Advanced computing to support urban climate neutrality

The increasing complexity of urban transportation systems and the growing volume of vehicles have made traffic congestion a persistent challenge in modern cities. Efficient traffic flow prediction is essential for mitigating congestion, improving road safety, optimizing traffic signal control, and enhancing overall transportation efficiency. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the field of traffic management, offering sophisticated algorithms capable of modeling, analyzing, and predicting complex traffic patterns with high accuracy. The application of AI in traffic flow prediction leverages vast amounts of real-time and historical data to generate precise forecasts, supporting data-driven decision-making by urban planners and traffic control authorities. The prediction of traffic flow involves analyzing time-series data that exhibit nonlinear, dynamic, and often stochastic behavior. Traditional statistical models, such as autoregressive integrated moving average (ARIMA), have proven to be limited in handling the high dimensionality and variability inherent in traffic systems. In contrast, AI algorithms possess the capacity to learn and adapt from complex data inputs without the need for explicit programming, making them particularly suitable for traffic-related applications. AI algorithms used in traffic flow prediction can be broadly categorized into machine learning (ML) and deep learning (DL) approaches. Machine learning algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), decision trees, and random forests have demonstrated effectiveness in short-term traffic prediction tasks. These algorithms are capable of identifying hidden patterns in traffic data and adjusting to changes in traffic behavior over time. Ensemble methods, which combine the strengths of multiple learning models, further enhance prediction accuracy and robustness. Deep learning algorithms, a subfield of AI inspired by the human brain’s neural architecture, have shown exceptional performance in capturing spatial-temporal dependencies in traffic data. Recurrent neural networks (RNNs), particularly long short-term memory (LSTM) networks and gated recurrent units (GRUs), are widely used for their ability to process sequential data and retain information over extended time intervals. Convolutional neural networks (CNNs) are employed to extract spatial features from traffic sensor data or road network imagery. Hybrid models that integrate CNNs with RNNs have achieved high levels of predictive precision by simultaneously learning spatial and temporal correlations. In addition to supervised learning methods, unsupervised and reinforcement learning techniques are also applied in traffic flow prediction. Clustering algorithms, such as k-means and DBSCAN, assist in identifying traffic patterns, while reinforcement learning models optimize adaptive traffic signal control systems by learning optimal actions through environmental interaction. This study explores the different types of AI algorithms used in traffic flow prediction, examining their theoretical foundations, structural differences, and practical applications. It aims to evaluate the comparative advantages of various algorithms in addressing the challenges of real-time traffic prediction in increasingly complex transportation networks.

To establish a pathway consistent with future development of a green, low-carbon, and environmentally friendly economy in Shaoxing, from the perspective of the synergistic effect of carbon-pollutant, this study evaluates the current performances of pollution reduction and carbon mitigation in Shaoxing based on carbon-pollution synergy and also analyzes the synergy effects and the driving factors of carbon and pollutant emissions, aiming to provide a reference for carbon peaking and synergistic carbon-pollutant emission reductions. The results indicated that during the 13th Five-Year Plan period, Shaoxing demonstrated strong synergy in carbon and pollution reduction efforts. The city has enhanced its energy-related carbon emission efficiency and gradually increased the decoupling level between carbon emissions and economic growth. The driving factors and their contributions to both carbon and atmospheric pollutant emissions were largely similar: Economic growth and population size contributed to emission increase, while carbon-pollutant emission efficiency and energy intensity effects contributed to emission reductions. Based on this and considering the current development model and future plans of the city, different carbon emission scenarios were set using the LEAP model. Under the baseline scenario, Shaoxing is expected to reach its carbon peak by 2030, while under a high-energy scenario, peaking may be delayed until 2035. However, with the implementation of more stringent carbon reduction policies, it is possible to achieve an earlier peak. The promotion of strong low-carbon policies, accelerated adjustments to energy and industrial structures, increased investment in low-carbon and renewable energy technologies, and improvements in energy efficiency can effectively facilitate the pursuit of synergistic carbon and pollution reduction in Shaoxing, thus accelerating the implementation of its dual-carbon strategy.

The transition to passenger car electrification is a crucial step in China’s strategic efforts to achieve carbon peak and carbon neutrality. However, previous research has not considered the variances in vehicle models. Hence, this study aims to fill this gap by comparing the carbon emission reduction and economic feasibility of battery electric vehicles (BEVs) in the Chinese market, taking into account different powertrains, vehicle segments, classes, and driving ranges. Next, the study identifies the most cost-effective BEV within each market segment, employing life-cycle assessment and life cycle cost analysis methods. Moreover, at different levels of technological development, we construct three low-carbon measures, including electricity decarbonization (ED), energy efficiency improvement (EEI), and vehicle lightweight (LW), to quantify the emission mitigation potentials from different carbon reduction pathways. The findings indicate that BEVs achieve an average carbon reduction of about 31.85% compared to internal combustion engine vehicles (ICEVs), demonstrating a significant advantage in carbon reduction. However, BEVs are not economically competitive. The total life cycle cost of BEVs is 1.04–1.68 times higher than that of ICEVs, with infrastructure costs accounting for 18.8–57.8% of the vehicle’ s life cycle costs. In terms of cost-effectiveness, different models yield different results, with sedans generally outperforming sport utility vehicles (SUVs). Among sedans, both A-class and B-class sedans have already reached a point of cost-effectiveness, with the BEV400 emerging as the optimal choice. In low-carbon emission reduction scenarios, BEVs could achieve carbon reduction potentials of up to 45.3%, 14.9%, and 9.0% in the ED, EEI, and LW scenarios, respectively. Thus, electricity decarbonization exhibits the highest potential for mitigating carbon emissions, followed by energy efficiency improvement and vehicle lightweight. There are obvious differences in the stages of impact among different measures. The ED measure primarily impacts the waste treatment process (WTP) stage, followed by the vehicle cycle, while the EEI measure only affects the WTP stage. The LW measure has a complex impact on emission reductions, as the carbon reductions achieved in the WTP stage are partially offset by the increased carbon emissions in the vehicle cycle.

Against the backdrop of global carbon neutrality goals and urban low-carbon transformation, the coupling of green infrastructure and carbon emission performance has become a core issue. This paper aims to systematically analyze and discuss the low-carbon city construction research influencing green infrastructure (GI) and urban carbon emission performance, taking Kunming as an example. Through research and analysis, GI, as a key low-carbon infrastructure, operates through a dual pathway of "carbon sequestration" and "emission reduction." Carbon sequestration can be achieved through plant photosynthesis, while emission reduction can reduce urban carbon intensity by regulating microclimate, guiding green transportation, and replacing grey infrastructure. Taking Kunming as an example, by implementing the concepts of "nature integration" and "nature governance," it was found that treating GI as "natural capital" is a powerful support for urban carbon neutrality and resilient development, and a key to achieving long-term low-carbon benefits. Kunming will continue to improve its low-carbon development model, promote the coordinated construction of carbon neutrality and resilient cities, and contribute to high-quality development in society, ecology, and economy.

With the acceleration of urbanization and the continuous growth of traffic flow, accurate prediction of highway traffic flow has become a key demand for optimizing traffic management and alleviating congestion. Traditional prediction methods are often inefficient in dealing with complex traffic patterns, while deep learning technology brings new solutions for traffic flow prediction with its powerful feature learning and pattern recognition capabilities. This paper reviews deep learning applications' current state and future trends in highway traffic flow prediction. It introduces deep learning technology and its advantages in traffic flow prediction. The paper then analyzes the specific applications of Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and their variants in data processing, feature extraction, and prediction performance. The challenges currently faced, such as data preprocessing and the capture of long-term dependencies, are also discussed, along with proposed solutions. Finally, the paper looks forward to the future development of deep learning in the field of traffic flow prediction, highlighting its importance in improving traffic management efficiency.

Thailand has established a target of carbon neutrality by 2050. Reaching this goal will require coordination and collaboration between stakeholders spanning sectors and scales, including energy system decision makers, land managers, and city planners. Robust decarbonization scenarios incorporating current plans and targets, additional measures needed, and trade-offs between strategies can help stakeholders make informed decisions in the face of uncertainty. Through iterative engagement with decision makers at the city and national levels, we develop and analyze carbon neutral scenarios for Thailand that incorporate Bangkok’s role using a global integrated assessment model. We find that Thailand can reach carbon neutrality through power sector decarbonization, energy efficiency improvements, widespread electrification, and advanced technologies including carbon capture and storage and hydrogen. Negative emissions technologies will also be needed to offset Thailand and Bangkok’s hardest-to-abate CO2 emissions. Bangkok, as a major population and economic center, contributes significantly to Thailand’s energy demand and emissions and can therefore play an important role in climate change mitigation. Accordingly, our results underscore the importance of subnational climate action in meeting Thailand’s carbon neutral goal. Our analysis also indicates that without sustained land-based carbon sequestration, much more mitigation effort will be needed in Thailand’s energy sector, including at the subnational scale, to reach carbon neutrality. These insights can help stakeholders identify priorities, consider tradeoffs, and make decisions that will impact Bangkok and Thailand’s long-term climate change mitigation potential. This analysis demonstrates how stakeholder engagement in integrated assessment modeling can facilitate and inform multilevel climate governance.

With the intensification of global climate change, carbon neutrality has become a crucial objective for achieving sustainable development, which critically requires systematic technological innovation and collaborative cooperation between technologies and countries. Through categorization and comprehensive technological assessments, a thorough examination of relevant technologies can furnish a framework to guide emission reduction efforts across various sectors. This review seeks to explore the methods by which various countries achieve carbon neutrality technology systems and pathways, with an in-depth study of the differences between the technological approaches and systems in China, the United States, and European countries. The construction of technology systems in several countries is reviewed, from the composition of the systems to the assessment of technologies that include indicators such as carbon reduction potential. Building upon an analysis of key technological pathways in renewable energy, carbon capture, utilization and storage, energy efficiency improvement, and hydrogen energy across different countries, a systematic evaluation is conducted from three key dimensions—policy formulation, resource endowment, and industrial foundation—to identify the similarities, differences, and driving factors in the construction of carbon neutrality technology systems among nations. Based on the previous work, we conducted a comparative analysis and summary of carbon neutrality pathways across various countries worldwide, systematically reviewing and evaluating carbon neutrality technologies in power generation, industry, transportation, and building sectors. Building upon these findings, the study offers recommendations for coupling diverse technological approaches and for international cooperation. By comparing international experiences and practices, this study provides operational references for countries in formulating technology planning and emission reduction strategies, and also provides an important basis for deepening global carbon neutral cooperation in the future.

In order to achieve China’s carbon peaking and carbon neutrality (double carbon) targets and to advance ecological conservation and high-quality development in the Yellow River Basin, it is essential that China reduces its energy intensity and increases its energy efficiency. This research developed an evaluation index system for energy efficiency and green development in the Yellow River Basin based on panel data collected from 64 of its prefecture-level cities and covering the period from 2011 to 2020. Each city’s energy efficiency and green development level index was calculated, and was analyzed together with the characteristics of its spatial pattern progression. The STIRPAT model was then used to investigate the influence mechanism of energy efficiency on green development. The final step in the analysis was to assess the process by which technical innovation influences the rise in energy efficiency from a green development point of view. The findings of this study indicate that: (1) There was a marked improvement in energy efficiency and green development levels across the Yellow River Basin over the study period of 2011 to 2020, but there are notable disparities among prefecture-level cities, with higher levels found in capital cities and cities in the lower reaches of the basin. (2) The improvement in energy efficiency has had a positive impact on the transition to green development, with factors such as human capital, urbanization levels, and the upgrading of industrial structures contributing significantly, while the level of foreign direct investment has had a limited impact. (3) Technological innovation plays a partial role in mediating the relationship between energy efficiency and green development in the Yellow River Basin, and passes the single-threshold test. When technological innovation surpasses the threshold value, the effect of energy efficiency on green development is significantly strengthened. This study indicates that improving energy efficiency, stimulating emerging industries, and enhancing technological innovation capabilities can significantly promote transformative green and high quality development in the Yellow River Basin of China.

By the end of 2020, most countries in the world have successively proposed carbon-neutral targets. Among them, the major economies in the world, such as the United States (USA), the European Union, Japan, and Canada, have proposed to achieve carbon-neutral targets by 2050. As the world’s largest carbon emitter, China has a total carbon emissions of more than 11.3 billion tons, accounting for about 30% of global carbon emissions. Therefore, the carbon emission reduction required for China is much higher than that of other economies, and its carbon-neutral tasks are obviously more complex and diversified. On 22 September 2020, the Chinese government announced in the 75th Session of the UN (United Nations) General Assembly (New York, USA) that China aims to achieve carbon neutrality before 2060. The announcement of the carbon-neutral target clearly indicated that China needs to carry out a self-revolution to achieve zero CO2 emissions before 2060. The concept of carbon neutrality is essentially a balance between carbon sources and carbon sinks. The carbon source is the process of releasing CO2 into the atmosphere, and the carbon sink is the process of absorbing CO2 from the atmosphere. Investigating the atmospheric system within a certain period, when the amount of CO2 emitted by all carbon sources into the system is equal to the amount of CO2 absorbed by all carbon sinks from the system, carbon neutrality can be achieved. There are various carbon sources and sinks in nature with complicated relationships. Among them, the most important carbon source related to human activities is energy production. In 2020, China’s power sector emitted about 4 billion tons of CO2 per year, which is close to 40% of the total emissions. Thus, the power sector is one of the key areas in emission reduction to achieve the carbon-neutral goal. Building a carbon-neutral power system is the only way to achieve decarbonization in the energy sector. Based on the carbon balance principle, this paper proposed the critical equation of carbon neutrality for power systems. And the further strategies in establishing a carbon-neutral power system were explored according to the carbon neutrality equation: (1) Improve energy efficiency thus reducing the consumption of carbonaceous energy; (2) adjust the energy structure and reduce the proportion of carbonaceous energy; (3) rebuild the balance of sources and sinks by adopting CO2 capture, utilization and storage (CCUS) technology to achieve low-carbon utilization of carbonaceous energy. Results indicate that, although improving energy efficiency of carbonaceous energy is effective in CO2 mitigation, it is limited by the declining energy saving potential of thermal power plants to be the main technical way in carbon emission reduction. Besides, increasing the proportion of renewable energy can quickly reduce the carbon emission intensity of the power system, which is currently the main technical way to reduce the CO2 emission of the power system. However, although energy conservation and the development of renewable energy can reduce the carbon emission intensity of the power system, the CCUS technology and the negative emission technology will be indispensable to achieve the goal of carbon neutrality. And the large-scale promotion of the CCUS technology must overcome technical obstacles of the rather high energy consumption of CO2 capture. Thus, building a carbon-neutral power system in the future requires a combination of energy efficiency, renewable energy and CCUS technology.

Data analytics is a key factor to make fully informed and data-driven decisions in modern manufacturing companies. With increasing international competition, classical approaches to data analytics have to be enhanced toward advanced data analytics to create smarter products, production processes and customer services. This leverages the full potential of the data to quickly gain insights and make decisions. Application areas include predictive analytics, augmented analytics and real-time analytics. In this paper an advanced data analytics platform (ADAP) for manufacturing companies is presented and verified on a real-world production line. ADAP combines process data obtained in a physical environment with domain knowledge from experts to create data-driven models in a digital environment. In addition, ADAP is well scalable and provides a comprehensible data structure throughout the entire data workflow. ADAP is verified on two different advanced data analytics applications on an electrocoating plant. In order to relate the applications to real production requirements, the needs of local manufactures from the region Ostwestfalen-Lippe (OWL) are taken into account.

Traffic flow has the characteristics of randomness, nonlinearity and periodicity. Using deep learning as the method of traffic flow prediction can make full use of traffic flow characteristics for prediction. In this paper, a recurrent neural network-LSTM (Long Short-Term Memory) model and its variant GRU (Gated Recurrent Units) are used to solve the traffic flow prediction problem. According to the road traffic information collected by the automatic measurement station (LAM) of the Dutch traffic management department, the vehicle traffic flow data has been predicted every five minutes. It’s verified that the GRU traffic flow prediction model performs well by comparing the prediction accuracy of LSTM and GRU.

Short-term traffic flow prediction plays an important role in intelligent transportation system. Numerous researchers have paid much attention to it in the past decades. However, the performance of traditional traffic flow prediction methods is not satisfactory, for those methods cannot describe the complicated nonlinearity and uncertainty of the traffic flow precisely. Neural networks were used to deal with the issues, but most of them failed to capture the deep features of traffic flow and be sensitive enough to the time-aware traffic flow data. In this paper, we propose a deep bi-directional long short-term memory (DBL) model by introducing long short-term memory (LSTM) recurrent neural network, residual connections, deeply hierarchical networks and bi-directional traffic flow. The proposed model is able to capture the deep features of traffic flow and take full advantage of time-aware traffic flow data. Additionally, we introduce the DBL model, regression layer and dropout training method into a traffic flow prediction architecture. We evaluate the prediction architecture on the dataset from Caltrans Performance Measurement System (PeMS). The experiment results demonstrate that the proposed model for short-term traffic flow prediction obtains high accuracy and generalizes well compared with other models.

This study is aimed at addressing key challenges in smart city traffic management systems: traffic flow prediction and congestion point identification, through the development of a deep learning model that integrates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Graph Neural Networks (GNN).The focus of the research was on collecting and preprocessing a large traffic dataset, including traffic camera images, vehicle movement trajectories, and city traffic network information, to train and validate the proposed model.Key findings demonstrate significant performance improvements of the model in traffic flow prediction and congestion point identification tasks over traditional models like ARIMA, as evidenced by higher accuracy, recall, and F1 scores.Furthermore, through generalization capability testing, this study confirmed the model's exceptional adaptability, effectively handling traffic data across different cities and time periods.The key conclusion of this research is that deep learning technology can significantly enhance the accuracy and efficiency of smart city traffic management, providing robust data support for urban traffic planning and scheduling.This discovery lays a foundation for further exploration of deep learning applications in the smart city domain.

To address the issue of spatiotemporal illusion in short-term traffic flow prediction and deeply explore the underlying short-term traffic flow network characteristics, a traffic flow prediction model that combines long-term spatiotemporal heterogeneity with short-term spatiotemporal features is proposed. In the long-term spatiotemporal branch, the Transformer structure is employed, and a self-supervised masking mechanism is utilized to pretrain the heterogeneity in long-term temporal and spatial dimensions separately. Additionally, a spatiotemporal adaptive module is designed, which adapts to and guides short-term traffic flow prediction across time series and traffic flow networks. In the short-term spatiotemporal branch, a recurrent neural ordinary differential equation (ODE) module is devised. This module is capable of continuously and dynamically adjusting short-term spatiotemporal features, better capturing and exploring potential short-term spatiotemporal characteristics. Through multiple cycles, this module gradually and accurately extracts and compresses road network features, integrates the adapted spatiotemporal heterogeneity, and reconstructs future short-term traffic flows in the decoder. Experiments are conducted on four traffic flow and two traffic speed datasets, showing that compared to traditional time series models, the proposed model’s prediction accuracy indicators have relatively improved by 45.09%, 39.14%, and 0.47% on average; compared to recurrent neural network (RNN) series models, the improvements are 18.91%, 15.77%, and 0.18% on average; compared to graph convolution series models, the improvements are 21.31%, 16.65%, and 0.21% on average; and compared to Transformer series models, the improvements are 6.57%, 6.23%, and 0.05% on average. The model’s general applicability and good performance in transportation speed scenarios were verified through a multi-step experiment conducted on the transportation speed dataset.

The growth rate of carbon emissions in resource-based provinces in China is higher than the national average, and the growth of carbon emissions is not isolated from the growth of GDP and energy consumption. Take Shanxi province as an example, this paper comprehensively considers the macro-economic growth, industrial structure adjustment, energy efficiency improvement, electric energy substitution, hydrogen energy development and other factors under the “carbon peak and carbon neutrality” target. And this paper applies the CEMS-4E (China Energy Model System) model system to quantitatively analyse the carbon emissions of resource-based provinces in China and the path of carbon peak energy transformation of resource-based provinces in the future. This paper could provide rationalized suggestions for the development and deployment of a low-carbon economy in China.