Global Greenhouse Gas Emissions Research Articles

Predicting future global temperature and greenhouse gas emissions via LSTM model

This work is executed to predict the variation in global temperature and greenhouse gas (GHG) emissions resulting from climate change and global warming, taking into consideration the natural climate cycle. A mathematical model was developed using a Recurrent Neural Network (RNN) with Long–Short-Term Memory (LSTM) model. Data sets of global temperature were collected from 800,000 BC to 1950 AD from the National Oceanic and Atmospheric Administration (NOAA). Furthermore, another data set was obtained from The National Aeronautics and Space Administration (NASA) climate website. This contained records from 1880 to 2019 of global temperature and carbon dioxide levels. Curve fitting techniques, employing Sin, Exponential, and Fourier Series functions, were utilized to reconstruct both NOAA and NASA data sets, unifying them on a consistent time scale and expanding data size by representing the same information over smaller periods. The fitting quality, assessed using the R-squared measure, ensured a thorough process enhancing the model's accuracy and providing a more precise representation of historical climate data. Subsequently, the time-series data were converted into a supervised format for effective use with the LSTM model for prediction purposes. Augmented by the Mean Squared Error (MSE) as the analyzed loss function, normalization techniques, and refined data representation from curve fitting the LSTM model revealed a sharp increase in global temperature, reaching a temperature rise of 4.8 °C by 2100. Moreover, carbon dioxide concentrations will continue to boom, attaining a value of 713 ppm in 2100. In addition, the findings indicated that the RNN algorithm (LSTM model) provided higher accuracy and reliable forecasting results as the prediction outputs were closer to the international climate models and were found to be in good agreement. This study contributes valuable insights into the trajectory of global temperature and GHG emissions, emphasizing the potential of LSTM models in climate prediction.

Redox potential is a robust indicator for decomposition processes in drained agricultural peat soils: A valuable tool in monitoring peatland wetting efforts

Peat decomposition driven by soil metabolic processes is responsible for approximately 2 % of global annual anthropogenic greenhouse gas emissions. A peat soil's redox potential (Eh) and pH reflect its biogeochemical state and are therefore linked to the rate of peat decomposition and greenhouse gas production. In this study, we aim to establish if continuous Eh measurements are an effective tool to monitor metabolic peat decomposition processes and thus to quantify the effects of peat wetting efforts. We applied continuous in-situ Eh measurements (>150 sensors 2020–2022) as a proxy for metabolic peat decomposition processes, which we validated under field conditions with extensive sampling of porewater chemistry (pH, NO3–, SO42−, Mn(II), Fe(II), S2− and CH4, >2000 samples) for five agricultural, drained, minerotrophic peatland sites in the Netherlands. These 5 sites consisted of plots with and without subsoil irrigation (SSI), where SSI aims to raise groundwater levels and thus wet the peat soil. We found that in-situ continuous Eh measurements closely reflected spatial and temporal heterogeneity in pore water chemistry. Therefore, we concluded that Eh is a robust proxy for peat decomposition processes. Building on this result, we used continuous Eh measurements to study the prevalence of specific metabolic processes from site-to-site in relation with groundwater level changes. We found that, while groundwater levels are an important driver for (an)aerobic conditions, groundwater levels do not explain the full dynamics and extent of (an)aerobic conditions. O2 intrusion was mostly limited to approximately 0.5 m depth at deep (>0.8 m) groundwater levels, likely due to air diffusion limitation. Higher and more constant groundwater levels year-round at SSI plots decreased oxygen intrusion and tended to deplete porewater Fe(II) and SO42−, which led to more reducing Eh and higher porewater CH4 concentrations. The depletion of electron acceptors and occurrence of methanogenesis differed from site to site. In summary, high-frequent Eh monitoring is found to be an effective tool to monitor metabolic peat decomposition processes and quantify the effects of peatlands wetting efforts. Therefore, this methodology is suitable to evaluate and further optimize peatland monitoring and preservation.

Promoting a sustainable diet through carbon labeling of food: Insights from young consumers in the Americas

The agri-food system is a major contributor to global greenhouse gas emissions, and its contribution is projected to grow significantly in coming years. Consumers can drive system change and help mitigate the climate crisis through demand behaviour, with youth uniquely positioned as key actors. Carbon labelling offers a tool for informing consumers about the carbon footprint of food, and thereby promoting purchase of lower-carbon products. This cross-cultural study (n = 815) sought to investigate perceptions of carbon labels on food amongst youth (18–24 years) from two medium-high CO2-emitting countries in the Americas – Canada and Argentina. Using a mixed methods online survey approach that integrates a quantitative questionnaire with open response questions, we found knowledge deficits in familiarity with the concepts ‘carbon footprint’ and especially ‘carbon label’, and these varied with country, gender, and level of education. Further, exemplars of six food carbon labels, standardized for the carbon emissions information displayed, differed for scores of usefulness, clarity, understanding, confusion, and incomprehensibility. Labels also differed in their relative preference ratings, which varied with education level, with the ‘Traffic light horizontal scale’ the most preferred overall. Our findings inform carbon label design and emissions-related education initiatives, each of which should be optimized for different segments of the youth market in order to effectively promote consumption of lower-carbon foods.

Flamingo: Environmental Impact Factor Matching for Life Cycle Assessment with Zero-shot Machine Learning

Consumer products contribute to more than 75% of global greenhouse gas (GHG) emissions, primarily through indirect contributions from the supply chain. Measurement of GHG emissions associated with products is a crucial step toward quantifying the impact of GHG emission abatement actions. Life cycle assessment (LCA), the scientific discipline for measuring GHG emissions, estimates the environmental impact associated with each stage of a product from raw material extraction to its disposal. Scaling LCA to millions of products is challenging as it requires extensive manual analysis by domain experts. To avoid repetitive analysis, environmental impact factors (EIFs) of common materials and products are published for use by LCA experts. However, finding appropriate EIFs for even a single product under study can require hundreds of hours of manual work, especially for complex products. We present Flamingo, an algorithm that leverages natural language machine learning (ML) models to automatically identify an appropriate EIF given a text description. A key challenge in automation is that EIF databases are incomplete. Flamingo uses industry sector classification as an intermediate layer to identify when there are no good matches in the database. On a dataset of 664 products, our method achieves an EIF matching precision of 75%.

Sector coupling for decarbonization and sustainable energy transitions in maritime shipping in Sweden

The maritime shipping industry accounts for 3 % of global greenhouse gas emissions and delivers 90 % of globally traded goods. Maritime shipping is heavily reliant on fossil fuels. There is increasing policy pressure to cut emissions to achieve the Paris Agreement and to meet decarbonization targets.This paper aims to analyze sector coupling for decarbonization and sustainable energy transitions in maritime shipping, exploring the interlinkages between the transport, energy, industry, agriculture and forestry sectors. First, this paper analyses the opportunities and barriers for sector coupling between the maritime shipping sector and other industries. Second, this paper adds new knowledge on the wider implications of sustainable energy transitions and decarbonization for the maritime shipping sector, the role of various stakeholders in supporting or impeding sustainable energy transitions, policy issues at the international, regional and national level and the links to sector coupling.This research uses a mixed methods approach, applying both qualitative research including interviews and quantitative energy modeling. The research thereby links theories from sustainability transitions with techno-economic modeling approaches.Our research finds that the sector couplings between the transport, energy, industry, agriculture and forestry sectors are of growing importance as maritime shipping is transitioning towards decarbonized and renewable marine fuels. At the same time there is competition for scarce natural resources with other sectors, including aviation and road transport. Socio-technical aspects, particularly of financial and political nature, are key factors that determine the speed and direction of the transition, yet they remain under-explored.

Technoeconomic evaluation of post-combustion carbon capture technologies on-board a medium range tanker

The international maritime organization has recently set targets and timelines for reducing global greenhouse gas emissions from the maritime industry, which currently stand at 1.1 Gt/year and make 3 % of the global emissions. Reducing emissions by increasing engine efficacy is the immediate target, but there is a limit to how much this path can achieve. Onboard post-combustion carbon capture and concentration in large marine vessels is emerging as an interim approach to reduce maritime emissions until large-scale deployment of low/zero emission fuels become viable. In this paper, we evaluate three carbon capture technologies (chemical absorption using either aqueous MEA or aqueous NH3 as the solvent, cryogenic separation, and membrane separation) for a medium-range tanker for two fuels, namely heavy fuel oil and liquefied natural gas. The capture cost per tonne of CO2 (recovery>90 %, purity>95 %) was considered as the assessment criterion, with simultaneous evaluation of other aspects such as energy and space demands. The simulations were carried out using MATLAB and ASPEN V12. For rate-based models, the adjustable parameters for the model were tuned using pilot plant data. Additionally, options for hot and cold energy integration were also assessed and implemented. Based on the reference ship conditions and assessment criteria, the simulation studies show that amine-based absorption is the best prospect for on-board capture by a clear margin.

Can the implementation of household waste classification mitigate greenhouse gas emissions in Beijing? A comprehensive analysis of recent trends and future scenarios

Household waste contributes significantly to global greenhouse gas (GHG) emissions, and waste classification is crucial for reducing emissions. This study focuses on Beijing and utilizes life cycle assessment (LCA) and material flow analysis (MFA) to calculate GHG emissions in waste management systems and quantify emission reduction potential of different measures. The results show that net emissions from the classification system in 2021 are 116.77 kg CO2-eq/t waste, reducing 61.82 % compared to the traditional mixed collection and transportation system. Waste volume, classification efficiency, and treatment strategies are the primary factors affecting emissions in classification systems. Recycling is identified as effective treatment methods. Three scenarios are designed to explore emission pathway of the system toward 2060. In the business-as-usual (BAU) Scenario, emissions will continue to grow to 108.57 × 104 t CO2-eq/yr in 2060. In the Classification Efficiency Scenario and the Comprehensive Scenario, emissions in 2060 will be cut to −177.26 × 104 t CO2-eq/yr and −702.00 × 104 t CO2-eq/yr, respectively. These results underscore the critical role of waste classification and recycling in mitigating the negative impacts of increasing waste volume. By 2060, combining waste classification with recycling can offset emissions by 803.51 × 104 t CO2-eq/yr, contributing 99 % to emission reduction potential. Improving classification efficiency and recycling ratio are key measures for achieving this reduction goal. Meanwhile, treatment methods and technologies should prioritize classification and recycling. Aiming at carbon neutrality, the study proposes several recommendations to improve classification systems, including enhancing classification efficiency, optimizing treatment facilities and strategies, and establishing recycling and utilization systems, etc.

Profitability of battery storage in hybrid hydropower–solar photovoltaic plants

Increased energy demand and rapid environmental changes triggered by global greenhouse gas emissions have forced numerous countries to consider renewable energy sources (RES) as possible alternatives to conventional fossil-fuel energy sources. Due to the inherent uncertainty, intermittency, and generally uncontrollable power generation by single-source renewable power plants, hybrid power plants (HPPs) incorporating several mutually complementary RES have lately gained much interest. Integrating battery storage systems with such HPPs has the potential to run them more similarly to conventional fossil-fueled power plants, providing controllable power generation, and reducing its variability. Given such a future scenario and the lack of existing detailed studies, this paper investigates the profitability potential for a viable business case for battery storage integration with utility-scale hybrid hydropower–solar photovoltaic (PV) plants. The study presented here is based on a hypothetical, two-reservoir cascaded hydropower plant in Sub-Saharan Africa. The role of the battery is assessed by considering the overall profitability of the HPP when participating in capacity markets, ancillary services, and energy arbitrage. The relationship between the value stacking of battery services and its impact on battery life has been critically examined. This study provides estimates on increased profitability, cost-optimal battery capacities, battery degradation estimates, and the HPP-battery interoperability aspects under various hydropower and electricity market operating scenarios. Batteries will likely increase cost-effectiveness by co-optimization with PV-system as well as power market contracts. In this case, adding a battery increased the profitability by about 2% when combining revenues from capacity markets and ancillary services.

Mapping the position and attitudes of stakeholders towards the utilization of the black soldier fly using MACTOR Tools: A study in Depok City, West Java, Indonesia

Depok City is located between the cities of Jakarta and Bogor. The population of the city has reached more than 2,000,000 people. This has consequences on the issue of waste, especially food waste. Food waste responsible for 8–10% of global anthropogenic greenhouse gas emissions. To support sustainable development, it is very important to reduce the amount of food loss. In 2019, food waste reached 931 million tons of food worldwide. Retailers and households are the biggest contributors to this waste at 13% and 61% respectively. This food waste exacerbates economic, environmental and social problems. The black soldier fly (BSF) insect (Hermetia illucens) can overcome the negative impact on the environment caused by food waste and at the same time can provide a sustainable source of protein. BSF larvae can digest food waste and convert it into biomass. However, the application of the use of the black soldier is not yet widely known in the City of Depok. For that, we need a comprehensive approach that involves various stakeholders. One of the most important elements in the successful application of the black soldier fly to the waste problems in Depok City is stakeholders mapping.

ENSURING BALANCE BETWEEN GOALS OF SUSTAINABLE DEVELOPMENT, COMPETITIVENESS AND ENERGY SECURITY

The study is devoted to determining the future framework of the world’s energy development in the new geostrategic realities associated with military conflicts in the world and the problem of global warming. It was examined emerging trends in achieving global net zero greenhouse gas emissions by 2050 and decarbonization efforts in the study. It was determined that the war in Ukraine became a catalyst for the energy transition in the world. It is noted that in order to achieve climate goals, it is necessary to increase the production of nuclear energy by three times by 2050. This provision was recorded in the declaration on triple nuclear energy at the UN Climate Change Conference (Dubai) in 2023. It is also noted that hydrogen energy is one of the technologies of clean energy and has great perspective, although the infrastructure associated with the use of this energy resource is currently very expensive. Attention is focused on the need to ensure a balance between the goals of sustainable development, competitiveness and energy security. The focus on secure supply chains and energy access and market stability issues is updated. It has been determined that in the new geostrategic realities, attention is focused on the fact that competitiveness must be considered through the prism of «green competitiveness». Jointly solving the issues of sustainable development, competitiveness and energy security is important for building a sustainable economy in the new geostrategic realities associated with military conflicts in the world and the problem of global warming. The logic of the formation of the future framework of energy development in the world in new geostrategic realities from the definition of the conceptual basis and technological support of energy security and competitiveness of the national economy has been presented in the work. At the same time, energy security is crucial for maintaining economic stability and achieving the goals of sustainable development. R

Farmer’s knowledge of greenhouse gases impact mitigation: Comparing Bogor and Sumbawa

Farming specifically contributes 10 – 12% of global anthropogenic Greenhouse Gases emissions, including the agricultural sector in Bogor and Sumbawa Regencies. This study aims to compares knowledge and perceptions of greenhouse gases in agriculture among farmers in Bogor and Sumbawa. This study used quantitative and qualitative approaches. Qualitative data was gathered by interviewing 150 farmers from Bogor and Sumbawa. Secondary data analysis is also used to complement the primary data collection. The data was obtained from the Bogor and Sumbawa agriculture services. Based on the results of the study, farmers in Bogor know more about climate change than Sumbawa regencies. Information spread among farmers tends to refer to practices and technology in farming, and the information related to disaster warnings and climate factors is not widely available. In this regard, it is necessary to increase the literacy and understanding of farmers regarding climate change. Literacy must be done so farmers can mitigate and adapt to climate change.

Vehicle-to-grid system optimization for electric vehicle – a review

The transportation industry is a major contributor to global greenhouse gas emissions, and the adoption of electric vehicles (EVs) presents a viable solution to this problem. The implementation of vehicle-to-grid (V2G) systems has significantly enhanced energy supply and utilization efficiency, particularly through the integration of renewable energy sources such as solar and wind. However, the complexity of the V2G system necessitates addressing multiple objectives and constraints. Previous research has employed optimization methods to refine the V2G system. However, traditional linear and quadratic programming approaches are limited to simple and linear objectives, while non-linear programming methods encounter challenges when dealing with uncertain variables. Consequently, there is a pressing need for a more dependable optimization method capable of managing uncertain variables in this intricate system, particularly in the context of renewable energy source integration. This paper reviews the feasible and reliable optimization approaches utilized by scholars and researchers, examining the multiple objective functions and constraints required for optimizing the V2G system.

A simulation-based investigation into the charging performance of lithium-ion and lead-acid batteries in electric vehicles

The transportation sector constitutes a major source of global greenhouse gas emissions, and the adoption of electric vehicles (EVs) can help mitigate this issue. This paper presents a simulation study examining the performance of lithium-ion and lead-acid batteries for EVs when charged using direct current (DC) chargers. A simulation model is employed to observe the charging behavior of these batteries and analyze the effects of various DC chargers. Factors such as the state of charge (SOC) and charging rate influence the charging behavior of batteries in EVs. The simulation results are compared and analyzed to ascertain the optimal charging strategy and infrastructure for EVs. The performance of different EVs is evaluated in terms of charging time, energy efficiency, and SOC. According to the findings, implementing the appropriate charging strategy and infrastructure for lithium-ion and lead-acid batteries in EVs can significantly enhance performance and encourage the widespread adoption of EVs.

Sensitivity of the global agricultural sector to changes in climate policy - EU countries compared to the rest of the world

Abstract There has been a decline in greenhouse gas (GHG) emissions per capita in all world regions since the 1990s. In developing countries, this decline has been attributed to population growth and an increase in absolute emissions, while in developed countries, the trend is mainly due to a decrease in absolute emissions combined with minor population changes. This paper aims to delve into the intricacies of global GHG emissions, with a spotlight on the agricultural sector. This paper assesses the patterns and reasons behind the decline in GHG emissions per capita since the 1990s across different regions. In particular, it addresses the concept of the “sustainable intensification of agriculture” and the debate between intensive vs. less-intensive production in the context of GHG emissions. Despite having high emissions per hectare, we argue that European countries show lower emissions in relation to production value, highlighting the region’s production intensity and efficiency. Compelling visual data representations and references from significant international bodies, such as the IPCC and EEA, bolster the paper’s findings and conclusions.

Application of Artificial Intelligence in Carbon Accounting and Firm Performance: A Review Using Qualitative Analysis

The increasing role of the corporate sector in global carbon emissions has raised significant concern among stakeholders, leading to a thorough reassessment of corporate responsibility. Corporations, directly influencing society due to their carbon emissions, acknowledged as externalities, are facing growing pressure to tackle this environmental challenge actively. As a reaction, companies are increasingly implementing carbon accounting and other environmentally conscious practices in line with a broader dedication to comprehensive environmental ethics. The accounting department, tasked with incorporating carbon accounting into non-financial reports alongside regular financial statements, encounters adoption obstacles such as limited awareness, insufficient expertise, unclear guidelines, and a lack of standardized terminology. This paper conducts a comprehensive study to evaluate the feasibility of using artificial intelligence (AI) solutions in carbon accounting and its subsequent effect on firm performance based on the well-established effectiveness of AI in financial reporting and accounting tasks. As of 2021, Saudi Aramco, the foremost emitter of carbon dioxide worldwide, accounts for more than 4 percent of global Greenhouse Gas Emissions. This highlights the pressing necessity for intervention in this industry. Moreover, the study highlights electricity and heat production as the primary global sources of carbon emissions. The research demonstrates a clear link between effective carbon accounting practices and improved firm performance, especially when stakeholders are highly aware of sustainability issues. Nevertheless, the paper highlights the considerable obstacles and the urgent requirement for extensive advancement in AI applications to fully exploit its potential as a significant resolution to the complexities of carbon accounting. The study is limited by the wide range of accounting standards companies use to disclose their environmental impact and a need for more information on using artificial intelligence in carbon accounting. The research highlights the crucial significance of collaborative endeavours in promoting AI solutions to strengthen carbon accounting practices, thereby enhancing corporate sustainability and overall performance.

Decarbonisation pathways of the cement production process via hydrogen and oxy-combustion

Decarbonising cement production is of profound importance for meeting global greenhouse gas emission reduction targets and mitigating the impact of climate change. This study evaluates various technical options for achieving deep decarbonisation in a clinker production facility by utilising hydrogen (H2) as an alternative fuel to replace fossil fuels and by integrating an oxy-combustion technique with carbon capture and storage (CCS). Using Aspen Plus process simulations, we examined the extent of decarbonisation and assessed the thermal and electrical energy demands. This was achieved by incorporating an amine-absorption-based CO2 capture to a conventional natural gas fuelled reference plant, implementing oxyfuel-combustion of natural gas, and exploring four different scenarios for replacing fossil fuel with H2. In these scenarios, H2 was assumed to be produced through on-site water electrolysis, which also supplied oxygen for oxyfuel combustion, potentially eliminating the need for an air separation unit (ASU). The processes utilizing H2, except for the case of indirectly heated pre-calcination, employed oxyfuel combustion. The results indicate that the natural gas-fuelled oxyfuel-combustion process had the lowest total energy input at 4.92 GJ/t clinker, approximately 35% lower than that of the reference plant. Processes using H2 reduced energy demand by 11% in the H2-d scenario and 33% in the H2-a scenario. However, the process with indirect calcination required 6.24 GJ/t clinker, about 8% more H2 fuel than direct calcination but helped eliminate the need for an ASU. The results also reveal that greater H2 substitutions led to higher total process energy requirements due to the inefficiencies of the electrolysis process. While the H2-using processes could reduce the CO2 generation by up to 559 kgCO2/t clinker, this represents only about 27.6% of the CO2 reductions relative to the reference plant. These findings underscore the limitation of fuel substitution alone in cement production and emphasize the need for innovations in raw materials and the adoption of CCS to achieve deeper decarbonisation in cement industries.

Towards a greener photovoltaic industry: Enhancing efficiency, environmental sustainability and manufacturing costs through solvent optimization in organic solar cells

The energy sector is a major contributor to global greenhouse gas emissions, necessitating a transition to renewable energy sources. The photovoltaic industry plays a crucial role in this transition by harnessing solar energy, a clean and abundant resource. However, the high cost of solar panels remains a challenge. Organic solar cells (OSCs) offer a promising alternative to conventional silicon-based cells due to their low production costs and flexibility. In this study, we focus on optimizing the performance of OSCs by investigating the influence of solvent volume in the hole transport layer. By gradually increasing the volume of dimethylformamide (DMF), dimethyl sulfoxide (DMSO), and tetrahydrofuran (THF) in the PEDOT:PSS layer, we analyse the impact on power conversion efficiency (PCE) and assess the economic and environmental implications. Our results demonstrate the potential for enhancing the PCE of OSCs through solvent optimization, thereby advancing the greening of the photovoltaic industry while considering economic viability and environmental sustainability.

Research on the Impact of Energy on Emission Reduction and Environmental Protection

All nations are concerned about how to deal with the problem of the increasing carbon dioxide emissions in the globe today. By replacing traditional non-renewable energy with clean energy, greenhouse gas emissions can be reduced, thus helping to tackle climate change. Since the industrial revolution, global greenhouse gas emissions and the amount of energy generated from fossil fuels have increased dramatically, resulting in the highest levels of atmospheric carbon dioxide in 400,000 years. Therefore, this article aims to analyze the data on various energy consumption and carbon dioxide emissions by incorporating them into a multiple linear model, in order to identify the impact of different energy sources on carbon dioxide emissions. The results show that only oil, coal, and hydropower have a significant positive correlation with carbon dioxide emissions, while other energy sources do not have a significant relationship. Based on the above analysis, it is hoped to provide some meaningful recommendations.

Ending extreme poverty has a negligible impact on global greenhouse gas emissions

Growing consumption is both necessary to end extreme poverty1and one of the main drivers of greenhouse gas emissions2, creating a potential tension between alleviating poverty and limiting global warming. Most poverty reduction has historically occurred because of economic growth3–6, which means that reducing poverty entails increasing not only the consumption of people living in poverty but also the consumption of people with a higher income. Here we estimate the emissions associated with the economic growth needed to alleviate extreme poverty using the international poverty line of US $2.15 per day (ref. 7). Even with historical energy- and carbon-intensity patterns, the global emissions increase associated with alleviating extreme poverty is modest, at 2.37 gigatonnes of carbon dioxide equivalent per year or 4.9% of 2019 global emissions. Lower inequality, higher energy efficiency and decarbonization of energy can ease this tension further: assuming the best historical performance, the emissions for poverty alleviation in 2050 will be reduced by 90%. More ambitious poverty lines require more economic growth in more countries, which leads to notably higher emissions. The challenge to align the development and climate objectives of the world is not in reconciling extreme poverty alleviation with climate objectives but in providing sustainable middle-income standards of living.

The Application of Feed - Forward Neural Network Architecture for Improving Energy Efficiency

The energy sector contributes approximately two-thirds of global greenhouse gas emissions. In this context, the sector must adapt to new supply and demand networks for all future energy sources. The ongoing transformation in the European energy field is driven by the ambition of the European Union to reach the climate objectives set for 2030. The main actions are increasing renewable energy production, adapting transition fuels like natural gas to reduce emissions, improving energy efficiency across all economic sectors, prioritizing building, transportation, and industry, developing Carbon Capture and Storage technologies, and ensuring universal access to clean and affordable energy. The significant changes envisaged in the energy sector to increase renewable energy production and consumption require improved integration and more use of predictive tools to support stakeholders' decision-making processes. This article presents a case study to assess the performance of predictive models based on a Feed-Forward Neural Network architecture that employ Root Mean Squared Propagation as their optimization function in terms of choosing the most appropriate activation function for this kind of data input and output. The training and testing phases of the models use data about building energy consumption. The lowest training time and Root Mean Square Error values were similar for Rectified Linear Unit and Tanh activation functions. The model with the Rectified linear Unit activation function performed best.