Search

Given the limitation of conventional soil pollution monitoring through mapping which is a costly, time-consuming work, the study aims to establish an image recognition model to identify the source of pollution automatically. The study choses a contaminated land and then use a non-destructive instrument that can quickly and effectively measure the content of heavy metals. A two concentration prediction models of Ni, Cu, Zn, Cr, Pb, As, Cd, and Hg using hyperspectral imaging were developed, Decision Tree and Back Propagation Neural Network, in combination of particle swarm optimization employed for optimization algorithm. As a result, random forest is more accurate than the forecast result of back propagation neural network. This study has established an excellent Cu and Cr model, which can accurately capture the pollution source. In addition, through aerial photographs, we also found that there were also high pollution reactions on the banks of the river. The developed model is beneficial for high pollution areas which can be quickly found, thereby following investigation and remediation work can be carried out with less time and cost consuming comparing with the conventional soil monitoring.

This paper proposed a PM 2.5 forecasting model using Long Short-Term Model (LSTM) sequence to sequence combined with the statistical method. Correlation Analysis, XGBoost, and Chemical processed are used as the methods to select the essential features. The air pollution data is extracted from Taiwan Environmental Protection Agency (EPA) for the Taichung City dataset in 2014–2018. The study points out that chemical processed model of particulate matter 10 micrometers or less in diameter (PM10), Sulfur Dioxide (SO2), and Nitrogen Dioxide (NO2) have the highest accuracy or lowest Root Mean Square Error (RMSE) and more short training and testing time among the other models. The chemical processed model of PM10, SO2, and NO2 (model B) has the highest accuracy (lowest RMSE), approximately 1 point lower RMSE values, and the shortest training and testing period among the other models. Furthermore, RMSE calculations based on the stations reveal that training with the entire station dataset has a 3 point higher RMSE value than training with each station dataset.

Marine litter is a significant threat to the marine environment, human health, and the economy. In this study, beach litter surveys along Vietnamese coasts were conducted in a local context to quantify and characterize marine litter using the modified GESAMP marine litter monitoring guideline. A total of 21,754 items weighing 136,820.2 g was recorded across 14 surveys from September 2020 to January 2021. Plastic was the most abundant type of litter by both quantity (20,744 items) and weight (100,371.2 g). Fishing gear 1 (fishing plastic rope, net pieces, fishing lures and lines, hard plastic floats) and soft plastic fragments were the most frequently observed items (17.65% and 17.24%, respectively). This study not only demonstrates the abundance and composition of marine litter in Vietnam, it also provides valuable information for the implementation of appropriate preventive measures, such as the redesign of collection, reuse, and recycling programs, and informs policy and priorities, with a focus on action and investment in Vietnam. Moreover, insights from this study indicate that citizen science is a useful approach for collecting data on marine litter in Vietnam.

Air pollution is at the center of pollution-control discussion due to the significant adverse health effects on individuals and the environment. Research has shown the association between unsafe environments and different sizes of particulate matter (PM), highlighting the importance of pollutant monitoring to mitigate its detrimental effect. By monitoring air quality with low-cost monitoring devices that collect massive observations, such as Air Box, a comprehensive collection of ground-level PM concentration is plausible due to the simplicity and low-cost, propelling applications in agriculture, aquaculture, and air quality, water resources, and disaster prevention. This paper aims to view IoT-based systems with low-cost microsensors at the sensor, network, and application levels, along with machine learning algorithms that improve sensor networks' precision, providing better resolution. From the analysis at the three levels, we analyze current PM monitoring methods, including the use of sensors when collecting PM concentrations, demonstrate the use of IoT-based systems in PM monitoring and its challenges, and finally present the integration of AI and IoT (AIoT) in PM monitoring, indoor air quality control, and future directions. In addition, the inclusion of Taiwan as a site analysis was illustrated to show an example of AIoT in PM-control policy-making potential directions.

Determining the location and size of new reservoirs requires a risk-informed decision approach. The scope of risk management, which has been increasingly recognized today, should consider the resulting economic benefit and the local unique hydrological conditions while maintaining necessary water quality in the river. Thus, the incorporation of environmental and economic factors into the reservoir capacity planning process is essential. This chapter presents an optimization-based risk analysis framework to size a new reservoir in a river basin with focus on sustainable development. The framework is designed for a multidisciplinary assessment of reservoir sizing, simultaneously addressing natural patterns of stream flows, adequate water supply, and pristine water quality in the river watershed. A set of water quality parameters, that is, dissolved oxygen (DO) and biochemical oxygen demand (BOD), is used as a surrogate index to reflect water quality impacts. A dynamic stochastic optimization is applied to the problems in which the uncertainty is modeled using the Markov Chain Monte Carlo (MCMC) technique. A case study of Hou-Lung River Basin in Taiwan is used to illustrate the capability of the framework.

Concerning Artificial Intelligence (AI)-based applications, it is necessary to reduce latency in real-time inference. This paper implements and compares two separate models, Inception V3 and Mobilenet, using Intel Neural Compute Stick (NCS) 2 and Raspberry Pi 4 as the edge devices. The Model Optimizer (MO), which generates an Intermediate Representation (IR) of the network, is used for optimizing these models. Then, the IR models are inferences in the edge device. Finally, the comparison of frame per second speed (FPS) and precision is provided. The results show that the speed on Inception V3 is 9 frames per second, while that on Mobilenet is 24 frames per second. Simultaneously, the accuracy reaches 41.28% on Inception V3, but misclassifies for Nissan Altima 2014, and reaches 71.29% on Mobilenet with right classification for Toyota Camry 2014.

Sand and dust storms in arid and semiarid regions deteriorate regional air quality and threaten public health security. To quantify the negative effects of river dust on regional air quality, this study selected the estuary areas located in central Taiwan as a case study and proposed an integrated framework to measure the fugitive emission of dust from riverbeds with the aid of satellite remote sensing and wind tunnel test, together with the concentrations of particulate matter with a diameter of

Groundwater quality in coastal area has been an issue of interest because of excessive groundwater extraction for human use, for example, industrialization, irrigation, which can lead to saltwater ...

This study was conducted to estimate the generation of single-use plastics (SUPs) and elucidate consumer behavior towards a plastic-free university. The results show that the consumption rate of plastic bottles was the highest at 1.39 g per student per day (g.s−1.d−1), followed by plastic cups (0.20 g s−1.d−1), and plastic bags (0.14 g s−1.d−1). Approximately 94.41% of students were highly aware of the negative impacts of SUPs. More than four-fifths of the students (82.32%) assumed that they were responsible for the SUP pollution issue, whereas 59.52% considered SUP reduction (or lack thereof) by individuals, governments, and producers/businesses be important factors. Approximately 19.03% of the students supported implementing a high fine, one-tenth agreed for a total ban on SUPs, while nearly one-fifth believed reducing SUP consumption was unnecessary. Strategies for plastic-free universities was initiated by establishing the goal of “plastic-free university” and implementing integrated actions including a ban (plastic cups and bags) awareness-raising, and suitable alternatives.

This paper proposed the forecasting model of Influenza-like Illness (ILI) and respiratory disease. The dataset was extracted from the Taiwan Environmental Protection Administration (EPA) for air pollutants data and the Centers for Disease Control (CDC) for disease cases from 2009 to 2018. First, this paper applied the ARIMA method, which trained based on the weekly number of disease cases in time series. Second, we implemented the Long short-term memory (LSTM) method, which trained based on the correlation between the weekly number of diseases and air pollutants. The models were also trained and evaluated based on five and ten years of historical data. Autoregressive integrated moving average (ARIMA) has an excellent model in the five-year dataset of ILI at 2564.9 compared to ten years at 8173.6 of RMSE value. This accuracy is similar to the Respiratory dataset, which gets 15,656.7 in the five-year dataset and 22,680.4 of RMSE value in the ten-year dataset. On the contrary, LSTM has better accuracy in the ten-year dataset than the five-year dataset. For example, on average of RMSE in the ILI dataset, LSTM has 720.2 RMSE value in five years and 517.0 in ten years dataset. Also, in the Respiratory disease dataset, LSTM gets 4768.6 of five years of data and 3254.3 of the ten-year dataset. These experiments revealed that the LSTM model generally outperforms ARIMA by three to seven times higher model performance.

Marine debris is a significant threat to the marine environment, human health and the economy in Can Gio island, Vietnam. In this study, we conducted beach litter surveys to quantify and characterize marine litter from six beach transects in this region for the first time using the OSPAR beach litter monitoring guideline. A total of 29,456 items weighting 529,432 g was recorded from 12 surveys in two monitoring campaigns in December 2019 (dry season) and in June 2020 (rainy season). Plastic was the most abundant type of litter in terms of quantity (a total of 26,662 items) and weight (325,606 g), followed by paper and cardboard, cloth, wood, metal, glass and ceramics, rubber and other items. Meanwhile, ropes (less than 1 cm in diameter) and plastic bags accounted for the major parts of sampled plastic items, i.e., 20.18% and 14.46%, respectively. In general, a higher percentage of marine litter, particularly the fishing related items, was found in the rainy season than in the dry season, possibly due to increased fishing and aquaculture activities. In contrast, a reduction pattern of the single use plastics in the rainy season might be due to the decreased tourism activities during the Covid pandemic period. This study not only showed the magnitude of litter pollution, but also provided valuable information that could help decision making to better control and reduce marine litter in the region. In addition, insights from this study indicate that there is an urgent need to design collection, reuse and recycling programs in the area. The collected recyclables, specially plastics, will be a great source of materials for recyclers in a circular economy achieving sustainable development goals.

There have been studies demonstrated the critical effects of air pollution on human health, specifically on the human respiratory system. In this paper, the number of respiratory disease case in Central Taiwan is forecasted through implementing Long Short-Term memory (LSTM) model. The study collected air quality and respiratory case data from open sources of Taiwan governments from 2009 to 2018 in Taichung City, Nantou County, and Changhua County of Central Taiwan. The implemented LSTM network is baseline performance which interprets how well of weekly respiratory forecasting based on multiple input air pollutant variables in the Keras deep learning library. The finding result shows high accuracy of forecasting model in Taichung with Root Mean Squared Error (RMSE) 0.053 and variance score 0.873. Although the forecasting result in Nantou County and Changhua County were not as high as expectation, the study still offers prospects for the future in applying the LSTM networks for issues in epidemiologic and environmental fields.

Human behavior altered in different socioeconomic conditions is the main contributor to deteriorating air quality, therefore changing the behavior is the goal of air policies. In this study, we propose an integrated framework to figure out the roles of socio-physical environments in promoting air quality control policies through behavioral perspectives. The study selects Changhua County in Central Taiwan, composed of 26 cities and townships, as a case study to investigate the impacts of social and economic factors and the air quality on individual’s knowledge, attitude and behavioral intention. The socioeconomic and environmental factors are collected from Taiwanese official information, while the knowledge, attitude, and intention toward the policies are obtained through questionnaires. Subsequently, multivariate analysis techniques including principal component analysis and redundancy analysis are utilized to simultaneously identify the causal relationships between socio-physical environments and the knowledge, attitude, and intention in different townships. Our findings suggest that individual’s knowledge, attitude, and intention toward the air polices cannot be raised simply in commensurate with the growth of the economy and the deterioration of air quality. Indeed, people living in highly urbanized regions and being well-educated, particularly in Changhua City, are less willing to take actions for air quality improvement although they are susceptible to environmental risks. On the contrary, people close to nature have more environmental knowledge, positive attitudes and more intentions to improve the air quality. The finding results will be beneficial to authorities in each city/township to organize environmental education plans corresponding to their socioeconomic conditions and behavioral patterns.

Composition of municipal solid waste (MSW) is rapidly changed along with socioeconomic factors, especially in developing countries. Understanding the association between MSW composition and socioeconomic factors is therefore instrumental when deciding types of technologies and optimizing management strategies. In the past decades, Taiwan has gradually evolved from an agricultural society to a post-industrial society through industrialization and urbanization. This study collects a 12-year worth of self-reported dataset in Taiwan, including MSW, individual and household social-economic factors, in order to unveil their relationships. Our analysis is based on multivariate approach. The results indicate that the major socioeconomic factors that dominate the MSW composition were safety concerns, economic activities, and lifestyle. Overall, MSW composition is increasingly complex as the economy experiences more prosperity, and there is an upward trend of recyclable wastes. Moreover, kitchen waste represents a distinct pattern between urban and rural communities, coupled with the contribution of total waste. Consistent with other countries, paper waste is increased in commensurate with the growth of economy. Interestingly, contrasting to the global trend, plastics and glass wastes generation rate decline when the economy expands economic activities. This attributes mainly to the strict enforcement of recycling policies accompanied with marketing campaigns that encourage recycling and enhance consumers’ green awareness. Strategies that facilitate modifying consumers’ socioeconomic factors and changing consumers’ behavior could play an important role in management of MSW in other developing countries.