A technique was developed to evaluate the adsorption of RHB from wastewater. On this point, the properties of the produced material were evaluated and explained in Sect. 1.5 . The study examined various factors: pH, concentration, contact time, adsorbent dosage, and temperature. These factors served as input data, while the output data was based on RHB removal efficiency. To forecast and optimize RHB adsorption, response surface methodology/central composite design (RSM-CCD), artificial neural network (ANN), and adaptive neuron-fuzzy inference system (ANFIS) models were used. The relevance of these models was also assessed using statistical metrics. The ANN and ANFIS models used 70% of the data for training, 15% for validation, and 15% for testing. Based on the RSM-CCD results, the process parameters were optimized for a pH of 7, a contact period of 55 min, an adsorbent concentration of 20 g/L, a temperature of 40 °C, and an RHB concentration of 100 mg/L. However, an ideally trained neural network has three phases: training, testing, and validation, with R2 values of 1, 0.96837, and 0.96146, respectively. The statistical results showed that the ANFIS strategy outperformed the RSM and ANN model methods. The results from actual water samples also indicated that the synthesized GCCH was highly effective in real-world treatment operations. Overall, the data demonstrate that the proposed adsorbent is both inexpensive and effective for the adsorptive removal of dyes from polluted waters.