新质生产力对海洋经济碳排放的影响因素与深度学习机器学习预测

Exploring the development laws of new quality productivity and leveraging its role in empowering marine economy high-quality development (MEHQ) is of great significance for promoting the construction of a maritime power in China, achieving the goals of Chinese-style modernization and solidifying the country’s advantages in marine economic development. This paper systematically reviews the mechanisms and effects of new quality productivity (NQP) in empowering MEHQ. Using panel data from 17 cities along the Bohai Sea from 2010 to 2022, we comprehensively measure the combined levels of NQP and MEHQ. Employing various statistical analysis methods, including benchmark regression models, multiple mediation effect models, and spatial Durbin models, we empirically test the mechanisms and spatial spillover effects of NQP in empowering MEHQ. The results indicate that NQP has a significant positive driving effect on MEHQ, and this conclusion remains valid after a series of robustness tests. The empowering effect of NQP on MEHQ mainly occurs through three pathways: marine technological innovation, optimization of marine industrial structure, and improvement of marine resource allocation efficiency. There is a positive correlation between NQP and MEHQ, with significant agglomeration phenomena, reflecting the non-uniform characteristics of spatial distribution. NQP not only empowers MEHQ but also exhibits significant spatial spillover effects, promoting MEHQ in adjacent regions and releasing growth dividends.

The marine economy’s new quality productive forces is an important driving force to promote the high-quality development of the marine economy. Exploring the level of marine economy’s new quality productive forces and its spatiotemporal evolution law will help to provide solid theoretical support and empirical basis for formulating scientific strategies to promote the accelerated development of marine economy. Based on panel data from 11 coastal provinces and cities from 2010 to 2022, this study applies the entropy value method to measure the level of marine economy’s new quality productive forces, and then uses the Dagum Gini coefficient and its decomposition, kernel density estimation method and spatial Markov chain model to reveal its regional differences and spatiotemporal evolution characteristics. The results of the study showed that: (1) The level of marine economy’s new quality productive forces in China and the three major marine economic circles (northern, eastern and southern) have grown annually, but regional imbalances are increasing. Among the constituent elements, scientific and technological productive forces exhibited the strongest growth momentum, while the development of green productive forces relatively lagged behind. (2) The level of marine economy’s new quality productive forces in individual provinces deviates significantly from the national average, resulting in supervariable density becoming the main source of spatial differentiation of marine economy’s new quality productive forces level. (3) Except for the eastern marine economic circle, other regions generally show obvious polarization, which not only limits the effective allocation of resources, but also affects the rational flow and transfer of new quality productive forces levels between different regions. In this regard, relevant policy recommendations are put forward: (1) The implementation of differentiated strategies promotes the regional adaptive development of marine economy’s new quality productive forces. (2) Strengthening internal and external linkage mechanisms to release the spillover effect of the marine economy’s new quality productive forces. (3) Science and technology drive green development and enhance the green content of marine economy’s new quality productive forces.

… identification results and the historical data of carbon emissions to complete the corresponding carbon emission data fitting. Finally, carbon emission data from the past three years in …

… (AI) and machine learning (ML) techniques, focusing on physics-informed neural networks (PINNs) methods and their transformative application to maritime systems. PINNs integrate …

This study introduces an innovative Emotional Artificial Neural Network (EANN) model to predict ship fuel consumption with high accuracy, addressing the challenges posed by complex environmental conditions and operational variability. This research examines the impact of climate change on maritime operations and fuel efficiency by analyzing climatic variables such as wave period, wind speed, and sea-level rise. The model’s performance is assessed using two ship types (bulk carrier and container ship with max 60,000 dead weight tonnage (DWT)) under various climate scenarios. A comparative analysis demonstrates that the EANN model significantly outperforms the conventional Feedforward Neural Network (FFNN) in predictive accuracy. For bulk carriers, the EANN achieved a Root Mean Squared Error (RMSE) of 5.71 tons/day during testing, compared to 9.91 tons/day for the FFNN model. Similarly, for container ships, the EANN model achieved an RMSE of 5.97 tons/day, significantly better than the FFNN model’s 10.18 tons/day. A sensitivity analysis identified vessel speed as the most critical factor, contributing 33% to the variance in fuel consumption, followed by engine power and current speed. Climate-change simulations showed that fuel consumption increases by an average of 22% for bulk carriers and 19% for container ships, highlighting the importance of operational optimizations. This study emphasizes the efficacy of the EANN model in predicting fuel consumption and optimizing ship performance. The proposed model provides a framework for improving energy efficiency and supporting compliance with International Maritime Organization Standards (IMO) environmental standards. Meanwhile, the Carbon Intensity Indicator (CII) evaluation results emphasize the urgent need for measures to reduce carbon emissions to meet the IMO’s 2030 standards.

… footprint, GHG emissions, population growth, economic growth, and how these factors interact with one another to support BE, and the responsible use of ocean … deep neural networks (…

Berthing operation heterogeneity across ship types causes significant uncertainty in assessing port congestion and carbon emissions over comparable timeframes. This study quantifies in-port emission dynamics for four cargo ship types (container, liquid bulk, dry bulk, and general cargo) using an operational phase-specific emission accounting model. We propose a hybrid deep learning model that integrates Two-Dimensional Convolutional Neural Networks (2DCNN) with Squeeze-and-Excitation Attention Mechanisms (SEAM) and Bidirectional Long Short-Term Memory Networks (BiLSTM) layers, optimized via the Triangulation Topology Aggregation Optimizer (TTAO) for hyperparameter tuning. Empirical analysis at Ningbo Zhoushan Port shows that liquid bulk carriers emit 23–41% more than other ship types due to extended auxiliary engine/boiler use during cargo handling. The 2DCNN-SEAM model significantly improves BiLSTM prediction accuracy—reducing Mean Absolute Percentage Error (MAPE) by 18.7% and increasing the R2 value to 0.94—by effectively capturing spatiotemporal congestion features. Results confirm that operational congestion is a critical emission multiplier, especially for ships requiring prolonged auxiliary system use during berthing. These insights inform targeted decarbonization strategies for port authorities, prioritizing operational efficiency and energy transition for high-emission ship categories.

Zero-carbon shipping is the prime goal of the seaborne trade industry at this moment. The utilization of ammonia and liquid hydrogen propulsion in a carbon-free propulsion system is a promising option to achieve net-zero emission in the maritime supply chain. Meanwhile, optimal ship voyage planning is a candidate to reduce carbon emissions immediately without new buildings and retrofits of the alternative fuel-based propulsion system. Due to the voyage options, the precise prediction of fuel consumption and carbon emission via voyage operation profile optimization is a prerequisite for carbon emission reduction. This paper proposes a novel fuel consumption and carbon emission quantity prediction method which is based on the onboard measurement data of a smart ship. The prediction performance of the proposed method was investigated and compared to machine learning and LSTM-model-based fuel consumption and gas emission prediction methods. The results had an accuracy of 81.5% in diesel mode and 91.2% in gas mode. The SHAP (Shapley additive explanations) model, an XAI (Explainable Artificial Intelligence), and a CO2 consumption model were employed to identify the major factors used in the predictions. The accuracy of the fuel consumption calculated using flow meter data, as opposed to power load data, improved by approximately 21.0%. The operational and flow meter data collected by smart ships significantly contribute to predicting the fuel consumption and carbon emissions of vessels.

… optimal prediction performance, we introduce the econometric (EC) and machine learning (… and assessing their applicability in predicting CO 2 emissions from global shipping based on …

PurposeTo achieve sustainable development in shipping, accurately identifying the impact of artificial intelligence on shipping carbon emissions and predicting these emissions is of utmost importance.Design/methodology/approachA multivariable discrete grey prediction model (WFTDGM) based on weakening buffering operator is established. Furthermore, the optimal nonlinear parameters are determined by Grey Wolf optimization algorithm to improve the prediction performance, enhancing the model’s predictive performance. Subsequently, global data on artificial intelligence and shipping carbon emissions are employed to validate the effectiveness of our new model and chosen algorithm.FindingsTo demonstrate the applicability and robustness of the new model in predicting marine shipping carbon emissions, the new model is used to forecast global marine shipping carbon emissions. Additionally, a comparative analysis is conducted with five other models. The empirical findings indicate that the WFTDGM (1, N) model outperforms other comparative models in overall efficacy, with MAPE for both the training and test sets being less than 4%, specifically at 0.299% and 3.489% respectively. Furthermore, the out-of-sample forecasting results suggest an upward trajectory in global shipping carbon emissions over the subsequent four years. Currently, the application of artificial intelligence in mitigating shipping-related carbon emissions has not achieved the desired inhibitory impact.Practical implicationsThis research not only deepens understanding of the mechanisms through which artificial intelligence influences shipping carbon emissions but also provides a scientific basis for developing effective emission reduction strategies in the shipping industry, thereby contributing significantly to green shipping and global carbon reduction efforts.Originality/valueThe multi-variable discrete grey prediction model developed in this paper effectively mitigates abnormal fluctuations in time series, serving as a valuable reference for promoting global green and low-carbon transitions and sustainable economic development. Furthermore, based on the findings of this paper, a grey prediction model with even higher predictive performance can be constructed by integrating it with other algorithms.

… machine learning in ship black carbon emission prediction and could provide references for reducing ship black carbon emissions and the formulation of emission … finance, industry, and …

Accurate prediction of CO 2 emissions from maritime transportation is critically important for environmental sustainability and effective regulatory action. In this study, hourly CO 2 …

Ship emissions are a significant source of atmospheric black carbon (BC) aerosols, impacting both human health and climate, particularly in nearshore marine environments. However, …

… -CBAMNet, a deep learning model integrating channel and spatial attention mechanisms to … spatiotemporal emission trends. The model significantly outperforms four deep learning …

… the “dual carbon” goal. In this study, we measured the marine fishery carbon emission efficiency in the … We analyzed the spatial–temporal variation characteristics of marine fishery …

… feature extraction of vessel carbon emissions. To validate the feasibility of … carbon emissions are obtained. This study reveals the temporal and spatial distribution of carbon emissions …

Quantifying and understanding changes in carbon emissions is essential for the U.S. shipping industry to reduce carbon emissions, especially after its return to the Paris Agreement. We estimated carbon emissions from 48,321 ships in the U.S. Exclusive Economic Zone (EEZ) using the power-based method based on 3.6 billion Automatic Identification System (AIS) reports. We explored the characterization of carbon emissions from the national, regional, and port levels during 2019-2021 by allocating emissions on a 1 km*1 km grid through an activity-weighted method. The results show: (1) Due to the COVID-19 pandemic, emissions within the EEZ show a temporal trend of decreased and then rebound, specifically from 32.628 Tg in 2019 to 30.741 Tg in 2020 and then bouncing to 31.786 Tg in 2021. The spatial differences in emissions show significant heterogeneity; (2) There are significant differences in emissions by vessel type, flag, and operational mode for the four regions of the U.S. (Great Lakes, Gulf Coast, Pacific Coast, and Atlantic Coast). Thus, these regions' emissions show different variability patterns over three years. Notably, "port congestion" led to record high emissions on the Pacific Coast; (3) Containerized cargo contributes the most to port core area emissions, so most ports with higher throughputs have higher emissions, with Long Beach and Los Angeles having the highest. Emissions from coastal ports are high and volatile, while inland ports are low and stable. This study provides the U.S. with a high spatiotemporal resolution inventory of carbon emissions from ships, and the findings are expected to provide some reference for controlling ship emissions.

With the intensification of global climate change, the discerning identification of carbon emission drivers and the accurate prediction of carbon emissions have emerged as critical components in addressing this urgent issue. This paper collected carbon emission data from Chinese provinces from 1997 to 2021. Machine learning algorithms were applied to identify province characteristics and determine the influence of provincial development types and their drivers. Analysis indicated that technology and energy consumption had the greatest impact on low-carbon potential provinces (LCPPs), economic growth hub provinces (EGHPs), sustainable growth provinces (SGPs), low-carbon technology-driven provinces (LCTDPs), and high-carbon-dependent provinces (HCDPs). Furthermore, a predictive framework incorporating a grey model (GM) alongside a tree-structured parzen estimator (TPE)-optimized support vector regression (SVR) model was employed to forecast carbon emissions for the forthcoming decade. Findings demonstrated that this approach provided substantial improvements in prediction accuracy. Based on these studies, this paper utilized a combination of SHapley Additive exPlanation (SHAP) and political, economic, social, and technological analysis—strengths, weaknesses, opportunities, and threats (PEST-SWOTs) analysis methods to propose customized carbon emission reduction suggestions for the five types of provincial development, such as promoting low-carbon technology, promoting the transformation of the energy structure, and optimizing the industrial structure.

China's National Ecological Civilization Demonstration Zone (NECDZ) policy has a significant role in ensuring national ecological security, and it is essential to investigate how the NECDZ policy affects the carbon emissions intensity of fisheries (CEIF) to advance China's commitment to reducing carbon emissions. This study evaluates the CEIF in 30 Chinese provinces from 2007 to 2021 using ecological civilization demonstration areas as a quasi-natural experiment and double machine learning (DML)to examine the impact and internal mechanisms of NECDZ implementation on the CEIF. We also explore spatial spillover effects using a spatial difference-in-differences approach. The results reveal that NECDZ implementation has a significantly negative impact on the CEIF and this effect continues over time. NECDZ policy potentially affects the CEIF through technology development, industrial structure improvement, and reduced energy consumption. Further investigation reveals that NECDZ implementation has spillover effects and inhibits the CEIF in surrounding regions. Therefore, it is essential to focus on developing the NECDZ policy to enhance fisheries' industrial structure, encourage low-carbon innovation in fishery technologies, and increase energy consumption efficiency. This could be supported by facilitating exchanges and cooperation with other areas, considering regional disparities, and assigning common but distinct responsibility for reducing the CEIF.

In this study, the green development of marine economy driven by marine scientific and technological innovation is empirically studied and the influencing factors are analyzed. The results show that the development of marine science and technology is significantly positively correlated with the green development of marine economy as a whole, and each input variable has a promoting effect on economic development, but with varied degree of effect. The analysis on the growth models of “Circum-Bohai Sea Economic Zone,” “Yangtze River Delta Economic Zone” and “Pearl River Delta Economic Zone” shows that at present, science and technology in each marine economic zone play an obvious role in promoting economic development, and each input variable plays a different role in promoting the green development of regional marine economy. With the help of threshold panel model, the influences of five factors, namely opening to the outside world, government investment, financial development, human capital and technology investment, on the green development of marine economy driven by marine scientific and technological innovation are investigated, and it is concluded that all kinds of external influencing factors will interfere with the role of marine scientific and technological innovation and achieve the effect of promoting or restricting it.

… To integrate the concept of low-carbon and green development into the … carbon emissions at the marine level, and predicts the development trend of carbon emissions from marine …

Maritime transportation is one of the essential drivers of the global economy as it enables both lower transportation costs and intermodal operations across multiple forms of transportation. Maritime ports are essential interfaces that support cargo handling between sea and hinterland transportation. Besides, in this area, environmental protection is becoming extremely important. Global warming, air pollution, and greenhouse gas emissions are all having a detrimental influence on the environment and will most likely continue to do so for future generations. Hence, there is a growing need to promote environmental sustainability in maritime-based transportation. The application of machine learning (ML), as one of the main subdomains of artificial intelligence (AI), can be considered a component within the process of digital transformation to advance green activities in maritime port logistics. Thus, this article presents the results of a systematic literature review of the recent literature on machine learning for promoting environmentally sustainable maritime ports. It collects and analyses the articles whose contributions lie in the interplay between three main dimensions, i.e., machine learning, port-related operations, and environmental sustainability. Throughout a review protocol, this research is constituted on the major focuses of impact, problems, and techniques to discern the current state of the art as well as research directions. The research findings indicate that the articles using polynomial regression models are dominant in the literature, and the recurrent neural network (RNN) and long short-term memory (LSTM) are the most recent approaches. Moreover, in terms of environmental sustainability, emissions and energy consumption are the most studied problems. mAccording to the research gaps observed in the review, two broad directions for future research are identified: (i) altering attention on a greater diversity of machine learning approaches for promoting environmental sustainability in ports and (ii) leveraging new outlooks to perform more green practical works on port-related operations.

As Digital Industry 4.0 advances, shipping operators are progressively implementing digital technologies for maritime decarbonization efforts.This review employs a bibliometric methodology to thoroughly examine and analyze the application of digital technology in decarbonizing shipping from 2005 to 2024. Examining 201 publications from the SCI-EXPANDED and SSCI databases elucidates the present condition, challenges, and prospects of digital technology applications in this domain.The review demonstrates the swift expansion of research on digital technologies for decarbonization within the shipping sector via an analysis of annual publication trends. Subsequent journal metrics and collaborative network analysis with VOSviewer identified particularly prolific journals, nations, institutions, and authors. Furthermore, this review delineates the field's principal research clusters and hotspots via keyword co-occurrence analysis, offering direction for future investigations. Ultimately, it examines research gaps in speed optimization, emission prediction, and autonomous ships by integrating keyword co-occurrence analysis with the content of recent publications, and then proposes prospective research options.Future studies on ship speed optimization could benefit from adopting multi-objective optimization methods, combining more machine-learning techniques with the FCP model, etc. Concerning emission prediction, future research efforts could focus on integrating more diverse external data sources into emission prediction models, adopting emerging technology applications, such as ship-based carbon capture (SBCC), introducing blockchain into smart emission monitoring systems, etc. Future research regarding autonomous ships can further refine optimizing route planning and navigation safety, autonomous ship energy efficiency and emission control, maritime communications and navigation systems, ship electrification, and green design.

… ships and marine structures. It serves critical roles in shipping… This stems from the industry's high-carbon emission nature, … improvement and process upgrading technologies, with …

… 2) To identify the most significant predictors of carbon emissions through supervised machine learning models, accounting for multicollinearity and complex interactions. 3) To evaluate …

… fixed Durbin model should be selected for empirical research, So all spatial econometric tests … To further investigate the spatial correlation between ocean and inland fishery product …

How does digital infrastructure influence synergistic effect on reducing pollution and carbon emissions? A new method based on double machine learning - ScienceDirect …

… integrates machine learning with … double machine learning (DML) to estimate causal effects. We showcase its use for the Earth sciences on two problems related to carbon dioxide fluxes…