Automatic and Fast Recognition of On-Road High-Emitting Vehicles Using an Optical Remote Sensing System

Enhancing vehicular emissions monitoring: A GA-GRU-based soft sensors approach for HDDVs

Vehicle emissions have a serious impact on urban air quality and public health, so environmental authorities around the world have introduced increasingly stringent emission regulations to reduce vehicle exhaust emissions. Nowadays, PEMS (Portable Emission Measurement System) is the most widely used method to measure on-road NOx (Nitrogen Oxides) and PN (Particle Number) emissions from HDDVs (Heavy-Duty Diesel Vehicles). However, the use of PEMS requires a lot of workforce and resources, making it both costly and time-consuming. This study proposes a neural network based on a combination of GA (Genetic Algorithm) and GRU (Gated Recurrent Unit), which uses CC (Pearson Correlation Coefficient) to determine and simplify OBD (On-board Diagnosis) data. The GA-GRU model is trained under three real driving conditions of HDDVs, divided by vehicle driving parameters, and then embedded as a soft sensor in the OBD system to monitor real-time emissions of NOx and PN within the OBD system. This research addresses the existing research gap in the development of soft sensors specifically designed for NOx and PN emission monitoring. In this study, it is demonstrated that the described soft sensor has excellent R2 values and outperforms other conventional models. This research highlights the ability of the proposed soft sensor to eliminate outliers accurately and promptly while consistently tracking predictions throughout the vehicle's lifetime. This method is a groundbreaking update to the vehicle's OBD system, permanently adding monitoring data to the vehicle's OBD, thus fundamentally improving the vehicle's self-monitoring capabilities.

Detecting high emitting vehicle subsets using emission remote sensing systems

It is often assumed that a small proportion of a given vehicle fleet produces a disproportionate amount of air pollution emissions. If true, policy actions to target the highly polluting section of the fleet could lead to significant improvements in air quality. In this paper, high-emitter vehicle subsets are defined and their contributions to the total fleet emission are assessed. A new approach, using enrichment factor in cumulative Pareto analysis is proposed for detecting high emitter vehicle subsets within the vehicle fleet. A large dataset (over 94,000 remote-sensing measurements) from five UK-based EDAR (emission detecting and reporting system) field campaigns for the years 2016-17 is used as the test data. In addition to discussions about the high emitter screening criteria, the data analysis procedure and future issues of implementation are discussed. The results show different high emitter trends dependent on the pollutant investigated, and the vehicle type investigated. For example, the analysis indicates that 23 % and 51 % of petrol and diesel cars were responsible for 80 % of NO emissions within that subset of the fleet, respectively. Overall, the contributions of vehicles that account for 80 % of total fleet emissions usually reduce with EURO class improvement, with the subset fleet emissions becoming more homogenous. The high emitter constituent was more noticeable for pollutant PM compared with the other gaseous pollutants, and it was also more prominent for petrol cars when compared to diesel ones.

Review on recent progress in on-line monitoring technology for atmospheric pollution source emissions in China

Emissions from mobile sources and stationary sources contribute to atmospheric pollution in China, and its components, which include ultrafine particles (UFPs), volatile organic compounds (VOCs), and other reactive gases, such as NH₃ and NO_x, are the most harmful to human health. China has released various regulations and standards to address pollution from mobile and stationary sources. Thus, it is urgent to develop online monitoring technology for atmospheric pollution source emissions. This study provides an overview of the main progress in mobile and stationary source monitoring technology in China and describes the comprehensive application of some typical instruments in vital areas in recent years. These instruments have been applied to monitor emissions from motor vehicles, ships, airports, the chemical industry, and electric power generation. Not only has the level of atmospheric environment monitoring technology and equipment been improving, but relevant regulations and standards have also been constantly updated. Meanwhile, the developed instruments can provide scientific assistance for the successful implementation of regulations. According to the potential problem areas in atmospheric pollution in China, some research hotspots and future trends of atmospheric online monitoring technology are summarized. Furthermore, more advanced atmospheric online monitoring technology will contribute to a comprehensive understanding of atmospheric pollution and improve environmental monitoring capacity.

Comparative Analysis of Machine Learning Algorithms in Automatic Identification and Extraction of Water Boundaries

Monitoring open water bodies accurately is important for assessing the role of ecosystem services in the context of human survival and climate change. There are many methods available for water body extraction based on remote sensing images, such as the normalized difference water index (NDWI), modified NDWI (MNDWI), and machine learning algorithms. Based on Landsat-8 remote sensing images, this study focuses on the effects of six machine learning algorithms and three threshold methods used to extract water bodies, evaluates the transfer performance of models applied to remote sensing images in different periods, and compares the differences among these models. The results are as follows. (1) Various algorithms require different numbers of samples to reach their optimal consequence. The logistic regression algorithm requires a minimum of 110 samples. As the number of samples increases, the order of the optimal model is support vector machine, neural network, random forest, decision tree, and XGBoost. (2) The accuracy evaluation performance of each machine learning on the test set cannot represent the local area performance. (3) When these models are directly applied to remote sensing images in different periods, the AUC indicators of each machine learning algorithm for three regions all show a significant decline, with a decrease range of 0.33–66.52%, and the differences among the different algorithm performances in the three areas are obvious. Generally, the decision tree algorithm has good transfer performance among the machine learning algorithms with area under curve (AUC) indexes of 0.790, 0.518, and 0.697 in the three areas, respectively, and the average value is 0.668. The Otsu threshold algorithm is the optimal among threshold methods, with AUC indexes of 0.970, 0.617, and 0.908 in the three regions respectively and an average AUC of 0.832.

Computational Intelligence in Remote Sensing: An Editorial

Computational intelligence is a very active and fruitful research of artificial intelligence with a broad spectrum of applications. Remote sensing data has been a salient field of application of computational intelligence algorithms, both for the exploitation of the data and for the research/development of new data analysis tools. In this editorial paper we provide the setting of the special issue "Computational Intelligence in Remote Sensing" and an overview of the published papers. The 11 accepted and published papers cover a wide spectrum of applications and computational tools that we try to summarize and put in perspective in this editorial paper.