Well-logging is one of the most useful and vital sources of information for development of reservoirs throughout their life span. Access to well-logging for all wells or at all intervals is impossible mainly due to Human error, high costs, field operating conditions, or lack of access to special logs for older field wells. Therefore, low-cost and accurate methods play a vital role in estimation of logs. In the present study, a set of logs available in Geolog software were used to compare the performance of Artificial Neural Network (ANN) and multi-resolution graph-based clustering (MRGC) for estimating the photoelectric factor(PEF) and Stoneley wave velocity plots. 70% and 30% of data were used for model training and validation, respectively. Correlation coefficient (R2) of the Stoneley wave velocity estimated based on reality log was respectively 96 and 98% in ANN and MRGC methods and 82 and 95% based on PEF log. The results show the preference and high accuracy of the MRGC method for estimating of well plots.