Search

Accurately predicting the concentration of PM2.5 (fine particles with a diameter of 2.5 μm or less) is essential for health risk assessment and formulation of air pollution control strategies. At present, there is also a large amount of air pollution data. How to efficiently mine its hidden features to obtain the future concentration of pollutants is very important for the prevention and control of air pollution. Therefore we build a pollutant prediction model based on Lightweight Gradient Boosting Model (LightGBM) shallow machine learning and Long Short-Term Memory (LSTM) neural network. Firstly, the PM2.5 pollutant concentration data of 34 air quality stations in Beijing and the data of 18 weather stations were matched in time and space to obtain an input data set. Subsequently, the input data set was cleaned and preprocessed, and the training set was obtained by methods such as input feature extraction, input factor normalization, and data outlier processing. The hourly PM2.5 concentration value prediction was achieved in accordance with experiments conducted with the hourly PM2.5 data of Beijing from January 1, 2018 to October 1, 2020. Ultimately, the optimal hourly series prediction results were obtained after model comparisons. Through the comparison of these two models, it is found that the RMSE predicted by LSTM model for each pollutant is nearly 50% lower than that of LightGBM, and is more consistent with the fitting curve between the actual observations. The exploration of the input step size of LSTM model found that the accuracy of 3-h input data was higher than that of 12-h input data. It can be used for the management and decision-making of environmental protection departments and the formulation of preventive measures for emergency pollution incidents. [ABSTRACT FROM AUTHOR]

The widespread use of the Internet of Things (Iot) makes it possible to connect everything but having enough IP addresses is a fundamental requirement of this paradigm. All previous environmental monitoring systems in China are based on IPv4. In combination with the characteristics and requirements of China's atmospheric environment monitoring system, this paper develops a monitoring system based on IPv6 technology. Users can directly access the monitoring equipment through the IPv6 website to view data and configure operations. This paper first introduces the design and implementation of the software and hardware of the system, then introduces the simplification of IPv6 protocol, the transplantation of IPv6 protocol on ARM and the design and implementation of embedded Web server system. The experimental results show that the developed atmospheric environment monitoring system can realize continuous data acquisition based on IPv6 and provide data-driven support for environmental protection management and decision-making. [ABSTRACT FROM AUTHOR]

The development of industry has brought about the pollution of the atmospheric environment. Pollution is harmful to people's health. Realizing the real-time monitoring of atmospheric environmental quality parameters can improve the above-mentioned effects. China's existing environmental monitoring systems focus on the accuracy of the system hardware itself for assessment, lack of data analysis and forecasting and early warning, and cannot provide managers and ordinary people with decision-making and activity guidance. This paper develops an IPV6-based high-spatial–temporal precision air pollutant monitoring and early warning platform. The feasibility of the system is verified through networking tests, operation tests, and early warning tests. Through actual data analysis and comparison, it is concluded that the monitoring system has field feasibility, and the atmospheric environment monitoring for the target observation area has achieved the desired observation function. This system integrates GIS technology and B/S architecture to analyze changes in the regional environment to provide support for regional environmental air quality management. The forecast and early warning module constructed by combining the weight method of the influence of different input factors on the environmental quality index and minute-level observations can provide technical support for the government to improve the level of supervision. [ABSTRACT FROM AUTHOR]

Accurate measurement of leaf area index (LAI) is important for agricultural analysis such as the estimation of crop yield, which makes its measurement work important. There are mainly two ways to obtain LAI: ground station measurement and remote sensing satellite monitoring. Recently, reliable progress has been made in long-term automatic LAI observation using wireless sensor network (WSN) technology under certain conditions. We developed and designed an LAI measurement system (LAIS) based on a wireless sensor network to select and improve the appropriate algorithm according to the image collected by the sensor, to get a more realistic leaf area index. The corn LAI was continuously observed from May 30 to July 16, 2015. Research on hardware has been published, this paper focuses on improved system algorithm and data verification. By improving the finite length average algorithm, the data validation results are as follows: (1) The slope of the fitting line between LAIS measurement data and the real value is 0.944, and the root means square error (RMSE) is 0.264 (absolute error ~ 0–0.6), which has high consistency with the real value. (2) The measurement error of LAIS is less than LAI2000, although the result of our measurement method will be higher than the actual value, it is due to the influence of weeds on the ground. (3) LAIS data can be used to support the retrieval of remote sensing products. We find a suitable application situation of our LAIS system data, and get our application value as ground monitoring data by the verification with remote sensing product data, which supports its application and promotion in similar research in the future. [ABSTRACT FROM AUTHOR]