Song Gao

Title: Song Gao - Innovator in Air Quality Prediction

Introduction

Song Gao is a prominent inventor based in Chengdu, China. He has made significant contributions to the field of environmental science, particularly in predicting air quality. His innovative approach combines advanced modeling techniques to enhance the accuracy of air quality predictions.

Latest Patents

Song Gao holds a patent for a "Method for predicting air quality index (AQI) based on a fusion model." This method proposes a differential fusion seasonal prediction model (DF-SPM) that integrates a random forest (RF) model with a convolutional neural network (CNN)-long short-term memory (LSTM)-attention (CLA) model. The method employs an optimal threshold interval (OTI) search algorithm to learn the OTI across four seasons during the prediction process. The final prediction results are derived from the outputs of both the RF model and the CLA model. This fusion model effectively combines the strengths of two independent models while considering the seasonal and periodic characteristics of AQI, leading to improved prediction accuracy.

Career Highlights

Song Gao is affiliated with Chengdu University of Technology, where he continues to advance research in air quality prediction. His work has garnered attention for its innovative use of machine learning techniques to address environmental challenges.

Collaborations

He collaborates with notable colleagues, including Hengsheng Zhang and Simin Wang, who contribute to his research endeavors.

Conclusion

Song Gao's innovative methods in predicting air quality demonstrate the potential of combining advanced modeling techniques to address pressing environmental issues. His contributions are paving the way for more accurate and reliable air quality assessments.