The paper has proposed a novel self-organizing-mapping algorithm based on data-field model for dual clustering of large-scale and high dimensional data in Wireless Sensor Networks(WSNs) in order to has good performance in cluster problems. The method maps the WSNs data from data space to the appropriate potential space in data field

which measures the interactions of the elements in large-scale and high dimensional data by taking probabilistic entropy of data distribution in the WSNs as the mass of data field

thus generating a two-dimension data field. Then

by employing distribution features of the potential center and the equipotential lines

without significantly increasing the time complexity

the good clustering result is obtained by minimum potential difference determination method.The comparing experiments on the synthetic datasets demonstrate the effectiveness of the algorithm. Experimental results show that the proposed method improves the clustering effect and has exact clustering result compared with other dual clustering algorithm

i.e. ICC and DFCM

and it has good scalability.