An Intelligent Prediction Model for the Synthesis Conditions of Metal-Organic Frameworks Utilizing Artificial Neural Networks Enhanced by Genetic Algorithm Optimization

In the field of emerging materials, metal-organic frameworks (MOFs) have gained prominence due to their unique porous structures, showing versatility in gas adsorption, storage, separation, and liquid processes. However, their decomposition, collapse tendencies, and complex synthesis make large-scale production costly and challenging with no accurate method for predicting synthesis conditions. This work proposes an intelligent prediction model based on the structural characteristics of MOFs to forecast synthesis conditions. A genetic algorithm-optimized back-propagation (BP) neural network was developed, starting with feature selection via the minimum redundancy maximum relevance algorithm to rank feature importance. The optimal number of inputs and outputs was determined on the basis of performance, followed by genetic algorithm optimization of the BP neural network. The best initial population size and number of hidden nodes were identified. The study compared 10 models, including a genetic algorithm-optimized BP neural network and a simple BP neural network. The results revealed that the R coefficient of the optimized model reached 96.2%, surpassing that of conventional methods with all R values of approximately 85%. This approach allows for accurate prediction of MOF synthesis conditions, aiding material manufacturing in precise control over synthesis processes, improving material quality, and reducing raw material waste.