Enhancing Transparency of Climate Efforts: MITICA’s Integrated Approach to Greenhouse Gas Mitigation

Sustainability, Journal Year: 2024, Volume and Issue: 16(10), P. 4219 - 4219

Published: May 17, 2024

Under the Paris Agreement, countries must articulate their most ambitious mitigation targets in Nationally Determined Contributions (NDCs) every five years and regularly submit interconnected information on greenhouse gas (GHG) aspects, including national GHG inventories, NDC progress tracking, policies measures (PAMs), projections various scenarios. Research highlights significant gaps definition of reporting GHG-related elements, such as inconsistencies between projections, targets, a disconnect PAMs scenarios, well varied methodological approaches across sectors. To address these challenges, Mitigation-Inventory Tool for Integrated Climate Action (MITICA) provides framework that links applying hybrid decomposition approach integrates machine learning regression techniques with classical forecasting methods developing emission projections. MITICA enables scenario generation until 2050, incorporating over 60 Intergovernmental Panel Change (IPCC) It is first modelling ensures consistency aligning tracking target setting IPCC best practices while linking climate change sustainable economic development. MITICA’s results include align observed trends, validated through cross-validation against test data, employ robust evaluating PAMs, thereby establishing its reliability.

Language: Английский

---

Global progress towards the Coal: Tracking coal Reserves, coal Prices, electricity from Coal, carbon emissions and coal Phase-Out

Gondwana Research, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 1, 2024

Language: Английский

---

Enhancing solar irradiance prediction for sustainable energy solutions employing a hybrid machine learning model; improving hydrogen production through Photoelectrochemical device

Applied Energy, Journal Year: 2025, Volume and Issue: 382, P. 125280 - 125280

Published: Jan. 13, 2025

Language: Английский

---

A comprehensive benchmark of machine learning-based algorithms for medium-term electric vehicle charging demand prediction

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(3)

Published: Feb. 10, 2025

Language: Английский

---

Statistical Comparison of Time Series Models for Forecasting Brazilian Monthly Energy Demand Using Economic, Industrial, and Climatic Exogenous Variables

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(13), P. 5846 - 5846

Published: July 4, 2024

Energy demand forecasting is crucial for effective resource management within the energy sector and aligned with objectives of Sustainable Development Goal 7 (SDG7). This study undertakes a comparative analysis different models to predict future trends in Brazil, improve methodologies, achieve sustainable development goals. The evaluation encompasses following models: Seasonal Autoregressive Integrated Moving Average (SARIMA), Exogenous SARIMA (SARIMAX), Facebook Prophet (FB Prophet), Holt–Winters, Trigonometric Seasonality Box–Cox transformation, ARMA errors, Trend, components (TBATS), draws attention their respective strengths limitations. Its findings reveal unique capabilities among models, excelling tracing seasonal patterns, FB demonstrating its potential applicability across various sectors, Holt–Winters adept at managing fluctuations, TBATS offering flexibility albeit requiring significant data inputs. Additionally, investigation explores effect external factors on consumption, by establishing connections through Granger causality test conducting correlation analyses. accuracy these assessed without exogenous variables, categorized as economical, industrial, climatic. Ultimately, this seeks add body knowledge prediction, well allow informed decision-making planning policymaking and, thus, make rapid progress toward SDG7 associated targets. paper concludes that, although achieves best accuracy, most fit model, considering residual autocorrelation, it predicts that Brazil will approximately 70,000 GWh 2033.

Language: Английский

---

Modeling the Efficiency of Resource Consumption Management in Construction Under Sustainability Policy: Enriching the DSEM-ARIMA Model

Sustainability, Journal Year: 2024, Volume and Issue: 16(24), P. 10945 - 10945

Published: Dec. 13, 2024

The aim of this research is to study the influence factors affecting efficiency resource consumption under sustainability policy based on using DSEM-ARIMA (Dyadic Structural Equation Modeling Autoregressive Integrated Moving Average) model. performed Thailand experience. findings indicate that continuous economic growth aligns with country’s objectives, directly contributing social growth. This efficient planning. It demonstrates management goal achieving 5.0. Furthermore, considering environmental aspect, it found and impacts ecological aspect due significant in construction. construction shows a rate increase 264.59% (2043/2024), reaching 401.05 ktoe (2043), which exceeds carrying capacity limit set at 250.25 ktoe, resulting long-term degradation. Additionally, political have greatest environment, exacerbating damage beyond current levels. Therefore, model establishes new scenario policy, indicating leads degradation reduced 215.45 does not exceed capacity. Thus, if utilized, can serve as vital tool formulating policies steer toward 5.0 effectively.

Language: Английский

---

Putting the Personalized Metabolic Avatar into Production: A Comparison between Deep-Learning and Statistical Models for Weight Prediction

Nutrients, Journal Year: 2023, Volume and Issue: 15(5), P. 1199 - 1199

Published: Feb. 27, 2023

Nutrition is a cross-cutting sector in medicine, with huge impact on health, from cardiovascular disease to cancer. Employment of digital medicine nutrition relies twins: replicas human physiology representing an emergent solution for prevention and treatment many diseases. In this context, we have already developed data-driven model metabolism, called "Personalized Metabolic Avatar" (PMA), using gated recurrent unit (GRU) neural networks weight forecasting. However, putting twin into production make it available users difficult task that as important building. Among the principal issues, changes data sources, models hyperparameters introduce room error overfitting can lead abrupt variations computational time. study, selected best strategy deployment terms predictive performance Several models, such Transformer model, recursive (GRUs long short-term memory networks) statistical SARIMAX were tested ten users. PMAs based GRUs LSTM showed optimal stable performances, lowest root mean squared errors (0.38 ± 0.16-0.39 0.18) acceptable times retraining phase (12.7 1.42 s-13.5 3.60 s) environment. While did not bring substantial improvement over RNNs term performance, increased time both forecasting by 40%. The worst though had For all considered, extent source was negligible factor, threshold established number points needed successful prediction.

Language: Английский

---

Deep graph gated recurrent unit network-based spatial–temporal multi-task learning for intelligent information fusion of multiple sites with application in short-term spatial–temporal probabilistic forecast of photovoltaic power

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 240, P. 122072 - 122072

Published: Nov. 10, 2023

Language: Английский

---

Enhanced Multi-Horizon Occupancy Prediction in Smart Buildings using Cascaded Bi-LSTM Models with Integrated Features

Energy and Buildings, Journal Year: 2024, Volume and Issue: 318, P. 114442 - 114442

Published: June 21, 2024

Accurate occupancy prediction in smart buildings is crucial for optimizing energy management, improving occupant comfort, and effectively controlling building systems, particularly short- long-term horizons. Recently, deep learning-based methods have gained considerable attention. However, the full potential of these remains under explored terms model architecture variations This study introduces cascaded LSTM Bi-LSTM models multi-horizon predictions from 10 minutes to 24 hours, integrating a modified activation function, additional input features, optimized hyper-parameters using OPTUNA. Traditional performance metrics various other analyses were conducted compare models. Both performed well predictions, with minimal differences results. Nevertheless, analysis focusing on non-zero data errors (accounting approximately 11% occupied periods) occupancy-wise showed significant gap between two The demonstrated consistent across horizons variations, accuracy 10-15% higher than model, highlighting its superior capability capturing complex dataset dynamics through bidirectional process. highlights importance feature analysis, multi-perspective result select most suitable prediction, validated pre- post-modeling analysis.

Language: Английский

---

Hybrid time series models with exogenous variable for improved yield forecasting of major Rabi crops in India

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Dec. 14, 2023

Abstract Accurate and in-time prediction of crop yield plays a crucial role in the planning, management, decision-making processes within agricultural sector. In this investigation, utilizing area under irrigation (%) as an exogenous variable, we have made exertion to assess suitability different hybrid models such ARIMAX (Autoregressive Integrated Moving Average with eXogenous Regressor)–TDNN (Time-Delay Neural Network), ARIMAX–NLSVR (Non-Linear Support Vector Regression), ARIMAX–WNN (Wavelet ARIMAX–CNN (Convolutional ARIMAX–RNN (Recurrent Network) ARIMAX–LSTM (Long Short Term Memory) compared their individual counterparts for forecasting major Rabi crops India. The accuracy ARIMA model has also been considered benchmark. Empirical outcomes reveal that modeling combination outperforms all other time series terms root mean square error (RMSE) absolute percentage (MAPE) values. For these models, average improvement RMSE MAPE values observed be 10.41% 12.28%, respectively over competing 15.83% 18.42%, benchmark model. incorporation variable framework inbuilt capability LSTM process complex non-linear patterns significantly enhance forecasting. performance supremacy evident. results suggest avoiding any generalization structures.

Language: Английский

---