Pollutant Concentration Prediction Based on the Optimization of Long-Short Distance in Space

As air pollution continues to pose a growing threat to human health and environmental well-being, accurate forecasting of pollutant concentration has become increasingly important. Existing prediction models can be divided into two categories: non-machine learning models and machine learning models. Nonmachine learning models excessively rely on historical data, while machine learning models have high time complexity and require large amounts of data. To solve the above problems, this paper proposes a spatial distance optimization-based model for predicting pollutant concentration. The proposed model uses a neural network for predicting pollutant concentration, with the nonlinear activation increasing the model's ability to fit nonlinear data. Additionally, it proposes a spatial distance optimization strategy that divides the surrounding monitoring stations based on their distance from the target station. As the neural network model deepens, the influence of more distant monitoring stations on the predicted values gradually reduces. The proposed model adapts the weights based on training errors, implicitly learning the distribution of the relationship between station distances and concentration values and fully exploiting the intrinsic information of the data. Simulation results show that the proposed model can achieve a prediction accuracy up to 6.38% higher than traditional methods.