Smart predictive viscosity mixing of CO2–N2 using optimized dendritic neural networks to implicate for carbon capture utilization and storage

Journal of environmental chemical engineering, Journal Year: 2024, Volume and Issue: 12(2), P. 112210 - 112210

Published: Feb. 14, 2024

Language: Английский

---

Identification of Stable Intermetallic Compounds for Hydrogen Storage via Machine Learning

Energy Storage, Journal Year: 2025, Volume and Issue: 7(1)

Published: Jan. 6, 2025

ABSTRACT Hydrogen is one of the most promising alternatives to fossil fuels for energy as it abundant, clean and efficient. Storage transportation hydrogen are two key challenges faced in utilizing a fuel. Storing H 2 form metal hydrides safe cost effective when compared its compression liquefaction. Metal leverage ability metals absorb stored can be released from hydride by applying heat needed. A multi‐step methodology proposed identify intermetallic compounds that thermodynamically stable have high storage capacity (HSC). It combines compound generation, thermodynamic stability analysis, prediction properties ranking discovered materials based on predicted properties. The US Department Energy (DoE) Materials Database Open Quantum (OQMD) utilized building testing machine learning (ML) models enthalpy formation compounds, formation, equilibrium pressure HSC hydrides. here require only attributes elements involved compositional information inputs do no need any experimental data. Random forest algorithm was found accurate amongst ML algorithms explored predicting all interest. total 349 772 hypothetical were generated initially, out which, 8568 stable. highest these 3.6. Magnesium, Lithium Germanium constitute majority compounds. predictions using present not DoE database reasonably close data published recently but there scope improvement accuracy with HSC. findings this study will useful reducing time required development discovery new used check practical applicability

Language: Английский

---

Forecasting geothermal temperature in western Yemen with Bayesian-optimized machine learning regression models

Geothermal Energy, Journal Year: 2025, Volume and Issue: 13(1)

Published: Jan. 12, 2025

Abstract Geothermal energy is a sustainable resource for power generation, particularly in Yemen. Efficient utilization necessitates accurate forecasting of subsurface temperatures, which challenging with conventional methods. This research leverages machine learning (ML) to optimize geothermal temperature Yemen’s western region. The data set, collected from 108 wells, was divided into two sets: set 1 1402 points and 2 995 points. Feature engineering prepared the model training. We evaluated suite regression models, simple linear (SLR) multi-layer perceptron (MLP). Hyperparameter tuning using Bayesian optimization (BO) selected as process boost accuracy performance. MLP outperformed others, achieving high $$\text {R}^{2}$$ R 2 values low error across all metrics after BO. Specifically, achieved 0.999, MAE 0.218, RMSE 0.285, RAE 4.071%, RRSE 4.011%. BO significantly upgraded Gaussian model, an 0.996, minimum 0.283, 0.575, 5.453%, 8.717%. models demonstrated robust generalization capabilities (MAE RMSE) sets. study highlights potential enhanced ML techniques novel optimizing exploitation, contributing renewable development.

Language: Английский

---

Enhanced Data-Driven Machine Learning Models for Predicting Total Organic Carbon in Marine–Continental Transitional Shale Reservoirs

Sustainability, Journal Year: 2025, Volume and Issue: 17(5), P. 2048 - 2048

Published: Feb. 27, 2025

Natural gas, as a sustainable and cleaner energy source, still holds crucial position in the transition stage. In shale gas exploration, total organic carbon (TOC) content plays role, with log data proving beneficial predicting reservoirs. However, complex coal-bearing layers like marine–continental transitional Shanxi Formation, traditional prediction methods exhibit significant errors. Therefore, this study proposes an advanced, cost- time-saving deep learning approach to predict TOC shale. Five well records from area were used evaluate five machine models: K-Nearest Neighbors (KNNs), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Extreme (XGB), Deep Neural Network (DNN). The predictive results compared conventional for accurate predictions. Through K-fold cross-validation, ML models showed superior accuracy over models, DNN model displaying lowest root mean square error (RMSE) absolute (MAE). To enhance accuracy, δR was integrated new parameter into models. Comparative analysis revealed that improved DNN-R reduced MAE RMSE by 57.1% 70.6%, respectively, on training set, 59.5% 72.5%, test original model. Williams plot permutation importance confirmed reliability effectiveness of enhanced indicate potential technology valuable tool parameters, especially reservoirs lacking sufficient core samples relying solely basic well-logging data, signifying its effective assessment development.

Language: Английский

---

Computational intelligence investigations on evaluation of salicylic acid solubility in various solvents at different temperatures

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 28, 2025

This research shows the utilization of various tree-based machine learning algorithms with a specific focus on predicting Salicylic acid solubility values in 13 solvents. We employed four distinct models: cubist regression, gradient boosting (GB), extreme (XGB), and extra trees (ET) for correlation drug to pressure, temperature, solvent composition. The dataset was preprocessed using Standard Scaler standardize it, ensuring each feature has mean zero standard deviation one, followed by outlier detection Cook's distance. Hyperparameter optimization made Differential Evolution (DE) method improved performance models. Monte Carlo Cross-Valuation used evaluation Measures including R2 score, Root Mean Squared Error (RMSE), Absolute (MAE) helped measure their performance. With an value 0.996, Extra Trees model displayed remarkable accuracy consistency, so showing better than other study emphasizes resilience ensemble methods capturing intricate data patterns effectiveness regression tasks application pharmaceutical manufacturing.

Language: Английский

---

Modeling the thermal transport properties of hydrogen and its mixtures with greenhouse gas impurities: A data-driven machine learning approach

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: 83, P. 1 - 12

Published: Aug. 8, 2024

Language: Английский

---

Investigate on spontaneous combustion characteristics of lignite stockpiles considering moisture and particle size effects

Energy, Journal Year: 2024, Volume and Issue: 309, P. 133193 - 133193

Published: Sept. 16, 2024

Language: Английский

---

Analysis and prediction of combustion characteristics of co-combustion of coal and biomass (straw, sludge and herb residue)

Journal of Thermal Analysis and Calorimetry, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 10, 2025

Language: Английский

---

Improving carbon dioxide emission predictions through a hybrid model utilising an advanced sparrow search algorithm

Environmental Technology, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 16

Published: Feb. 16, 2025

The dramatic increase in carbon dioxide emissions is a major cause of global warming and climate change, posing serious threat to human development profoundly affecting the ecosystem. Currently, prediction studies rely heavily on large amount data support, accuracy predictions greatly reduced when are scarce. In addition, inherent uncertainty, volatility, complexity CO2 emission further exacerbate challenge accurate prediction. To address these issues, novel hybrid model for proposed this paper. A feature screening method designed effective reliable selection from perspective algorithm stability, which can improve performance. order accurately predict periodic sequences with limited training samples, least squares support vector machine employed parameters optimised using improved sparrow search enhanced by Sin chaos mapping, adaptive inertia weights Cauchy-Gauss variables. An empirical study conducted Chinese as case study, validity superiority verified through comparative experiments. results show that SSA has stronger optimisation capability faster convergence speed. terms results, best consistency actual data, significantly improves accuracy.

Language: Английский

---

Prediction of Carbon Emissions and Flue Gas Flow in a 200mw Coal-Fired Boiler Power Plant Under Peak Shaving Using an Optimized Bpnn Model

Published: Jan. 1, 2025

Language: Английский

---