Artificial intelligence unlocks ecological environment governance —smart statistical monitoring based on meteorology.

In recent years, the issue of governance of the ecological environment has been a subject of high of social concern, and the challenges in the governance of smog is even more remarkable. China has accumulated a vast real-time monitoring system, which mainly obtains pollution data through national monitoring stations, providing a strong foundation for atmospheric governance. However, there are still several challenges in obtaining data from national monitoring stations, such as high cost and difficulty in comprehensive coverage. In the internet world, big data, cloud computing and other technologies are rapidly developing. It is imperative that new countermeasures counterfeit, falsify, and establish a sound long-term supervision mechanism. It is a popular research issue in academia and a policy difficulty faced by government departments. In terms of statistical models, various deep learning methods that have made major breakthroughs in the field of computer vision are used to try to obtain standardized estimates of concentration based on picture data. In general, based on the collection and arrangement of a large amount of image data over the past three years, 7 types of deep learning models have been constructed, which can achieve fast reading and accurate estimation of PM2.5 concentrations. Based on this model, we have put forward practical policy recommendations with a view to helping the early realization of smart monitoring to reduce concentration. For the standardized PM2.5 data, the minimum estimate error can reach 0.42. On this basis, we also put forward policy recommendations with practical value, with a view to helping the early realization of smart monitoring of pollutant concentrations. [ABSTRACT FROM AUTHOR]