Abstarct: In the present work, for the first time, a new carboxylate-functionalized walnut shell was prepared via esterification of walnut shell with meldrum’s acid. The characterization of the carboxylate-functionalized walnut shell (CFWNS) by different techniques approved that carboxylic groups were introduced onto the surface of walnut shell. The performance of the modified adsorbent was studied for the removal of Pb2+ ions from aqueous solution in a batch adsorption system. The analysis data show that the Langmuire isotherm can satisfactorily explain the equilibrium data, and the maximum adsorption capacity for Pb2+ ions was found to be 192.3 mg g-1 at 0.8 g L-1 of the adsorbent, pH 5.5 and temprature of 298 K. This value is much higher than those reported by some other researchers. The kinetic studies revealed that this bio-sorption is a chemisorption process. Two models, namely Artificial Neural Network (ANN) and multiple linear regression (MLR) model were used to construct an empirical model for prediction the removal percentage of Pb2+ ions under different experimental coditions. These models were validated using a test set of 20 data. A comparison between the developed models shows that the ANN model is able to predict the removal percentage of Pb2+ ions more accurately. Consequently, the ANN model could be applied for the designing of an automated wastewater remediation plan. Also it has to be noted that the used CFWNS was recovered using 2Na-EDTA, and employed for the removal of Pb2+ ions from aqueous solutions.