Search

The early detection of fuel leaks in filling stations is crucial to minimize environmental risks, such as soil and groundwater contamination. There are some commercial products for fuel leakage detection based on statistical analysis of data from station inventory books. Although they solve the tackled problem, they have some important drawbacks, such as their high price, and issues related to the privacy of station data, which must be shared with the company owning the reconciliation technology. In this work, a solution based on Artificial Intelligence is proposed to address this problem. Machine Learning techniques, specifically two-class supervised classifiers, are applied to data extracted from inventory books of real petrol stations. The classification models used in this paper are trained and tested with real data of days without leaks and simulated data of days with leaks. Thus, the more representative of reality these data are, the better the classifiers will work when implemented in a real filling station. In this sense, the most novel contribution of this paper is the way in which the training sets are constructed to achieve a realistic scenario. These sets are composed of time data windows in which the leak can begin on any day within the window, not necessarily on the first day, as the authors had assumed in a previous contribution. Therefore, they are mixed windows containing a variable number of non-leaking and leaking days. In addition, the design of these data sets complies with the requirements of the current European standard UNE-EN 13160–5. This allows the classifiers to work under even more realistic conditions and thus increase the practical applicability of their results. This work demonstrates that by using two-class classifiers it is possible not only to comply with the standard in terms of the maximum allowable ratio of false positives and false negatives, but also to detect the leak in a shorter time than that established in the norm. [Display omitted] • The detection of fuel leaks in petrol stations is approached as a classification problem. • In order to study compliance with current regulations it is essential to work in a scenario that is as realistic as possible. • Mixed time windows improve the reliability of the results regarding fuel leaks detection. • The proposed solution allows to accomplish the efficiency requirements of current regulations. [ABSTRACT FROM AUTHOR]

This paper explores consumer green consumption practices and considers a set of factors, including cognitive and behavioural level constructs, that influence green consumption. The paper primarily aims to predict the green purchase intention and classify a consumer as a green or non-green consumer. A total of 310 responses were collected and analyzed using machine Learning techniques like Decision Tree, Random Forest, Gradient Boosting, XGBoost, K-Nearest Neighbour, and Support Vector Machine, and the models were validated using different performance metrics. The paper reveals that the main driving factors for a consumer to consider greener options are green self-identification, followed by environmental knowledge, environmental consciousness, and the impact of social media. The current work will allow better product development and the targeting and positioning of green products/services offerings to customers already classified by the system. • Machine learning techniques were employed to predict green purchase intention (GPI). • Green Self-identification & Environmental Consciousness were the crucial factors in influencing GPI. • Social and health consciousness had less of an impact on influencing GPI. • Perceived personal inconvenience was reported to have no significant impact on GPI. [ABSTRACT FROM AUTHOR]

A good risk warning model is an effective way to guarantee the stable operation of the carbon market and exert its emission reduction function. This paper takes the China's pilot carbon market as the research object and measures the carbon market risk by ARMA-GARCH-VaR. Then, influential factors are selected as non-market characteristics from the perspective of causality and incorporated into the risk warning model, and SMOTE and SMOTEENN are introduced to deal with the unbalanced samples. Results show that (1) The risk fluctuations of Beijing and Shenzhen carbon market are large, and the risk fluctuations of Guangdong carbon market are relatively smooth in the early period and larger in the recent period. (2) Air quality, average daily temperature, CSI 300, power coal, natural gas, European carbon market, exchange rate, and Baidu index are all important factors in the risk volatility of carbon market. (3) The Classification Decision Tree (CDT) has the best performance. CDT has the best performance in Guangdong carbon market, SMOTE-CDT has the best performance in Hubei carbon market, and SMOTEENN-CDT has the best performance in Shanghai carbon market, in which SMOTEENN-CDT has a 76% Recall. The non-equilibrium treatment improves the overall Recall, and the risk warning model after non-equilibrium treatment can avoid missing important risk points. This paper can provide a certain degree of reference for the improvement of carbon trading market and risk management. [Display omitted] • A carbon market warning model is constructed. • The average VaR of the carbon trading markets in Shenzhen and Beijing is larger. • CDT performs better in market risk warning. • The model improves 34.8% in the avoidance of risk compared with other models. [ABSTRACT FROM AUTHOR]

Blockchain technology, with its peer-to-peer trading feature, influences the management of energy consumption by offering the potential to transform transparency, efficiency, and sustainability within the energy sector. Nonetheless, there is a need to develop analytical decision-making models tailored for managing peer-to-peer energy transactions to improve energy resilience. Therefore, the purpose of this paper is to address the research question: How can energy distribution systems be protected via blockchain technology to enhance energy resilience and mitigate vulnerabilities to disruptions ? This paper employs a conceptual research model design and a mathematical decision-making model to address the research question by capturing the peer-to-peer trading capability of blockchain technology. The theory of planned behavior provides theoretical explanations for the proposed model. The sample includes longitudinal energy consumption data from 2015 to 2023 in Texas. The findings indicate a significant improvement in energy efficiency along with a considerable decrease in total electricity consumption. Post hoc analysis results reveal that the seasonal autoregressive integrated moving average algorithm is effective as a reliable input for the proposed mathematical model. The significant implications are to implement blockchain-based smart grids in which energy systems become more resilient to disruptions, as the peer-to-peer capability enables users to trade energy. The proposed model suggests that energy will be used more efficiently and effectively. This paper contributes to prior works by introducing a mathematical model that captures the trading behavior of energy consumers. Moreover, this paper proposes the SARIMA algorithm to predict energy demand. • A mathematical peer-to-peer trading model is presented to improve resilience. • A blockchain-based smart grid is presented for consumer energy consumption. • Five machine learning algorithms are presented in energy demand management. • Longitudinal energy consumption data of Texas is used in the model. • Theoretical support is provided using the theory of planned behavior. [ABSTRACT FROM AUTHOR]

The relationship between government and enterprise has attracted extensive attention. Under the increasingly severe requirement of sustainable development, there is still a lack of research on the economic effect of political acuity from the perspective of enterprise's positive party value creation. We built a dictionary of political acuity and demonstrated reliability through machine learning algorithms such as K-Nearest Neighbor (KNN). Then, based on the annual reports of China's listed companies from 2013 to 2020, the relationship between political acuity, ESG atmosphere, and corporate performance is empirically discussed. Examination through the formal institutional perspective of informal institutionalization shows that the positive acuity of the Communist Party of China(CPC) and the democratic parties(DPC) will improve corporate performance, while the negative acuity will have an early warning effect on performance. Furthermore, the stronger ESG atmosphere synergized this relationship. The CPC's negative acuity has supervision effect on non-state-owned companies, and this supervisory effect still exists in the ESG atmosphere. However, whether the moderating effect is considered or not, the positive political acuity of state-owned enterprises doesn't significantly improve performance. We found that the CPC's embedding in corporate governance will lead to both economic and political benefits, and have thresholds. We constructed a political acuity dictionary and introduced text analysis and nonparametric estimation method in this paper, which provided a basis and reference for future research on political acuity at the enterprise level. Our findings also enrich the institutional theory and the embeddedness theory. Meanwhile, our research broadened the boundary of political parties, ESG, and enterprises, the integration of ideological values and formal institutions, and had practical implications for the green transformation of firms and the precise positioning of political party functions. • We build a dictionary of political acuity for the first time. This dictionary provides a new measurement perspective for the study of corporate political sentiment and sustainable development. • From the perspective of positive value creation, we examine the impact path of a company's party acuity, ESG atmosphere, and financial performance. This paper helps to expand the governance boundaries of ideology and formal institutions, political concepts, and corporate behavior. • We explored the accounting consequences of political acuity for different types of firms, and measured the economic and political effects thresholds. • We introduced machine learning, python crawler, text analysis, and nonparametric estimation methods into this paper, which helped to expand the technical approach to corporate governance and green transformation. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to the strategic planning of the supply chain for lime cultivation. The uncertainty associated with lime production due to factors such as transportation, crime, and water availability, among others, represents different challenges. To address these challenges, the authors propose the use of machine learning tools coupled with deterministic optimization to obtain optimal solutions for the supply chain for future years. This paper highlights the use of justice schemes to ensure an equitable distribution of lime production between farmers and learning machines to quantify the insecurity impact on lime production in Michoacan. The problem can be solved using a Mixed-Integer Linear Programming (MILP) model that focuses on maximizing economic benefits, minimizing the use of irrigation water in crops, and minimizing Carbon Dioxide Equivalent (CO 2eq) emissions within the supply chain. The results demonstrate that the proposed approach can effectively address the challenges facing the lime production supply chain, resulting in an optimized and equitable lime production and distribution between farmers using the Social Welfare Justice scheme. Scenario A presents a utopian viewpoint with maximum benefits and minimum CO 2eq generated emissions, corresponding to $ 4.08 × 109 and 1.94 × 106 tons of CO 2eq , respectively. This paper contributes to the growing body of literature on the use of Artificial Intelligence (AI) in supply chain management, specifically in the optimization of supply chain processes. [Display omitted] [ABSTRACT FROM AUTHOR]

To achieve carbon neutrality, China must grasp the intricate factors driving coal market, as it addresses coal consumption and reduces the carbon footprint. While previous studies have identified certain factors, they have largely overlooked the impact of the overall industry sector on the coal market. In this paper, a hybrid causal machine learning model was proposed that combine with least absolute shrinkage and selection operator (LASSO), multiple linear regression (MLR), peter and clark momentary conditional independence (PCMCI) and interpretable machine learning. The approach employed a complex network perspective to identify 10 key factors in China's coal market from three dimensions: industrial sector, foreign trade and energy market. The hierarchical pattern of these factors is classified into two levels: direct factors, primarily encompassing crude oil futures, exchange rates and architectural decoration, and intermediary factors, mainly including the chemical industry and building material. Interestingly, this paper reaffirms the roles of crude oil futures and exchange rates in the coal market, as identified in prior studies. Additionally, it uncovers new influential factors primarily driven by the chemical industry and architectural decoration, previously unexplored. Furthermore, this paper found a significant contemporaneous relationship between crude oil futures and coal price index (0.151) as well as coal consumption (0.102), and the strong relationship between coal consumption and the Indonesian Rupiah to Chinese Yuan exchange rate (0.063) was also confirmed. Among the emerging dominant factors, the coal price index and the chemical industry (0.145), along with coal consumption and building materials (0.250), also exhibit a strong contemporaneous relationship. These findings highlight the importance of considering the entire industry sector while analyzing the coal market and promoting a cleaner transformation of the industry in China, and the paradigm presented not only applicable to the coal market, but can be extended to other industries. [Display omitted] • Better grasping key factors in China's coal market critical to carbon neutrality. • A comprehensive study encompassing industrial sector, foreign trade and energy market. • A novel hybrid machine learning models and industry-wide features are introduced. • Identification and categorization of direct and intermediary factors. • Findings offer a new paradigm for decision-making, driving cleaner production reforms. [ABSTRACT FROM AUTHOR]

The supercritical carbon dioxide (sCO 2) Brayton cycle, known for its superior thermal efficiency and compact turbomachinery size, can utilize various heat sources. The printed-circuit heat exchangers (PCHE) used in the power cycle, particularly the recuperators and cooler, significantly influence the thermal efficiency of the cycle. However, they exhibit intricate characteristics attributed to large thermal inertia and nonlinear heat transfer. This paper explores the one-dimensional dynamic modeling and control issues for PCHE. The established dynamic PCHE models are verified through different scenarios. Then, a novel control strategy is proposed for fast temperature reference tracking and disturbance rejection. The composite controller includes three parts: the main control is based on the principle of model predictive control (MPC); Gaussian process (GP) regression modeling is incorporated as the feedforward; and the disturbance observer (DOB) is introduced for unexpected disturbance estimation and compensation. Compared with traditional controllers, simulations demonstrate that for reference tracking the settling time of the proposed method can be saved by more than 50%, and for disturbance rejection the recovery time can be reduced by more than 30%. The results indicate the presented strategy can ensure the safe and effective operation of the sCO 2 power cycle. • A one-dimensional dynamic model of printed-circuit heat exchanger for supercritical CO 2 is established. • The machine learning method, namely Gaussian process regression, is presented for output temperature prediction. • The model predictive control-based strategy is proposed for efficient temperature tracking and disturbance rejection. [ABSTRACT FROM AUTHOR]

Machine learning (ML) models have gained importance in predicting recycled aggregate concrete (RAC) properties, offering supposed benefits over conventional empirical and statistical techniques. However, whether ML models are externally generalizable for predicting RAC properties remains unanswered. This study addresses this gap by developing a systematic experimental framework for evaluating the external generalizability of ML models for predicting the compressive strength of RAC. Using a literature review, the authors created a primary dataset of 414 data points and sourced a secondary dataset comprising 330 data points from a previous paper. In Phase 1, prominent ML models like Random Forest (RF) and Extreme Gradient Boost (XGB) were tested for high-accuracy prediction on both primary and secondary datasets. A coefficient of determination (R2) as high as 0.76 for the primary dataset and 0.82 for the secondary dataset for testing sets was obtained for XGB. However, when the best-performing models of phase 1 were trained and tested with data sourced from different datasets in varying combinations, the ML model's performance significantly deteriorated (R2 < 0.25), demonstrating that ML models are not externally generalizable. The study's results highlight the trade-off between the ML model's prediction accuracy within the given dataset and its external generalizability. The study reveals that complex ML models, like XGB, may over-fit specific data, reducing their generalizability. These findings call for the intelligent usage of ML tools to identify nuanced hypotheses and promote rigorous science rather than unilaterally working on the accuracy of ML models. The study emphasizes the consideration of ML models' generalizability in the future. • External Generalizability of the ML modeling is evaluated. • A systematic methodological framework using multiple datasets is presented. • Current ML models for materials research are likely not generalizable. • These findings call for the intelligent usage of ML tools. • The study emphasizes the consideration of ML models' generalizability in the future. [ABSTRACT FROM AUTHOR]

Accurate prediction of the Particulate Matter 2.5 (PM 2.5) plays a crucial role in the accurate management of air pollution and prevention of respiratory diseases. However, PM 2.5 as a time series is extremely difficult to accurately predict. In this paper, a Hybrid Integration (HIG) algorithm that combines data pre-processing, time-series decomposition, signal decomposition, a prediction module, a matching strategy, and a hybrid integrated optimization algorithm is proposed. First, the optimal parameters for the four individual models were selected by integrating multiple evaluation perspectives. Additivity was then determined by Seasonal and Trend decomposition using LOWESS (STL), followed by refinement decomposition using signal decomposition. The four new sequences were reconstructed using Range Entropy (RangeEn) and mapped to the models. Additionally, Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) methods were optimized using the HIG algorithm. The results show that the HIG-RNN and HIG-LSTM are more advantageous than the ordinary method in terms of reasonable weight assignment. Finally, an innovative confusion test method was developed to test the stability of the prediction direction. To ensure generalizability, validation was performed using PM 2.5 data from two regions of China. The results show that the method significantly improves the prediction performance and provides a powerful tool for policy formulation and management. [Display omitted] • A hybrid integration (HIG) algorithm is proposed. • Prediction results were evaluated using the original COI and improved ICOI. • Creative time-frequency analysis bypasses traditional time series constraints. • RangeEn can assess entropy series for regularity to avoid excessive decomposition. • A pioneer confusion test for model direction consistency check was developed. [ABSTRACT FROM AUTHOR]

Simulating anaerobic digestion (AD) using a machine learning (ML) is important for guiding methane production in practice. But the performance of the ML is affected by operational conditions and microbial types and quantities, which lead to low accuracy of the traditional model. In this study, a combined ML algorithm SMOTER-GA-RF was constructed by expanding the number of genomic data, introducing oversampling technique (SMOTER) and genetic algorithm (GA) to increase prediction accuracy, which the test set R2 increased 36.22%. The normalized root mean square error and percent bias of the validation set (D2) were 8.92% (<10%) and 4.13% (<15%), indicating the accuracy of prediction. Simultaneously, the predictive accuracy of the validation sets (V1–V5) in the presence of Gaussian white noise remained high, confirming the robustness of the SMOTER-GA-RF. Furthermore, similar ML models were collected and compared, and it was found that SMOTER-GA-RF constructed in this paper had best effect. Finally, important factors affecting the AD performance of straw were analyzed using SHAP. The hydraulic retention time was controlled at approximately 40 d, volatile fatty acid should be controlled within 1000 mg/L, and the relative abundances of the important archaea Methanoculleus , Methanobacterium and Methanosarcina in the second stage of AD were controlled at 5–10%, <18%, and <5%. [Display omitted] • GA determined the hyper-parameters of the RF to increase the prediction performance. • SMOTER generated new samples strengthened the learning capacity of extreme data. • SMOTER-GA-RF model had good predictive ability and robustness in monitoring and controlling the AD process. • SHAP quantified the range of important features promoting the AD of straw lignocellulose. [ABSTRACT FROM AUTHOR]

Addressing the urgent need for accurate carbon emissions forecasting to support global emissions reduction goals, this paper introduces a novel approach for carbon emissions prediction that dynamically considers the spatial–temporal correlation of carbon emissions across forecasting targets. Traditional statistical and machine learning models have limitations, such as oversimplification and inefficiency in capturing evolving dynamics among multiple forecasting targets, alongside a focus on longer forecasting horizons like monthly or yearly. To tackle these, we propose an innovative Dynamic Spatial–Temporal Graph Convolutional Recurrent Network (DSTGCRN), a blend of graph convolutional and recurrent neural network structures customized for up-to-date multi-regional spatial–temporal predictions at a daily level. Comprehensive empirical analyses on datasets from China, the US, and the EU confirm DSTGCRN's superior performance and robustness across diverse geographical contexts. It outperforms the second-best among 10 baseline models, achieving 40.6%, 24.6%, and 38.5% improvements in MAE, RMSE, and MAPE, respectively, across various horizons. The incorporation of environmental data, including temperature and Air Quality Index, as supplementary predictors in the DSTGCRN model, has demonstrated its efficacy in the context of the China dataset. The DSTGCRN model's improved accuracy and daily multi-regional forecasting deepen emission dynamics understanding, supporting the development of informed and region-specific environmental policies that can respond promptly to changes. [ABSTRACT FROM AUTHOR]

Environmental managers attempt to increasingly incorporate precautionary principles into decision making. The literature lacks Machine Learning -based approaches for forewarning lifecycle environmental impacts. This paper proposes a method to support electric vehicle design. The main innovation of the work lays in merging Life Cycle Assessment (LCA) and Machine Learning foundations to provide support and awareness to designers. The present approach overcomes the present literature because it provides a method for the design phase, is based on a well-established methodology (LCA) and provides quantitative results from little inputs. The approach exploits machine Learning Methods to develop models with the design features of a generic electric vehicle (such as vehicle mass and distance traveled) in six phases (Problem definition; Data collection; Data Preparation; Modeling; Model evaluation; Model interpretation). Differently from existing environmental analyses, all stages of the product life cycle have been considered in building the database; moreover, the model provides quantitative results. Regression models and supervised algorithms were used. The obtained model can be used by product engineers, as well as those not experts on LCA. Moreover, the model guarantees the database and hypothesis's uniqueness, ensuring the results coherence and comparability. The level of accuracy obtained in the case study (error or 17%) is comparable with studies handling full environmental analysis (that should be more accurate), and outstanding, as the present case is for the design phase. Future works will focus on additional significative indicators, similar electric vehicle design and integration with prospective LCA approaches. [ABSTRACT FROM AUTHOR]

Plastic waste pollution is a challenging and complex issue caused mainly by high consumption of single-use plastics and the linear economy of "extract-make-use-throw". Improvements in recycling efficiency, behaviour changes, circular business models, and a more precise waste management system are essential to reduce the volume of plastic waste. This paper proposes a simplified conceptual model for a smart plastic waste separation system based on sensor technology and deep learning (DL) to facilitate recovery and recycling. The proposed system could be applied either at the source (in a smart waste bins) or in a centralised sorting facility. Two smart separation systems have been investigated: i) the one utilising 6 sensors (near-infrared (NIR), humidity, temperature, CO 2 , CH 4 , and a laser profile sensor) and ii) the one with an RGB camera to separate packaging materials based on their composition, size, cleanliness, and appearance. Simulations with a case study showed that for a camera-based sorting, Inception-v3, a DL model based on convolution neural networks (CNN), achieved the best overall accuracy (78%) compared to ResNet-50, MobileNet-v2, and DenseNet-201. In addition, the separation resulted in a higher number of misclassified items in bins, as it focused solely on appearance rather than material composition. Sensor-based sorting faced limitations, particularly with dark colouration and organic matter entrapment. Combining the information from sensors and cameras could potentially mitigate the limitations of each individual method, thus resulting in higher purity of the separated fractions. [Display omitted] • Plastic packaging waste is separated using sensors and deep learning algorithms. • The Separation is based on plastic type and cleanliness. • Inseption-V3 yielded the best classification results (78.34 %). • Sensors resulted in a better identification of dirty packaging items then camera. • Both methods minimised the number of items in the mixed waste bin. [ABSTRACT FROM AUTHOR]

This paper focuses on addressing a critical challenge in 3D printing: managing energy consumption. 3D printing has emerged as a transformative technology in manufacturing, but its energy demands are a key concern for cost-effectiveness and sustainability. To tackle this challenge, an energy management system is proposed to leverage manifold model morphing and semi-supervised machine learning, to reduce production costs for 3D printing. The manifold model is a mathematical representation of the 3D object to be printed, and the refinement process involves optimizing the morphing parameters of the manifold model to achieve desired printing outcomes. To enable flexibility in the grasping space, the semi-supervised machine learning is then incorporated to leverage unlabeled data, enhancing the accuracy and robustness of the energy management system. The proposed system addresses the challenges of limited labeled data and complex morphologies of biological products in layered additive manufacturing. The energy management system is more applicable to soft robotics and biomedical products. The performance of the proposed system is evaluated through extensive experiments that demonstrate its effectiveness and efficacy in predicting and managing energy consumption in 3D printing. Our system offers a practical solution for estimating energy consumption in the design stage, and thus guides the designers to adopt the optimal part geometry and process planning for cleaner production. The results highlight that the proposed system is capable of optimizing energy usage in 3D printing, contributing to the advancement of green and sustainable industrial practices. • A manifold morphing method is proposed to generate multiple family-products. • A kinematics model of the self-grasping manifold is constructed for validation. • A semi-supervised deep network is designed to leverage generated family-products. • The system addresses the challenges of limited sample data in energy management. [ABSTRACT FROM AUTHOR]

Climate change led an increase in the frequency of severe droughts, the effects of which are exacerbated by a lack of water storage. Despite increasing research on global-scale total water storage (TWS) change and drought prediction, basin-scale long-term hydrological drought, TWS change, and El Nino–Southern Oscillation (ENSO) influence in East Africa (EA) remain unexplored. In this paper, we used multiple approaches, of ensemble machine learning (ML) and weighted averaging, to conduct a basin-scale exploratory analysis of future hydrological drought and TWS change for the period 2025–2099. Climate change will affect future hydrological conditions in the basins, with maximum severity values of −90.3, −726.6, and −2567.7 Gt in the Tana, Turkana, and Victoria basins, respectively, under RCP6.0. Similarly, we found maximum severities of −187.5 and −277.7 Gt in the Abaya-Chamo and Tanganyika basins, respectively, under RCP 2.6. The most severe El Nino drought and exceptional La Nina conditions in the basins were found under both RCP scenarios. To ensure future water security in EA, sustainable water resource management strategies that can mitigate the impacts of extreme climate events in the future are urgently needed. [ABSTRACT FROM AUTHOR]

With industrial informatization, rich data frameworks provide the possibility of efficient design and global optimization of methane to hydrogen processes. However, the high coupling between mixed variables leads to the difficulty of first-principles modeling (FPM) to capture the optimal Pareto front in infeasible domains. In this paper, a machine learning proxy (MLP) method is proposed to minimize economic, exergy destruction, CO 2 emissions, and maximize hydrogen production. First, process simulation as FPM is built using physical properties, energy balance, and reaction kinetics to analyze single variable effects and objective trade-offs. Then, datasets consisting of feed, heat transfer, and design variables are built by sampling the FPM in design and extended spaces. The eXtreme Gradient Boosting (XGBoost) with hyperparameter optimization is built as a proxy FPM, capturing the complex mapping between variables and objectives. Finally, the Pareto front is searched in design and extended spaces by combining the proxy model and genetic algorithm. The proposed method benefits 20.2%, 37.2%, 46.7%, and 2.3% in economic, exergy destruction, CO 2 emissions and hydrogen production respectively compared to the heuristic design. XGBoost not only can effectively proxy FPM to capture the complex behavior of reforming techniques, but also can perform better in infeasible domains that are difficult to explore with FPM. [Display omitted] • A MLP optimization method is proposed to explore the trade-offs for four objectives. • The R2 score of XGBoost is above 98.4% for four objective values. • Proxy model exhibits effective exploration of the space far beyond the FPM boundaries. • TAC, exergy destruction, CO 2 emissions, and H 2 production benefits 20.2%, 37.2%, 46.7% and 2.3%. [ABSTRACT FROM AUTHOR]

Water is the most valuable natural resource on earth that plays a critical role in the socio-economic development of humans worldwide. Water is used for various purposes, including, but not limited to, drinking, recreation, irrigation, and hydropower production. The expected population growth at a global scale, coupled with the predicted climate change-induced impacts, warrants the need for proactive and effective management of water resources. Over the recent decades, machine learning tools have been widely applied to various water resources management-related fields and have often shown promising results. Despite the publication of several review articles on machine learning applications in water-related fields, this review paper presents for the first time a comprehensive review of machine learning techniques applied to water resources management, focusing on the most recent achievements. The study examines the potential for advanced machine learning techniques to improve decision support systems in the various sectors within the realm of water resources management, which includes groundwater management, streamflow forecasting, water distribution systems, water quality and wastewater treatment, water demand and consumption, hydropower and marine energy, water drainage systems, and flood management and defence. This study provides an overview of the state-of-the-art machine learning approaches to the water industry and how they can be used to ensure water supply sustainability, quality, and flood and drought mitigation. This review covers the most recent related studies to provide the most recent snapshot of machine learning applications in the water industry. Overall, LSTM networks have been proven to exhibit reliable performance, often outperforming ANN models, traditional machine learning models, and established physics-based models. Hybrid ML techniques have exhibited great forecasting accuracy across all water-related fields, often showing superior computational power over traditional ANNs architectures. In addition to purely data-driven models, physical-based hybrid models have also been developed to improve prediction performance. These efforts further demonstrate that Machine learning can be a powerful practical tool for water resources management. It provides insights, predictions, and optimisation capabilities to help enhance sustainable water use and management and improve socio-economic development, healthy ecosystems and human existence. • We present a review of ML techniques for water resources management (WRM). • ML proved to be efficient in identifying patterns within nonlinear datasets. • Transformer architectures can be used to simplify reinforcement learning. • Generative Pre-trained Transformers open further opportunities to WRM. [ABSTRACT FROM AUTHOR]

Air pollution has a significant impact on human health and influences housing choices. Existing studies on determinant factors affecting property prices, including air pollution, mainly employed hedonic and spatial regression models that have limitations in capturing non-linear relationships and local interactions. Neglecting the non-linear relationships can lead to incomplete estimation impacts between explainable features and prices. To fill these gaps, this study used machine learning algorithms and SHAP (SHapley Additive exPlanations) to identify the relative importance of air pollutant variables on land values and their non-linear mechanism. The results showed that the Extreme Gradient Boosting (XGBoost) outperformed Ordinary Least Squares (OLS), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), K-Nearest Neighbors (K-NN), and Extra Tree Regression (ETR) models in price prediction and capturing the non-linear relationship between air pollution and land values. Notably, Ozone (O 3) and Nitric Oxide (NO) concentrations contribute 1.64% and 1.47% to land value variation, respectively. The results confirmed the non-linear relationship and identified that the threshold effect between air pollution and land values is at mean concentration values. Furthermore, we observed that the negative influence of O 3 and NO on land values appears as their concentration level is higher than 29.3 and 13 ppb, respectively. This paper contributes valuable insights by advancing our understanding of the non-linear mechanism impact of air pollution on house and land values, informing environmental policymaking, and shedding light on housing decisions. [ABSTRACT FROM AUTHOR]

This paper focuses on a comprehensive solution for dry municipal solid waste (MSW) management with describes the scenario of the gasification process. For this purpose, the potential of implementing the MSW gasification process in Southeast Asia (Iran) with three agents of air, steam, and air-steam is investigated. In order to manage the MSW gasification process as accurately as possible in the study area, a thermodynamic, exergy, economic, environmental, carbon footprint, water footprint, ecological emergy, and risk assessment for the three mentioned gasification agents were carried out in the most populated cities of Iran. In the capital of Iran (Tehran) with the largest population and as a result of largest MSW production, the potential of the gasification process has been investigated at different times (10 consecutive years and 12 months of a year). Finally, by combining artificial neural networks and genetic programming, comprehensive relationships have been established to predict the thermodynamic conditions of gasification with an air-steam agent. The general results of the survey indicate that gasification with air agents has good potential for most regions. The use of the steam agent has created worse economic, environmental, and risk conditions than the other two agents. Investigating the potential of the gasification process in Tehran shows that this city has a good potential to implement this process compared to other cities in Iran, and the most suitable location for establishing the gasification process is the 4th region of this city. [Display omitted] • Potential of municipal solid waste (MSW) gasification for all Iranian cities. • Comparison of using air, steam, and air-steam agents for MSW gasification. • The payback period of air agent MSW gasification is lower than other agents. • Machine Learning used for prediction of the behavior of MSW gasification. [ABSTRACT FROM AUTHOR]

The efficient distribution and timely vaccine delivery to the masses during any pandemic situation require reliable and efficient vaccine cold chain management (VCCM). Therefore, the present study is an effort to explore the factors of VCCM to develop a sustainable and resilient healthcare delivery system in any health outbreak. The factors of VCCM are scrutinized using Fuzzy-Delphi method and then prioritized adopting Fuzzy-Analytical Hierarchy Process (F-AHP) approach while considering the stakeholders' inputs. Finally, factors are categorized into clusters by implementing a machine learning tool ' k -means clustering' algorithm. The results of the study are further validated by conducting extended robustness tests. The findings of the study highlight the factors, namely, cold chain infrastructure, vaccine storage guidelines and availability of skilled professionals as the most important for VCCM. The ′ k -means clustering' algorithm analysis classifies all the 16 factors into three clusters: continuous process improvement (including eight factors), stakeholders' coordination (five factors) and maximum resource utility (three factors). The study can be significantly useful to VCCM decision-makers to implement the prioritized factors by ensuring the advanced cold chain infrastructure and issuing special storage and distribution guidelines to fight against health outbreaks like COVID-19. This is one of the few papers to discuss the factors of VCCM for developing a sustainable and resilient healthcare delivery system in the context of pandemics and stakeholders can address the factors in different clusters at a time. [Display omitted] • Vaccine cold chain management (VCCM) to develop a resilient healthcare delivery system during health outbreaks. • Prioritization of factors of VCCM using Fuzzy-Analytic Hierarchy Process approach. • Categorization of factors of VCCM by implementing a machine learning tool of K − m e a n s clustering algorithm. • Storage and distribution guidelines to fight against the COVID-19 outbreak. [ABSTRACT FROM AUTHOR]

Determining the rural domestic water consumption (RDWS, L/person-day) and rural sewage production (RSP, L/person-day) of rural residents at the county scale can provide decision support for rural domestic sewage treatment. However, methods for predicting county-scale RDWS and RSP based on geographical, social, and governance factors are rarely reported. This paper proposes an RDWS and RSP prediction method based on Automated Machine Learning (AutoML) for the Inner Mongolia Autonomous Region. The RDWS and RSP in the Inner Mongolia Autonomous Region were successfully predicted from multi-source data. The AutoML model accurately predicted RDWS (mean absolute error = 1.7072, R2 = 0.7759) and RSP (mean absolute error = 0.6580, R2 = 0.65107). Average years of education (AYOS), proportion of resident population, and proportion of elderly and children (POEAC) were key driving factors related to RDWS prediction. The most important factors associated with RSP prediction were AYOS, POEAC, and annual average precipitation (AAP). An explanatory analysis further revealed dependence between the input variables, RDWS, and RSP. The framework was demonstrated to be a practical tool for qualitative and quantitative analyses of rural domestic water consumption and domestic sewage production in the Inner Mongolia Autonomous Region. Overall, this study provides a solution for predicting county-level RDWS and RSP, providing a reference for the design of rural domestic sewage treatment. [Display omitted] • Less than 24% of rural domestic sewage is currently treated in Inner Mongolia. • Planning needs county-scale domestic water consumption and sewage production data. • Best of many models based on data from multiple sources were selected automatically. • Nonlinear relationships between input output variables were quickly revealed. [ABSTRACT FROM AUTHOR]

Reinforcement Learning (RL) provides a pathway for efficiently utilizing the battery storage in a microgrid. However, traditional value-based RL algorithms used in battery management focus on formulating the policies based on the reward expectation rather than its probability distribution. Hence the scheduling strategy is solely based on the expectation of the rewards rather than the distribution. This paper focuses on scheduling strategy based on probability distribution of the rewards which optimally reflects the uncertainties in the incoming dataset. Furthermore, the prioritized experience replay samples of the training experience are used to enhance the quality of the learning by reducing bias. The results are obtained with different variants of distributional RL algorithms like C51, Quantile Regression Deep Q -Network (QR-DQN), Fully Quantizable Function (FQF), Implicit Quantile Networks (IQN) and rainbow. Moreover, the results are compared with the traditional deep Q -learning algorithm with prioritized experienced replay. The convergence results on the training dataset are further analyzed by varying the action spaces, using randomized experience replay and without including the tariff-based action while enforcing the penalties for violating battery SoC limits. The best trained Q -network is tested with different load and PV profiles to obtain the battery operation and costs. The performance of the distributional RL algorithms is analyzed under different schemes of Time of Use (ToU) tariff. QR-DQN with prioritized experience replay has been found to be the best performing algorithm in terms of convergence on the training dataset, with least fluctuation in validation dataset and battery operations during different tariff regimes during the day. [Display omitted] • Distributional reinforcement learning algorithm is utilized with prioritized experience samples. • Performances of a wide variety of distributional reinforcement learning algorithms are benchmarked. • Characteristics include variations in discrete action spaces and penalty on exceeding SoC limits. • The system is trained on one week dataset while tested on the 3-days dataset. • Battery technology implications have been discussed with respect to various algorithms. [ABSTRACT FROM AUTHOR]

Forward Osmosis (FO) has emerged as a highly promising membrane-based water treatment process owing to its intrinsic advantages, such as low energy requirements and the potential for high water recovery. The lab-prepared highly efficient thin film composite (TFC) FO membranes that were used in this research work. The resultant polyamide-based FO membrane showed exceptional performance, notably achieving a high-water flux of 60.94 ± 3.5 L/m2.h and a constrained solute flux of 1.52 ± 0.08 g/m2.h. Machine learning methodologies are strategically employed in this study to construct predictive models for FO membrane performance. Notably, the accuracy of the van't Hoff equation's linear assumption is significantly enhanced by introducing an osmotic pressure calculation based on water activity, considering the nuanced effects of external and internal concentration polarization. The research employs MATLAB software alongside an artificial neural network (ANN) to develop predictive models. MATLAB facilitates the creation of a comprehensive theoretical model, offering insights into forecasting water flux through FO membranes by systematically analyzing diverse membrane parameters and their impact on performance. Concurrently, the ANN model was employed to predict the permeate flux for the laboratory-scale FO membrane system, utilizing the input parameters within the network's training range (R2 > 0.91). An economic assessment is also conducted to estimate the projected membrane cost, a pivotal determinant of system viability. Collectively, these investigations yield valuable insights into the intricacies of FO membrane design and optimization, elucidating their performance dynamics in water treatment and allied applications. This research significantly contributes to the ongoing quest to develop more efficient and precise membrane processes. [Display omitted] [ABSTRACT FROM AUTHOR]