Waterflood or water injection is implemented in oil field to maintain reservoir pressure and improve oil production. Since the wells can produce different fluids (i.e. oil, water and gas), the produced water is usually injected back into the reservoir to sweep the oil and improve oil recovery. Production optimization is applied in waterflood reservoir using a single objective function or multi-objective function of two conflicting functions. The multi-objective optimization finds a set of non-dominated solutions known as Pareto optimal solutions. This study focuses in investigating different multi-objective functions and the development of hybrid algorithms applied in different benchmark test models and real-oil field sector models developed by water injection. Multi-objective optimization using the Non-dominated Sorting Genetic Algorithm, second version (NSGA-II) has been applied in this study to investigate different multi-objective functions. The multi-objective optimization studies using NSGA-II algorithm are applied in Brugge field benchmark model and real-field sector models. Hybrid MODE with the dynamic-random local search algorithm developed for chemical process applications was also applied in a real-field sector model and it showed a 70% improvement in the convergence compared to NSGA II solution. Two new hybrid approaches are introduced using evolutionary neural network (EvoNN) and bi-objective genetic programming (BioGP) as guiding input into NSGA-II algorithm to improve the convergence and diversity of the Pareto front solutions. The two hybrid methods are validated and tested using constrained and unconstrained benchmark test problems and compared with NSGA-II algorithm. Different performance metrics are used to compare and validate the hybridization techniques. Both the EvoNN guided NSGA-II algorithm and the BioGP guided NSGA-II algorithm could converge and match the Pareto front solutions for the constrained and un-constrained test problems with overall better performance metrics compared to NSGA-II algorithm. The evolutionary neural-network data-driven model is built and trained using initial solutions generated by NSGA-II optimization coupled with the reservoir simulation model. Evolutionary optimization incorporated in the EvoNN strategy is applied in the trained data-driven model to generate the Pareto optimal solution, which is then used as a guiding input into NSGA-II optimization. The described method is applied in two case studies (i.e. Brugge field model & water injection pattern model) to maximize total oil production and minimize total water production from the field. The decision variables for the two case-studies are the bottom hole pressure (BHP) for the producers and the water injection (qwi) for the injectors. The Pareto optimal solutions obtained with data-driven model guided NSGA-II in both models show improvement in convergence and diversity of the solution. The convergence to the Pareto optimal solution has improved by 9% for case-1 (i.e. Brugge field) and by 43% for case-2 (i.e. water injection pattern model) compared to NSGA-II algorithm. In addition, the Pareto optimal solution obtained by the proposed hybridization has shown improvement in the water-oil ratio (WOR) up to 6% in the Brugge field and up to 97% in the water injection pattern model compared to NSGA II algorithm. This improvement can lead to wide applications in using evolutionary optimizations in real field simulation models at acceptable computation time. Two case studies; one with Brugge field using different objective functions and second with real field sector model are also used to validate the novel hybrid optimization technique that combines the NSGA-II and evolutionary neural network (EvoNN) methods The benchmark model for the Brugge field is used for the first optimization study, with the two distinct objective functions of maximizing short-term net present value (NPVS) and long-term NPV (NPVL). In the second research study, a sector model of a real oil field in the Middle East that was developed by waterflooding in order to optimize cumulative oil gain and reduce cumulative water production is used. The decision variables employed in the two studies are the bottom-hole pressure (BHP) for the producers and the water injection rates (qwi) for the injectors. The real field sector model is run for ten years with twenty time steps and has four producers and three injectors. The hybrid approach of using EvoNN guided NSGA-II resulted in a 70% improvement in the convergence and the computation demand for the Brugge field model. For the real field sector model, EvoNN guided NSGA-II algorithm resulted in a better convergence obtained at all generations compared to the NSGA-II algorithm solution. The maximum total oil production determined by EvoNN guided NSGA-II is 550.6×103 m3 compared to 522×103 m3 by NSGA-II. Water oil ratio (WOR) is reduced with lower water production obtained by the EvoNN guided NSGA-II algorithm compared to the NSGA-II algorithm. The best optimal solution from the EvoNN guided NSGA-II optimization for the real field sector is determined by the net flow method (NFM) at 521.25×103m3 oil and 5208.6×103m3 water. A hybrid method of using the bi-objective genetic programming (BioGP) algorithm as guiding input into NSGA-II optimization is applied in two case studies; the Brugge field benchmark model and a real-field sector model of a Middle Eastern oil field developed with waterflood. The two conflictive objective functions defined for both case-studies are maximizing cumulative oil production and minimizing cumulative water production. The decision variables are defined as bottom-hole pressure (BHP) for the producers and injection rate (qwi) for the injectors at each time-step. The Pareto front solution obtained by the proposed hybrid approach of using BioGP guided NSGA-II algorithm is converging at generation 50 to the NSGA-II solution at generation 100 with better diversity, which implies 50% improvement in computational efficiency. The Pareto front solutions obtained by BioGP guided NSGA-II algorithm at different generations have better convergence and diversity compared to the Pareto solution obtained by NSGA-II algorithm only. The Pareto optimal solutions produced by the proposed EvoNN guided NSGA-II algorithm and the proposed BioGP guided NSGA-II algorithm will provide the decision maker multiple optimum options for controlling the production and injection of the wells in the oil field development depending on the needs and operational variables.