Stand Boundaries on Estimated Area and Timber Volumes , 1999 .

[17]  Pierre L'Ecuyer,et al.  A random number generator based on the combination of four LCGs , 1997 .

[18]  C. Mooney,et al.  Monte Carlo Simulation , 1997 .

[19]  George Marsaglia,et al.  Some portable very-long-period random number generators , 1994 .

[20]  Pierre L'Ecuyer,et al.  Efficient and portable combined random number generators , 1988, CACM.

[21]  Edzer Pebesma,et al.  GSTAT: a program for geostatistical modelling, prediction and simulation , 1998 .

[22]  R. M. Lark,et al.  Regression analysis with spatially autocorrelated error: simulation studies and application to mapping of soil organic matter , 2000, Int. J. Geogr. Inf. Sci..

[23]  J. R. Heringa,et al.  Simulation of a directed random-walk model the effect of pseudo-random-number correlations , 1996, cond-mat/9612227.

[24]  Alan M. Ferrenberg,et al.  Monte Carlo simulations: Hidden errors from "good" random number generators. , 1992, Physical review letters.

[25]  István Deák,et al.  Random Number Generators and Simulation , 1990 .

[26]  Makoto Matsumoto,et al.  Twisted GFSR generators II , 1994, TOMC.

[27]  Harald Niederreiter,et al.  Random number generation and Quasi-Monte Carlo methods , 1992, CBMS-NSF regional conference series in applied mathematics.

[28]  P. L'Ecuyer,et al.  Fast combined multiple recursive generators with multipliers of the form a=/spl plusmn/2/sup q//spl plusmn/2/sup r/ , 2000, 2000 Winter Simulation Conference Proceedings (Cat. No.00CH37165).

[29]  Donald Ervin Knuth,et al.  The Art of Computer Programming , 1968 .

[30]  Randall E. Schumacker,et al.  Random-Number Generator Validity in Simulation Studies: An Investigation of Normality , 1998 .

[31]  P. Kyriakidis,et al.  Error in a USGS 30-meter digital elevation model and its impact on terrain modeling , 2000 .

[32]  J. Hammersley,et al.  Monte Carlo Methods , 1965 .

[33]  P. Burrough,et al.  Principles of geographical information systems , 1998 .

[34]  Pierre L'Ecuyer,et al.  Fast combined multiple recursive generators with multipliers of the form a = ±2q ±2r , 2000, WSC '00.

[35]  P. Moore.  A Million Random Digits with 100,000 Normal Deviates. , 1955 .

[36]  Stan Openshaw,et al.  Learning to live with errors in spatial databases , 1989 .

[37]  Ling Bian,et al.  Comparing Effects of Aggregation Methods on Statistical and Spatial Properties of Simulated Spatial Data , 1999 .

[38]  P. Hellekalek.  Good random number generators are (not so) easy to find , 1998 .

[39]  Takuji Nishimura,et al.  Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator , 1998, TOMC.

[40]  M. Charlton,et al.  Quantitative geography : perspectives on spatial data analysis by , 2001 .

[41]  Pierre L'Ecuyer,et al.  Combined Multiple Recursive Random Number Generators , 1995, Oper. Res..

[42]  Philip C. Emmi,et al.  A Monte Carlo Simulation of Error Propagation in a GIS-Based Assessment of Seismic Risk , 1995, Int. J. Geogr. Inf. Sci..

[43]  K. Holmesa,et al.  Error in a USGS 30-meter digital elevation model and its impact on terrain modeling , 2000 .

[44]  P. Goovaerts.  Geostatistics in soil science: state-of-the-art and perspectives , 1999 .

[45]  Ana Proykova,et al.  How to improve a random number generator , 2000 .

[46]  Brian D. Ripley,et al.  Thoughts on pseudorandom number generators , 1990 .

[47]  Pierre L'Ecuyer,et al.  On the performance of birthday spacings tests with certain families of random number generators , 2001 .

[48]  L'EcuyerPierre,et al.  Beware of linear congruential generators with multipliers of the form a = 2q 2r , 1999 .

[49]  Pierre L'Ecuyer,et al.  Beware of linear congruential generators with multipliers of the form a = ±2q ±2r , 1999, TOMS.

[50]  Donald Ervin Knuth,et al.  The Art of Computer Programming, Volume II: Seminumerical Algorithms , 1970 .

[51]  S. K. Park,et al.  Random number generators: good ones are hard to find , 1988, CACM.