One of the greatest challenges for aircraft maintenance is localized corrosion induced fatigue and cracking, which is induced by aluminum alloys susceptibility to aggressive environment. Although pit growth kinetics was thoroughly investigated and nicely modeled by power law, the uniform corrosion impact on pit growth kinetics was ignored in the past, and therefore resulted in pit growth deviation from the ideal power law as indicated in a preliminary result. Uniform corrosion dissolved the surface material and thus induced reference plane recession and pit depth reduction. This non-trivial difference was proved to have a significant influence on pit growth modelling especially in high pH conditions. In this work, temperature and pH influence on uniform corrosion of 2024-T3, 6061-T6, and 7075-T6 aluminum alloys were reported through the free immersion test method. Extensive results performed in various pH (3 to 10), chloride concentration (0.01M to 1M), and temperatures (20⁰C to 80⁰C) from up to 1 month is reported to mimic real applications. A comparison with the weight loss experiment was demonstrated to provide a quantitative significance of pitting and uniform corrosion, respectively. Severity of uniform corrosion were measured and versus various pH, temperature, time, and chloride concentration. The key finding in this work was that uniform corrosion rate is oxygen-dependent with a dynamic influence of passivation. Therefore, to identify the contribution of oxygen and passivation (as affected by pH and temperature), experimental approaches including electrochemical impedance spectroscopy (EIS) and cathodic polarization were utilized. Furthermore, TEM images and electron diffraction were performed to assess the structure and morphology of the protective corrosion product driven by temperature. In addition, the Artificial Neural Network (ANN) modelling was employed to analyze the data obtained. A statistic-based model is able to recognize corrosion behavior pattern versus various conditions, therefore a prediction model can be generated according to the environmental inputs. In summary, the ultimate goal of this study is to suggest an effective maintenance for high value DoD and industrial assets according to an experiment-based prediction model and to understand the impact of different environmental parameters. In this study, a successful uniform corrosion predictive model was developed within specified conditions, which has a significant modification over pit depth growth. Therefore, a predictive model based on lab experimental data is applicable and an efficient low cost maintenance is doable.