首页|Shanghai University Reports Findings in Machine Learning (Prediction and explana tion for ozone variability using cross-stacked ensemble learning model)
Shanghai University Reports Findings in Machine Learning (Prediction and explana tion for ozone variability using cross-stacked ensemble learning model)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting from Shanghai, People's Repub lic of China, by NewsRx journalists, research stated, "With the development of m onitoring technology, the variety of ozone precursors that can be detected by mo nitoring stations has been increased dramatically. And this has brought a great increment of information to ozone prediction and explanation studies." The news correspondents obtained a quote from the research from Shanghai Univers ity, "This study completes feature mining and reconstruction of multi-source dat a (meteorological data, conventional pollutant data, and precursors data) by usi ng a machine learning approach, and built a cross-stacked ensemble learning mode l (CSEM). In the feature engineering process, this study reconstructed two VOCs variables most associated with ozone and found it works best to use the top seve n variables with the highest contribution. The CSEM includes three base models: random forest, extreme gradient boosting tree, and LSTM, learning the parameters of the model under the integrated training of cross-stacking. The cross-stacked integrated training method enables the second-layer learner of the ensemble mod el to make full use of the learning results of the base models as training data, thereby improving the prediction performance of the model. The model predicted the hourly ozone concentration with R of 0.94, 0.97, and 0.96 for mild, moderate , and severe pollution cases, respectively; mean absolute error (MAE) of 4.48 mg /m, 5.01 mg/m, and 8.71 mg/m, respectively. The model predicted ozone concentrat ions under different NO and VOCs reduction scenarios, and the results show that with a 20 % reduction in VOCs and no change in NO in the study are a, 75.28 % of cases achieved reduction and 15.73 % o f cases got below 200 mg/m. In addition, a comprehensive evaluation index of the prediction model is proposed in this paper, which can be extended to any predic tion model performance comparison and analysis."
ShanghaiPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine LearningOzone
NETL
NSTL
