Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 23 - 41
Published: Jan. 1, 2024
Language: Английский
Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 23 - 41
Published: Jan. 1, 2024
Language: Английский
Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106333 - 106333
Published: March 1, 2025
Language: Английский
Citations
7Journal of Machine and Computing, Journal Year: 2024, Volume and Issue: unknown, P. 1140 - 1151
Published: Oct. 5, 2024
Addressing the associated rise in Carbon Emissions (CE) as smart cities expand becomes paramount. Effective low-carbon urban planning demands robust, precise assessments. This research introduces a cutting-edge solution via an Artificial Intelligence (AI) -driven Footprint (CF) impact assessment. A detailed dataset, collected over 3 years, was harnessed to gather insights into vital factors, including CE, Energy Consumption (EC) patterns, variations land use, transportation dynamics, and changes air quality. The cornerstone of this is developing Multi-modal Stacked VAR-LSTM model. model proposes provide accurate CF predictions for environments by merging capabilities Vector Autoregression (VAR) with Long Short-Term Memory (LSTM) neural networks. process encompasses dedicated assessments each data segment, harnessing VAR delineate interdependencies refining these LSTM network using residuals from analysis. By interweaving AI-driven carbon footprint discourse, study underscores vast potential sculpting future development strategies that are sustainable sensitive impact.
Language: Английский
Citations
15Environmental Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown
Published: March 21, 2025
Language: Английский
Citations
2Earth Systems and Environment, Journal Year: 2024, Volume and Issue: 8(4), P. 1109 - 1125
Published: July 3, 2024
Abstract Prediction of carbon dioxide (CO 2 ) emissions from agricultural soil is vital for efficient and strategic mitigating practices achieving climate smart agriculture. This study aimed to evaluate the ability two machine learning algorithms [gradient boosting regression (GBR), support vector (SVR)], deep [feedforward neural network (FNN) convolutional (CNN)] in predicting CO Maize fields agroclimatic regions i.e., continental (Debrecen-Hungary), semi-arid (Karaj-Iran). research developed three scenarios . Each scenario by a combination between input variables [i.e., temperature (Δ), moisture (θ), date measurement (SD), management (SM)] SC1: (SM + Δ θ), SC2: Δ), SC3: θ)]. Results showed that average emission Debrecen was 138.78 ± 72.04 ppm ( n = 36), while Karaj 478.98 174.22 36). Performance evaluation results train set revealed high prediction accuracy achieved GBR SC1 with highest R 0.8778, lowest root mean squared error (RMSE) 72.05, followed SC3. Overall, performance MDLM ranked as > FNN CNN SVR. In testing phase, 0.918, RMSE 67.75, SC3, (R 0.887, 79.881). The GRB findings provide insights into strategies, enabling stakeholders work towards more sustainable climate-resilient future
Language: Английский
Citations
7Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 114, P. 105776 - 105776
Published: Aug. 26, 2024
Language: Английский
Citations
7Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: unknown, P. 105910 - 105910
Published: Oct. 1, 2024
Language: Английский
Citations
5Renewable and Sustainable Energy Reviews, Journal Year: 2024, Volume and Issue: 209, P. 115128 - 115128
Published: Nov. 28, 2024
Language: Английский
Citations
5Energies, Journal Year: 2024, Volume and Issue: 17(7), P. 1628 - 1628
Published: March 28, 2024
The greenhouse effect formed by the massive emission of carbon dioxide has caused serious harm to Earth’s environment, in which power sector constitutes one primary contributors global gas emissions. Reducing emissions from electricity plays a pivotal role minimizing and mitigating ecological, economic, social impacts climate change, while prediction provides valuable point reference for formulation policies reduce electricity. article detailed review research results on deep learning-based prediction. Firstly, main neural networks applied domain forecasting at home abroad, as well models combining other methods networks, are introduced, roles different methods, when combined with discussed. Secondly, were used predict emissions, performance was compared. Finally, application realm is summarized, future directions researchers understand dynamics development trend learning forecasting.
Language: Английский
Citations
4Sustainability, Journal Year: 2025, Volume and Issue: 17(4), P. 1471 - 1471
Published: Feb. 11, 2025
In the face of global climate change, accurately predicting carbon dioxide emissions has become an urgent requirement for environmental science and policy-making. This article provides a systematic review literature on emission forecasting, categorizing existing research into four key aspects. Firstly, regarding model input variables, thorough discussion is conducted pros cons univariate models versus multivariable models, balancing operational simplicity with high accuracy. Secondly, concerning types, detailed comparison made between statistical methods machine learning methods, particular emphasis outstanding performance deep in capturing complex relationships emissions. Thirdly, data, explores annual daily emissions, highlighting practicality predictions policy-making importance providing real-time support policies. Finally, quantity, differences single ensemble are examined, emphasizing potential advantages considering multiple selection. Based literature, future will focus integration multiscale optimizing application in-depth analysis factors influencing prediction, scientific more comprehensive, real-time, adaptive response to challenges change. comprehensive outlook aims provide scientists policymakers reliable information promoting achievement protection sustainable development goals.
Language: Английский
Citations
0Land, Journal Year: 2025, Volume and Issue: 14(4), P. 844 - 844
Published: April 12, 2025
Northeast China, a traditional heavy industrial base, faces significant carbon emissions challenges. This study analyzes the drivers of in 35 cities from 2000–2022, utilizing machine-learning approach based on stacking model. A model, integrating random forest and eXtreme Gradient Boosting (XGBoost) as base learners support vector machine (SVM) meta-model, outperformed individual algorithms, achieving coefficient determination (R2) 0.82. Compared to methods, model significantly improves prediction accuracy stability by combining strengths multiple algorithms. The Shapley additive explanations (SHAP) analysis identified key drivers: total energy consumption, urbanization rate, electricity population positively influenced emissions, while sulfur dioxide (SO2) smoke dust average temperature, humidity showed negative correlations. Notably, green coverage exhibited complex, slightly positive relationship with emissions. Monte Carlo simulations three scenarios (Baseline Scenario (BS), Aggressive De-coal (ADS), Climate Resilience (CRS)) projected peak 2030 under ADS, lowest fluctuation (standard deviation 5) largest reduction (17.5–24.6%). Baseline indicated around 2039–2040. These findings suggest important role de-coalization. Targeted policy recommendations emphasize accelerating transition, promoting low-carbon transformation, fostering urbanization, enhancing sequestration China’s sustainable development achievement dual-carbon goals.
Language: Английский
Citations
0