Different studies show the advantages of atmospheric water harvesting (AWH) in different climates for irrigation purposes, especially in dry periods. Moreover, we used the advantages of multi-objective optimization to reformulation of support vector machines (SVMs) classification. Therefore, the main purpose of this study is to develop a multi-objective support vector machine classification algorithm for the estimation of the potential AWH using major geographic and topographic indicators. In this regard, in this study, the dataset of AWH in different climates and regions has been used for training the classification learning algorithm. The test of the model has been done by using data from 10 case studies and three features, including climate type, elevation, and distance to the coastline. The results of the developed model could estimate the potential and suitability of AWH, and the verification of the results confirmed the effectiveness of the proposed method.