The application of the fossil diesel in engines is detrimental to the humans as they pollute the environment. Currently, all-embracing research is in progression to discover an alternative fuel and improve its quality. The nanoparticles are one of the current technologies that is beneficial for upgrading the fuel properties. Among nanoparticles, GQD stands out and offers a plethora of technical advantages for future uses as an additive to reduce emission profiles. The suitability of newly created additives, such as GQD, to improve the characteristics of IC engines driven by alternative fuels was highlighted. GQD, as a novel and intriguing zero-dimensional material of the carbon family, has been actively researched in order to generate inexpensive and environmentally friendly materials. There is a dearth of orderly investigations ANN generated modeling of diesel engine's efficacy of IC engines fueled with ternary blends of GQD, waste fish oil biodiesel (WOFB), and diesel fuel in the existing works. The correlation between engine speed (1800, 2100, and 2400 rpm), GQD+ethanol blend (2-8 vol. conc.), and WFOB and diesel fuel mixture and engine performance indicators (power, torque, braking specific fuel consumption) and emission characteristics (CO, CO2, UHC, NOx) was modelled using ANN. Finally, the results showed that adding GQD+E to 10%WOFB increases braking power and engine torque, with B10 + E6 + GQD45 fuel having the maximum brake power and engine torque. The average difference in braking power and engine torque between the B10 + E6 + GQD45 gasoline and the D100 is 13.84% and 16.95%, respectively. Adding GQD+E to 10% WOFB also lowered BSFC, UHC, CO, and NO emissions, with B10 + E6 + GQD45 fuel having the lowest UHC and CO emissions.In comparison to D100, UHC, CO, and CO2 dropped by 21.70, 24.67, and 26.38%, respectively. As a result, adding GQD+E to 10% WOFB increases engine performance while lowering emissions. Also, the results for ANN showed that, both Pearson’s correlation coefficient (0.96, 0.71, 0.95, 0.92, 0.84 and 0.91 for CO2, NO, UHC, BSFC, brake power and engine torque, respectively) and RMSE (0.0295, 0.0227, 1.6545, 1.5046, 11.2515, 0.1557 and 0.3913 for CO2, NO, UHC, BSFC, brake power and engine torque respectively) for either parameter traits show the efficacy of ANN as observed from the predicted values being close to the experimental values.