Utilizing time series data from 1961 to 2019 recorded around the world and machine learning to create a Global Temperature Change Prediction Model

Malakouti, Seyed matin

doi:10.1016/j.cscee.2023.100312

Cited by 26 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 depicts the evolution process of tuning hyperparameters using 10-fold cross-validation and grid search. In this process, 80% of the data are used for training, 10% for testing, and 10% for validation [ 38 ]. In the process of hyperparameter tuning, a fine-grained grid search method is employed to gradually search for the optimal hyperparameters (the model has the lowest RMSE ).…”

Section: Methodsmentioning

confidence: 99%

Advancing Construction 3D Printing with Predictive Interlayer Bonding Strength: A Stacking Model Paradigm

Wu,

Luo,

Long

et al. 2024

Materials

View full text Add to dashboard Cite

To enhance the quality stability of 3D printing concrete, this study introduces a novel machine learning (ML) model based on a stacking strategy for the first time. The model aims to predict the interlayer bonding strength (IBS) of 3D printing concrete. The base models incorporate SVR, KNN, and GPR, and subsequently, these models are stacked to create a robust stacking model. Results from 10-fold cross-validation and statistical performance evaluations reveal that, compared to the base models, the stacking model exhibits superior performance in predicting the IBS of 3D printing concrete, with the R2 value increasing from 0.91 to 0.96. This underscores the efficacy of the developed stacking model in significantly improving prediction accuracy, thereby facilitating the advancement of scaled-up production in 3D printing concrete.

show abstract

Section: Methodsmentioning

confidence: 99%

Advancing Construction 3D Printing with Predictive Interlayer Bonding Strength: A Stacking Model Paradigm

Wu,

Luo,

Long

et al. 2024

Materials

View full text Add to dashboard Cite

show abstract

“…The researcher used the 10-fold cross-validation method [36][37][38][39][40][41][42][43][44] and grid search method to reach the best performance of machine learning algorithms to identify gammas and hadrons. Following are explanations of Grid Search and the 10-fold cross-validation technique:…”

Section: Methodsmentioning

confidence: 99%

Discriminate primary gammas (signal) from the images of hadronic showers by cosmic rays in the upper atmosphere (background) with machine learning

Malakouti

2023

Phys. Scr.

Self Cite

View full text Add to dashboard Cite

The grid search approach was used in this article to tune the hyperparameters of the Light Gradient Boosting Machine, Random Forest, Gradient Boosting, Extra Tree, Ada Boost, and Linear Discriminant Analysis algorithms for Gamma and Hadron classification. The findings of ROC and Precision-Recall curves were also discussed to assess the performance of algorithms in the Gamma and Hadron classification. with the light gradient boosting machine, it took 33 seconds to get an AUC value of 0.94 for the Gamma and Hardon classification. Also, the results of the Random Forest, the light gradient boosting machine, and the Linear Discriminant Analysis were all about the same.

show abstract

“…This involved filling the missing values with the average method, deleting the noise data, and normalizing the data; then, 85% of the data were selected for network training (10 months), 7.5% for testing (1 month), and the remaining 7.5% for validation (1 month). The 10-fold cross-validation technique [20][21][22][23][24] (Section 2.4) and the grid search method (Section 2.3) were used for tuning the hyperparameters of the LightGBM algorithm (Section 2.2).…”

Section: Evaluation Processmentioning

confidence: 99%

Prediction of Wind Speed and Power with LightGBM and Grid Search: Case Study Based on Scada System in Turkey

Malakouti¹

2023

IJEPM

View full text Add to dashboard Cite

Due to the speeding up of climate change, there is an urgent need to switch from using fossil fuels to producing energy using renewable energy sources. This change has to happen as soon as feasibly possible. Thus, in this article, to forecast wind speed and wind energy output in Turkey, the Light Gradient Boosting Machine (LightGBM) approach was applied, the hyperparameters of the LightGBM were tuned to the grid search method, and finally some evaluation criteria such as root mean square error and R 2 were calculated to show the performances of the LightGBM. Fortunately, an R 2 value of 0.98 for forecasting wind speed was found after 25 s. Additionally, the assessment criterion R 2 =1 for predicting the production power of the wind turbine was attained after 90 s.

show abstract

Utilizing time series data from 1961 to 2019 recorded around the world and machine learning to create a Global Temperature Change Prediction Model

Cited by 26 publications

References 28 publications

Advancing Construction 3D Printing with Predictive Interlayer Bonding Strength: A Stacking Model Paradigm

Advancing Construction 3D Printing with Predictive Interlayer Bonding Strength: A Stacking Model Paradigm

Discriminate primary gammas (signal) from the images of hadronic showers by cosmic rays in the upper atmosphere (background) with machine learning

Prediction of Wind Speed and Power with LightGBM and Grid Search: Case Study Based on Scada System in Turkey

Contact Info

Product

Resources

About