In China, about one-third of the land area is over 2000 m, and a large number of equipments using diesel engines are operating in these areas. In order to optimizate the performance and emission characteristics of diesel engines, the investigation have been carried out for a highland diesel engine fueled with 80% diesel +10% n-butanol +10% PODE3 at an altitude of 2000 m. Firstly, a source model of the diesel engine was developed in CONVERGE and validated. Secondly, the combustion chamber geometry (CCG) of the diesel engine was expressed using two cubic Bézier curves and the shape of the curves was controlled using five variables (Hdep, C1, C2, LP2a and LP2b) and two fixed values. Then, the soot, NOx and HC emissions were predicted for different CCG shapes using response surface methodology and artificial neural networks (ANN), and a more appropriate prediction method for ANN was determined by comparing the performance of both. Finally, the predictions of the ANN were optimized using Non-dominated sorting genetic algorithm III (NSGA III) to obtain the Pareto fronts and the optimal solutions were selected from the Pareto fronts using VlseKriterijumska Optimizacija I Kombrissino Resenje (VIKOR). Through optimization, the optimal solution reduced soot, NOx and HC emissions by 67.15%, 7.08% and 92.48%, respectively, compared with the original CCG of the CI engine. In addition, the best CCG was analyzed in detail. Overall, ANN-NSGA III is an efficiently optimized method. The optimized CCG can effectively reduce the emission of CI engine.