Application of RAGABP ANN Based on AM-MCMC in Water Quality Evaluation

The quality evaluation is a main matter in evaluation, conservancy and protection of water resources; it can provide scientific advice for protect and cure water resources deterioration and formulate water resources management plan. So water quality evaluation can also give guidance to sustain water utilization and to build a water-saving society. Back Propagation Artificial Neural Net based on Real coded Accelerating Genetic Algorithm and Markov Chain Monte Carlo which based on Adaptive Metropolis was used to evaluation water quality. RAGA was used to optimize topology, initialize weights and bias of BP; MCMC was adopted to produce enough simulated samples for training BP net and to consider fuzziness between adjacent grades of water quality. Adaptive Metropolis method was taken as a sampling method to improve sampling efficiency of MCMC. Results of study cases show RAGABP based on AM-MCMC improve convergence velocity more 20% than standard BP, and evaluation results of RAGABP are more objective, reasonable than that of single indicator method. Further more, the RAGABP based on AM-MCMC can be used to evaluate flood disaster loss, earthquake disaster loss and so on.