Cloud MapReduce for particle filter-based data assimilation for wildfire spread simulation

MapReduce is a domain-independent programming model for processing data in a highly parallel fashion. With MapReduce, parallel computing can be automatically carried out in large-scale commodity machines. This paper presents a method that utilizes the parallel and distributed processing capability of Hadoop MapReduce for particle filter-based data assimilation in wildfire spread simulation. We parallelize the sampling and weight computation steps of the particle filtering algorithm based on the MapReduce programming model. Experiment results show that our approach significantly increases the performance of particle filter-based data assimilation.

[1]  Benjamin Moseley,et al.  Fast clustering using MapReduce , 2011, KDD.

[2]  Michael C. Schatz,et al.  Rapid parallel genome indexing with MapReduce , 2011, MapReduce '11.

[3]  Bernd Freisleben,et al.  Cloud MapReduce for Monte Carlo bootstrap applied to Metabolic Flux Analysis , 2013, Future Gener. Comput. Syst..

[4]  Xiaolin Hu,et al.  DEVS-FIRE: design and application of formal discrete event wildfire spread and suppression models , 2012, Simul..

[5]  Naga K. Govindaraju,et al.  Mars: A MapReduce Framework on graphics processors , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[6]  Xiaolin Hu,et al.  DEVS-FIRE: Towards an Integrated Simulation Environment for Surface Wildfire Spread and Containment , 2008, Simul..

[7]  Yi Pan,et al.  Parallel rough set based knowledge acquisition using MapReduce from big data , 2012, BigMine '12.

[8]  Lei Xing,et al.  Monte Carlo simulation of photon migration in a cloud computing environment with MapReduce. , 2011, Journal of biomedical optics.

[9]  Christoforos E. Kozyrakis,et al.  Evaluating MapReduce for Multi-core and Multiprocessor Systems , 2007, 2007 IEEE 13th International Symposium on High Performance Computer Architecture.

[10]  Jignesh M. Patel,et al.  A comparison of join algorithms for log processing in MaPreduce , 2010, SIGMOD Conference.

[11]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[12]  Xiaolin Hu,et al.  Data assimilation using sequential monte carlo methods in wildfire spread simulation , 2012, TOMC.

[13]  Geoffrey C. Fox,et al.  Twister: a runtime for iterative MapReduce , 2010, HPDC '10.