Haze Prediction Model Using Deep Recurrent Neural Network

Semi-supervised urban haze pollution prediction based on multi-source heterogeneous data

Particulate matter (PM) is defined by the Texas Commission on Environmental Quality (TCEQ) as "a mixture of solid particles and liquid droplets found in the air". These particles vary widely in size. Those particles that are less than 2.5 μm in aerodynamic diameter are known as Particulate Matter 2.5 or PM2.5. Urban haze pollution represented by PM2.5 is becoming serious, so air pollution monitoring is very important. However, due to high cost, the number of air monitoring stations is limited. Our work focuses on integrating multi-source heterogeneous data of Nanchang, China, which includes Taxi track, human mobility, Road networks, Points of Interest (POIs), Meteorology (e.g., temperature, dew point, humidity, wind speed, wind direction, atmospheric pressure, weather activity, weather conditions) and PM2.5 forecast data of air monitoring stations. This research presents an innovative approach to air quality prediction by integrating the above data sets from various sources and utilizing diverse architectures in Nanchang City, China. So for that, semi-supervised learning techniques will be used, namely collaborative training algorithm Co-Training (Co-T), who further adjusting algorithm Tri-Training (Tri-T). The objective is to accurately estimate haze pollution by integrating and using these multi-source heterogeneous data. We achieved this for the first time by employing a semi-supervised co-training strategy to accurately estimate pollution levels after applying the U-air system to environmental data. In particular, the algorithm of U-Air system is reproduced on these highly diverse heterogeneous data of Nanchang City, and the semi-supervised learning Co-T and Tri-T are used to conduct more detailed urban haze pollution prediction. Compared with Co-T, which train time classifier (TC) and subspace classifier (SC) respectively from the separated spatio-temporal perspective, the Tri-T is more accurate with a and faster because of its testing accuracy up to 85.62 %. The forecast results also present the potential of the city multi-source heterogeneous data and the effectiveness of the semi-supervised learning. We hope that this synthesis will motivate atmospheric environmental officials, scientists, and environmentalists in China to explore machine learning technology for controlling the discharge of pollutants and environmental management.

Health risk assessment of exposure to various vapors and fumes in a factory of automobile manufacturing

This study aimed to comprehensively evaluate the health risk of exposure to various vapors and fumes in a factory of automobile manufacturing. This study was performed in 2021 on 115 workers. Vapors and fumes were gathered by the adsorbent tubes of activated charcoal and mixed cellulose esters (MCE) membrane filter, respectively. The flow rate for vapors and fumes were between 0.05 and 0.20 L per min and 1 to 4 L per min, respectively. After preparing, samples were analyzed. To assess the non-cancer and cancer risk of the pollutants, the method proposed environmental protection agency (EPA) was applied. The total concentration of copper (1.031 ppm), manganese (0.114), and 2-butoxyethanol (91.767 ppm) were found to be higher than The threshold limit values (TLVs). The values of non-cancer risk (HQ) due to exposure to vapors of benzene (6.583), toluene (1.396), ethyl benzene (1.212), xylene (31.148), 2-butoxyethanol (89.302), 2-propanol (4.695), 1,2,3-trimethylbenzene (1.923), copper (2.336), manganese (715.82), aluminum (3.772), and chromium (107.066) were higher than the acceptable limit. Moreover, the estimated LCR for benzene (2.15 × 10-4), ethyl benzene (3.97 × 10-4), vinyl chloride (1.25 × 10-4), and chromium (2.11 × 10-2) were higher than the threshold risk level set by EPA. It is emphasized that preventive measures are performed.

Does green credit policy promote corporate green innovation? Evidence from China

Green innovation is an important strategy for companies to achieve sustainable development goals. In addition to helping companies create a green image and improve their competitive advantage, green innovation can reduce pollution and improve the ecological and social environment, with positive external effects. The green credit policy (GCP) is an addition to traditional environmental regulations. Taking the 2012 Green Credit Guidelines as a quasi-natural experiment, this study finds that GCP significantly reduces the quantity and quality of green innovation in green credit-restricted firms by discouraging enterprises' debt financing. Heterogeneity analysis showed that the negative impact was concentrated mainly on non-state-owned enterprises (non-SOEs). This study recommends diversifying financing channels to ease corporate debt financing constraints. The conclusions could enrich existing research on the economic consequences of environmental regulatory policies and provide a reference for the strategic planning of green innovation development in enterprises.

Role of climate fund raising under fiscal balance on climate change mitigation: an analysis from Pareto optimality

Since there is little progress being made in multinational climate discussions, climate finance is at a crossroads as lenders must come up with new plans for the "Future of Environment Funds." The mission of effectively and efficiently distributing money to support the shift to low-carbon, climate-resilient economies has been given to climate finance organizations. Due to its purpose to contribute to a paradigm shift, the Green Climate Fund (GCF) is anticipated to help the most vulnerable populations adapt to and mitigate climate change. This research alters the premise of the Baumol and Oates public externality model to make it more appropriate for global climate governance analysis. This research then deduces the special pricing conditions to persuade the market to comply with Pareto optimality criteria by contrasting the Pareto optimality model of global climate governance and the market equilibrium model. The rules and potential approaches that must be followed for raising capital and allocating GCFs are then determined by taking into account global Pareto optimality and fiscal balance. The study finds that when each country assumes that the GCF aims to achieve Pareto optimality in climate governance globally and its own fiscal balance, the equilibrium results of the international climate game will not achieve both the financial balance of the GCF and global Pareto optimality simultaneously. The GCF may successfully finance non-bankable components of bigger "almost bankable projects," according to our empirical analysis of the GCF portfolio structure and strategy in this research. This lends credence to an alternative interpretation of the GCF.

Visualizing the sustainable development goals and natural resource utilization for green economic recovery after COVID-19 pandemic

After the COVID-19 outbreak, this study examines the influence of modifications in China's Sustainable Growth Goals (SDGs) and economic development goals on Chinese enterprises' energy conservation and emissions reduction behavior. Meanwhile, the COVID-19 epidemic has erupted, displacing the flimsy traditional techniques. As a result, the post-COVID-19 pandemic emphasizes the need for a long-term sustainable development method compatible with the local and regional environmental systems. The main objective of this study is used as a roadmap to steer the post-COVID-19 pandemic on a sustainable green path by emphasizing sustainable energy strategies to connect in SDG-related efforts. The investigation in this paper begins with examining significant impacts in the energy industry and their impact on progress toward sustainability. The empirical findings that the CO₂ emissions reduction objectives in long-term development plans had a considerable impact on energy saving and emissions reduction, lowering energy consumption intensity by 3.33% and carbon emission intensity by 4.23% between 2010 and 2019. Besides, the results and long and short run techniques are built to describe the Sustainable Development Goals interface, with the result revealing that Sustainable Development Goals enhance the green economic recovery performance. Furthermore, this study recommends that the key natural resources and green economic recovery policies to overcome the climate change impacts by COVID-19 pandemic.

Spatial green growth in China: exploring the positive role of investment in the treatment of industrial pollution

The industrial sector of China is critical to the country's economic growth. On the other side, industrialisation has resulted in a high rate of emissions, pushing China to spend extensively on industrial pollution remediation. As a result, this study looks at the relationship between investment completed in the treatment of industrial pollution and economic development. Initially, the study used the global Moran's I test (Queen's contiguity matrix) to find spatial autocorrelation for the 'investment completed in the treatment of industrial pollution' factor, where the study found a positive association across Chinese provinces, and suggest the existence of spatial autocorrelation. Thereafter, a time-fixed effect spatial error model was used due to the lowest Akaike information criterion and Bayesian information criterion to analyse regional data of China from 1999 to 2018. The data reveal a positive association between investment completed in the treatment of industrial pollution and regional economic growth, both in the short and long term. Furthermore, the negative consequences of urban wages and foreign investment on investment completed in the treatment of industrial pollution are having the reverse effect on regional green development, necessitating ecologically friendly actions to mitigate the negative environmental effects of both. The results highlight the need for policymakers in other countries to review their plans for economic expansion and create environmentally friendly legislation. By implementing the Chinese green economic growth model, policymakers in industrially polluting nations can reduce industrial pollution and foster green growth in their nation.

Developing a Hybrid Neuro-Fuzzy Method to Predict Carbon Dioxide (CO2) Permeability in Mixed Matrix Membranes Containing SAPO-34 Zeolite

This study compares the predictive performance of different classes of adaptive neuro-fuzzy inference systems (ANFIS) in predicting the permeability of carbon dioxide (CO₂) in mixed matrix membrane (MMM) containing the SAPO-34 zeolite. The hybrid neuro-fuzzy technique uses the MMM chemistry, pressure, and temperature to estimate CO₂ permeability. Indeed, grid partitioning (GP), fuzzy C-means (FCM), and subtractive clustering (SC) strategies are used to divide the input space of ANFIS. Statistical analyses compare the performance of these strategies, and the spider graph technique selects the best one. As a result of the prediction of more than 100 experimental samples, the ANFIS with the subtractive clustering method shows better accuracy than the other classes. The hybrid optimization algorithm and cluster radius = 0.55 are the best hyperparameters of this ANFIS model. This neuro-fuzzy model predicts the experimental database with an absolute average relative deviation (AARD) of less than 3% and a correlation of determination higher than 0.995. Such an intelligent model is not only straightforward but also helps to find the best MMM chemistry and operating conditions to maximize CO₂ separation.

Waste management and green technology: future trends in circular economy leading towards environmental sustainability

The effective treatment of waste to be used as a resource in future has a major role in achieving environmental sustainability and moving towards circular economy. The current research is aimed to provide in-depth detail regarding prominent trends and research themes, evolution, future research orientation, main characteristics, and mapping of research publications on waste management, technological innovation in circular economy domain from the year 2000 to 2021. Different analyses including text mining and bibliometric and content analyses were applied to answer the research question and provide the details on aforementioned variables. From the bibliometric analyses, a total of 1118 articles were drawn out from the Scopus database to conceptualize the core body of research. As a result, the following themes were identified: electronic waste, circular economy transition, plastic waste, bio-based waste management, lifecycle assessment, and ecological impacts, and construction and demolition waste management. The highlighted features, future research orientation, and prominent research perspective can provide guideline for future research to enrich the literature through conducting studies on provided research directions and help lead waste management and technological innovation policymakers, professionals, and practitioners in moving towards circular transition.

Predictive Control of the Mobile Robot under the Deep Long-Short Term Memory Neural Network Model

At present, there is a phenomenon of network data packet loss in the trajectory tracking control system, which will degrade or even destabilize the system's performance. Therefore, this work first explains the theory of the deep long-short term memory (LSTM) neural network model, the kinematic model of mobile robots, and the trajectory tracking error model. The reasons for data packet loss in the control system are analyzed. Second, a prediction model based on the LSTM network is designed according to the theory mentioned above. Finally, the training effect of the LSTM model and the robot trajectory tracking effect based on the model are tested by setting up simulation experiments. The research results are as follows: (1) The pose test error of the mobile robot will eventually tend to zero through the simulation curve generated by the pose parameters (x, y, θ) of the mobile robot. (2) The trajectory tracking error of the deep LSTM neural network prediction and compensation method with the packet loss rate of 5% is less than that with the packet loss rate of 10%. (3) The linear velocity υ of the mobile robot based on the prediction model of the LSTM network varies greatly but is always in the interval (−2, 2). Its angular velocity ω initially fluctuates greatly but gradually tends to zero after about 13 s. (4) When the prediction model tracks the trajectory of the robot, the horizontal position x, the vertical position y, and the angle θ coincide with the reference trajectory. The exploration is conducted to provide a reference for the research on data packet loss in the networked mobile robot trajectory tracking system.

Construction and Analysis of Emotion Recognition and Psychotherapy System of College Students under Convolutional Neural Network and Interactive Technology

This study's aim is to effectively establish a psychological intervention and treatment system for college students and discover and correct their psychological problems encountered in a timely manner. From the perspectives of pedagogy and psychology, the college students majoring in physical education are selected as the research objects, and an interactive college student emotion recognition and psychological intervention system is established based on convolutional neural network (CNN). The system takes face recognition as the data source, adopts feature recognition algorithms to effectively classify the different students, and designs a psychological intervention platform based on interactive technology, and it is compared with existing systems and models to further verify its effectiveness. The results show that the deep learning CNN has better ability to recognize student emotions than backpropagation neural network (BPNN) and decision tree (DT) algorithm. The recognition accuracy (ACC) can be as high as 89.32%. Support vector machine (SVM) algorithm is adopted to classify the emotions, and the recognition ACC is increased by 20%. When the system's K value is 5 and d value is 8, the ACC of the model can reach 92.35%. The use of this system for psychotherapy has a significant effect, and 45% of the students are very satisfied with the human-computer interaction of the system. This study aims to guess the psychology of students through emotion recognition and reduce human participation based on the human-computer interaction, which can provide a new research idea for college psychotherapy. At present, the mental health problems of college students cannot be ignored; especially every year, there will be news reports of college students' extreme behaviors due to depression and other psychological problems. An interactive college student emotion recognition and psychological intervention system based on convolutional neural network (CNN) is established. This system uses face recognition as the basic support technology and uses feature recognition algorithms to effectively classify different students. An interaction technology-based psychological intervention platform is designed and compared with existing systems and models to further verify the effectiveness of the proposed system. The results show that deep learning has better student emotion recognition ability than backpropagation neural network (BPNN) and decision tree algorithm. The recognition accuracy is up to 89.32%. Support vector machine algorithm is employed to classify emotions, and the recognition acceptability rate increases by 20%. When K is 5 and d is 8, the acceptability rate of the model can reach 92.35%. The effect of this system in psychotherapy is remarkable, and 45% of students are very satisfied with the human-computer interaction of this system. This work aims to speculate students' psychology through emotion recognition, reduce people's participation via human-computer interaction, and provide a new research idea for university psychotherapy.

Proposing an Adaptive Neuro-Fuzzy System-Based Swarm Concept Method for Predicting the Physical Properties of Nanofluids

This paper employs dispersed nanoparticles (NPs) to build an adaptive neuro-fuzzy system (ANFIS) for predicting their thermal conductivity (TC) and viscosity according to the most important input data including concentration, size, the thickness of the interfacial layer, and intensive properties of NPs. In this regard, we gather an extensive and comprehensive data set from different sources. Here, the ANFIS model factors are optimized by using the particle swarm optimization (PSO) technique. Afterward, the obtained results are compared with previously published models which did a better job in predicting target values. In the following, to investigate the validity of our proposed model, statistical and graphical techniques are employed and it was proved that this model is efficient to evaluate the output values. Amounts of results obtained from the PSO-ANFIS model evaluation are 0.988 and 0.985 for the R2 and 0.0156 and 0.0876 for root mean squared error (RMSE) of TC ratio and viscosity ratio values, respectively, letting out a valid forecast of targets. Finally, by performing various statistical analyzes, it can be said that this model shows a high ability to predict target values and can be considered a good alternative to previous models.

GIS-Based Frequency Ratio and Analytic Hierarchy Process for Forest Fire Susceptibility Mapping in the Western Region of Syria

Forest fires are among the most major causes of global ecosystem degradation. The integration of spatial information from various sources using statistical analyses in the GIS environment is an original tool in managing the spread of forest fires, which is one of the most significant natural hazards in the western region of Syria. Moreover, the western region of Syria is characterized by a significant lack of data to assess forest fire susceptibility as one of the most significant consequences of the current war. This study aimed to conduct a performance comparison of frequency ratio (FR) and analytic hierarchy process (AHP) techniques in delineating the spatial distribution of forest fire susceptibility in the Al-Draikich region, located in the western region of Syria. An inventory map of historical forest fire events was produced by spatially digitizing 32 fire incidents during the summers of 2019, 2020, and 2021. The forest fire events were divided into a training dataset with 70% (22 events) and a test dataset with 30% (10 events). Subsequently, FR and AHP techniques were used to associate the training data set with the 13 driving factors: slope, aspect, curvature, elevation, Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), Topographic Wetness Index (TWI), rainfall, temperature, wind speed, TWI, and distance to settlements, rivers and roads. The accuracy of the maps resulting from the modeling process was checked using the validation dataset and receiver operating characteristics (ROC) curves with the area under the curve (AUC). The FR method with AUC = 0.864 achieved the highest value compared to the AHP method with AUC = 0.838. The outcomes of this assessment provide constructive spatial insights for adopting forest management strategies in the study area, especially in light of the consequences of the current war.

Applying Optimized ANN Models to Estimate Dew Point Pressure of Gas Condensates

It is economically and technically essential to promptly and accurately estimate the dew point pressure (DPP) of gas condensate to, for example, characterize fluids, evaluate the performance of reservoirs, plan and develop reservoirs for gas condensates, and design/optimize a production system. Indeed, it is difficult to experimentally explore the DPP. Furthermore, experimental tests are time-consuming and complicated. Therefore, it is required to develop an accurate, reliable DPP estimation framework. This paper introduces artificial neural network (ANN) models coupled with optimization algorithms, including a genetic algorithm (GA) and particle swarm optimization (PSO), for DPP estimation. A total of 721 data points were employed to train and test the algorithm. In addition, the outlier data were identified and excluded. The root-mean-squared error (RMSE) and the coefficient of determination (R2) were calculated to be 230.42 and 0.982 for the PSO-ANN model and 0.0022 and 0.997 for the GA-ANN model, respectively. The model estimates were found to be in good agreement with the experimental dataset. Therefore, it can be said that the proposed method is efficient and effective.

Novel prosperous computational estimations for greenhouse gas adsorptive control by zeolites using machine learning methods

To predict CO₂ adsorptive capture, as a vital environmental issue, using different zeolites including 5A, 13X, T-Type, SSZ-13, and SAPO-34, different models have been developed by implementing artificial intelligence algorithms. Hybrid adaptive neuro-fuzzy inference system (Hybrid-ANFIS), particle swarm optimization-adaptive neuro-fuzzy inference system (PSO-ANFIS) and the least-squares support vector machine (LSSVM) modeling optimized with the coupled simulated annealing (CSA) optimization have been employed for the models. The developed models, validated by utilizing various graphical and statistical methods exhibited that the Hybrid-ANFIS model estimations for the gas adsorption on 5A, T-Type, SSZ-13, and SAPO-34 zeolites with average absolute relative deviation (AARD) % of 8.21, 1.92, 4.99 and 2.26, and PSO ANFIS model estimations for the gas adsorption on zeolite 13X with an AARD of 4.85% were in good agreement with corresponding experimental data. It could be deduced that the proposed models were more prosperous and efficient in favor of the design and analysis of adsorption processes than previous ones.

Haze Grading Using the Convolutional Neural Networks

As an air pollution phenomenon, haze has become one of the focuses of social discussion. Research into the causes and concentration prediction of haze is significant, forming the basis of haze prevention. The inversion of Aerosol Optical Depth (AOD) based on remote sensing satellite imagery can provide a reference for the concentration of major pollutants in a haze, such as PM2.5 concentration and PM10 concentration. This paper used satellite imagery to study haze problems and chose PM2.5, one of the primary haze pollutants, as the research object. First, we used conventional methods to perform the inversion of AOD on remote sensing images, verifying the correlation between AOD and PM2.5. Subsequently, to simplify the parameter complexity of the traditional inversion method, we proposed using the convolutional neural network instead of the traditional inversion method and constructing a haze level prediction model. Compared with traditional aerosol depth inversion, we found that convolutional neural networks can provide a higher correlation between PM2.5 concentration and satellite imagery through a more simplified satellite image processing process. Thus, it offers the possibility of researching and managing haze problems based on neural networks.

Estimating the density of deep eutectic solvents applying supervised machine learning techniques

Deep eutectic solvents (DES) are recently synthesized to cover limitations of conventional solvents. These green solvents have wide ranges of potential usages in real-life applications. Precise measuring or accurate estimating thermophysical properties of DESs is a prerequisite for their successful applications. Density is likely the most crucial affecting characteristic on the solvation ability of DESs. This study utilizes seven machine learning techniques to estimate the density of 149 deep eutectic solvents. The density is anticipated as a function of temperature, critical pressure and temperature, and acentric factor. The LSSVR (least-squares support vector regression) presents the highest accuracy among 1530 constructed intelligent estimators. The LSSVR predicts 1239 densities with the mean absolute percentage error (MAPE) of 0.26% and R² = 0.99798. Comparing the LSSVR and four empirical correlations revealed that the earlier possesses the highest accuracy level. The prediction accuracy of the LSSVR (i.e., MAPE = 0. 26%) is 74.5% better than the best-obtained results by the empirical correlations (i.e., MAPE = 1.02%).

Classification of Urban Pollution Levels Based on Clustering and Spatial Statistics

In recent years, the occurrence and frequency of haze are constantly increasing, severely threatening people’s daily lives and health and bringing enormous losses to the economy. To this end, we used cluster analysis and spatial autocorrelation methods to discuss the spatial and temporal distribution characteristics of severe haze in China and to classify regions of China. Furthermore, we analyzed the interaction between haze pollution and the influence of economy and energy structure in 31 provinces in China, providing references for the prevention and treatment of haze pollution. The processed data mainly include API, meteorological station data, and PM 2.5 concentration distribution vector graph. The results show the yearly haze pattern from 2008 to 2012, and present a strong pattern of pollution concentrated around Beijing–Tianjin, the Yangtze River Delta, southwest China, and central China. The overall spatial pattern of decreasing from north to south is relatively constant over the study period.

An Investigation on Spiking Neural Networks Based on the Izhikevich Neuronal Model: Spiking Processing and Hardware Approach

The main required organ of the biological system is the Central Nervous System (CNS), which can influence the other basic organs in the human body. The basic elements of this important organ are neurons, synapses, and glias (such as astrocytes, which are the highest percentage of glias in the human brain). Investigating, modeling, simulation, and hardware implementation (realization) of different parts of the CNS are important in case of achieving a comprehensive neuronal system that is capable of emulating all aspects of the real nervous system. This paper uses a basic neuron model called the Izhikevich neuronal model to achieve a high copy of the primary nervous block, which is capable of regenerating the behaviors of the human brain. The proposed approach can regenerate all aspects of the Izhikevich neuron in high similarity degree and performances. The new model is based on Look-Up Table (LUT) modeling of the mathematical neuromorphic systems, which can be realized in a high degree of correlation with the original model. The proposed procedure is considered in three cases: 100 points LUT modeling, 1000 points LUT modeling, and 10,000 points LUT modeling. Indeed, by removing the high-cost functions in the original model, the presented model can be implemented in a low-error, high-speed, and low-area resources state in comparison with the original system. To test and validate the proposed final hardware, a digital FPGA board (Xilinx Virtex-II FPGA board) is used. Digital hardware synthesis illustrates that our presented approach can follow the Izhikevich neuron in a high-speed state (more than the original model), increase efficiency, and also reduce overhead costs. Implementation results show the overall saving of 84.30% in FPGA and also the higher frequency of the proposed model of about 264 MHz, which is significantly higher than the original model, 28 MHz.