Improving the prediction of wind speed and power production of SCADA system with ensemble method and 10-fold cross-validation

Malakouti, Seyed matin

doi:10.1016/j.cscee.2023.100351

Cited by 13 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model was trained and tested on a tenfold cross‐validation repeated 10 times. Cross‐validation has been widely used in many studies (Bo et al., 2022; Malakouti, 2023; Viscarra Rossel et al., 2019). The tenfold cross‐validation involves splitting all the observations into 10 equal parts, training the model on nine parts and testing it on the remaining part.…”

Section: Methodsmentioning

confidence: 99%

Global cropland nitrous oxide emissions in fallow period are comparable to growing‐season emissions

Shang,

Cui,

van Groenigen

et al. 2024

Global Change Biology

View full text Add to dashboard Cite

Croplands account for ~ one‐third of global anthropogenic nitrous oxide (N2O) emissions. A number of recent field experiments found substantial fallow‐period N2O emissions, which have been neglected for decades. However, the global contribution of the fallow‐period emissions and the associated drivers remain unclear. Based on 360 observations across global agroecosystems, we simulated the ratio of the fallow to the whole‐year N2O emissions (Rfallow) by developing a mixed‐effect model and compiling cropping‐system‐specific input data. Our results revealed that the mean global gridded Rfallow was 44% (15%–75%, 95% confidence interval), with hotspots mainly in the northern high latitudes. For most cropping systems, soil pH was the dominant driver of global variation in Rfallow. Global cropland emission factors (i.e., the percentage of fertilizer N emitted as N2O, EFs) in EF‐based models doubled to 1.9% when the fallow‐period N2O emissions were included in our simulation, similar to EFs estimated by process‐based and atmospheric inversion models (1.8%–2.3%). Overall, our study highlights the importance of fallow‐period N2O emissions in annual totals, especially for single cropping systems and croplands in acidic areas. To accurately estimate N2O emissions for national greenhouse gas inventories, it is crucial to update current EFs with full consideration of the fallow‐period N2O emissions in the Intergovernmental Panel on Climate Change (IPCC) Tier 1 method.

show abstract

Section: Methodsmentioning

confidence: 99%

Global cropland nitrous oxide emissions in fallow period are comparable to growing‐season emissions

Shang,

Cui,

van Groenigen

et al. 2024

Global Change Biology

View full text Add to dashboard Cite

show abstract

“…PLSR projects the Raman data onto a subspace of latent variables (LVs), which have maximum covariance with the response(s). The performance results of the machine learning algorithm were obtained using 5-fold cross-validation [ 55 ].…”

Section: Methodsmentioning

confidence: 99%

Performance of Classification Models of Toxins Based on Raman Spectroscopy Using Machine Learning Algorithms

Zhang,

Liu,

et al. 2023

Molecules

View full text Add to dashboard Cite

Rapid and accurate detection of protein toxins is crucial for public health. The Raman spectra of several protein toxins, such as abrin, ricin, staphylococcal enterotoxin B (SEB), and bungarotoxin (BGT), have been studied. Multivariate scattering correction (MSC), Savitzky–Golay smoothing (SG), and wavelet transform methods (WT) were applied to preprocess Raman spectra. A principal component analysis (PCA) was used to extract spectral features, and the PCA score plots clustered four toxins with two other proteins. The k-means clustering results show that the spectra processed with MSC and MSC-SG methods have the best classification performance. Then, the two data types were classified using partial least squares discriminant analysis (PLS-DA) with an accuracy of 100%. The prediction results of the PCA and PLS-DA and the partial least squares regression model (PLSR) perform well for the fingerprint region spectra. The PLSR model demonstrates excellent classification and regression ability (accuracy = 100%, Rcv = 0.776). Four toxins were correctly classified with interference from two proteins. Classification models based on spectral feature extraction were established. This strategy shows excellent potential in toxin detection and public health protection. These models provide alternative paths for the development of rapid detection devices.

show abstract

“…During the model and feature selection process, evaluation metrics and methods are necessary to assess the model's performance. We employed ten-fold cross-validation to split the dataset, a method that provides a more reasonable and accurate evaluation, especially when dealing with small datasets [37]. The performance of the model is determined by accuracy and F1_Score.…”

Section: Feature and Model Selectionmentioning

confidence: 99%

Machine Learning Phase Prediction of Light-Weight High-Entropy Alloys Containing Aluminum, Magnesium, and Lithium

Li,

Liu,

Yan

et al. 2024

Metals

View full text Add to dashboard Cite

With the development of society, there is an increasingly urgent demand for light-weight, high-strength, and high-temperature-resistant structural materials. High-entropy alloys (HEAs) owe much of their unusual properties to the selection among three phases: solid solution (SS), intermetallic compound (IM), and mixed SS and IM (SS and IM). Therefore, accurate phase prediction is crucial for guiding the selection of element combinations to form HEAs with desired properties. Light high-entropy alloys (LHEAs), as a significant branch of HEAs, exhibit excellent performance in terms of specific strength. In this study, we employ a machine learning (ML) method to realize the design of light-weight high-entropy alloys based on solid solutions. We determined the Gradient Boosting Classifier model as the best machine learning model through a two-step feature and model selection, in which its accuracy and F1_Score achieve 0.9166 and 0.8923. According to the predicted results, we obtained Al28Li35Mg15Zn10Cu12 LHEAs, which are mainly composed of 90% solid solution. This alloy accords with the prediction results of machine learning. But it is made up of a two-phase solid solution. In order to obtain a light-weight high-entropy alloy dominated by a single solid solution, we designed Al24Li15Mg26Zn9Cu26 LHEAs on the basis of machine learning prediction results accompanied by expert experience. Its main structure includes a single-phase solid solution. Our work provides an alternative approach to the computational design of HEAs and provides a direction for future exploration of light-weight high-entropy alloys.

show abstract

Improving the prediction of wind speed and power production of SCADA system with ensemble method and 10-fold cross-validation

Cited by 13 publications

References 37 publications

Global cropland nitrous oxide emissions in fallow period are comparable to growing‐season emissions

Global cropland nitrous oxide emissions in fallow period are comparable to growing‐season emissions

Performance of Classification Models of Toxins Based on Raman Spectroscopy Using Machine Learning Algorithms

Machine Learning Phase Prediction of Light-Weight High-Entropy Alloys Containing Aluminum, Magnesium, and Lithium

Contact Info

Product

Resources

About