The present study is aimed at adsorptive removal of Mercury (Hg²⁺) using highly functionalized nanomaterials based on Graphene Oxide Zeolitic Imidazolate Framework composite (ZIF-67@GO). Solvothermal methodology was used to synthesize ZIF-67@GO composite. Synthesized compounds were confirmed by FTIR, SEM, PXRD and EDX analysis. The as-prepared ZIF-67@GO was tested as efficient adsorbent for effective removal of Mercury (Hg²⁺) from aquatic environment. The atomic adsorption spectrophotometer was used to monitor the process of adsorption of Hg⁺² on ZIF-67@GO. From the adsorption data, the maximum removal efficiency achieved was 91.1% using 10 mg amount of composite for 50 mL using 20 ppm Mercury (Hg²⁺) solution. Different parameters like pH, contact time, concentration, adsorption kinetics and isotherm were also examined to explore adsorption process. Adsorption data fitted well for Freundlich Model having R² value of 0.9925 than Langmuir Isotherm with R² value of 0.9238. Kinetics were rapid and excellently described via 2nd order model with R² = 0.99946 than 1st order model with R² value of 0.8836. Freundlich and pseudo 2nd order models validated that multilayer chemisorption occurs during adsorption process due to the presence of highly functionalized sites on ZIF-67@GO composite. The synthesized composite material has shown excellent reusability. Thus, water stable ZIF-67@GO composites can efficiently be used for Mercury (Hg²⁺) confiscation from water.

The adsorption of dyes using 39 adsorbents (16 kinds of agro-wastes) were modeled using random forest (RF), decision tree (DT), and gradient boosting (GB) models based on 350 sets of adsorption experimental data. In addition, the correlation between variables and their importance was applied. After comprehensive feature selection analysis, five important variables were selected from nine variables. The RF with the highest accuracy (R² = 0.9) was selected as the best model for prediction of adsorption capacity of agro-waste using the five selected variables. The results suggested that agro-waste characteristics (pore volume, surface area, agro-waste pH, and particle size) accounted for 50.7% contribution for adsorption efficiency. The pore volume and surface area are the most important influencing variables among the agro-waste characteristics, while the role of particle size was inconspicuous. The accurate ability of the developed models’ prediction could significantly reduce experimental screening efforts, such as predicting the dye removal efficiency of agro-waste activated carbon according to agro-waste characteristics. The relative importance of variables could provide a right direction for better treatments of dyes in the real wastewater.