Data mining with agricultural soil databases is a relatively young research area. In the agricultural field, the determination of the soil category mainly depends on the atmospheric conditions and the different characteristics of the soil. Classification as an essential data mining technique used to develop models describing different classes of soil. Such analysis can provide us with a comprehensive understanding of various soil databases in general. In our study, we proposed a new technique based on Neuro-fuzzy classification and applied it to large soil databases to discover significant relationships. We used our technique for three benchmark datasets from the UCI machine learning repository for land categorization and they were Statlog (Landsat Satellite), Covertype and 3 datasets. Our goal was to develop an efficient classification model with the proposed method and, then, compare its performance with two well-known supervised classification algorithms Multilayer Perceptron and Support Vector Machine. We estimated the performance of these classification techniques in terms of different evaluation measures such as accuracy, Kappa statistic, true positive rate, false positive rate, precision, recall and F-measure. The proposed technique had an accuracy of 99.4% with the Statlog dataset, 97.7% with the Covertype dataset, and 90% with dataset 3; and in every respect, it performed better than the Multilayer Perceptron and Support Vector Machine algorithms. Data mining is about extracting interesting patterns that represent knowledge from real-world databases. Software applications related to data mining include various methodologies developed by both commercial and research organizations. Different data mining techniques used for... half of the paper ......Combines the human logical reasoning of fuzzy-based systems with the learning and connection structure of ANNs using fuzzy set and language model based approaches. In our work, we proposed a new Neuro-fuzzy based classification method for soil data mining. We apply our method to three benchmark datasets from the UCI machine learning repository for soil classification, and then compare its performance with MLP- and SVM-based classification models. This research study is organized as follows: Section 2 includes related works done in this field; Section 3 describes our proposed Neuro-fuzzy classification based method. Section 4 explains the methodology in terms of our proposed neuro-fuzzy method, MLP and SVM. Section 5 discusses the classification performance analysis and results; and Section 6 is reserved for the conclusion.