Search

Since there has been concern about food security, accurate prediction of wheat yield prior to harvest is a key component. Random Forest (RF) has been used in many classification and regression applications, such as yield estimation, and the performance of RF has improved by tuning its hyperparameters. In this paper, different changes are made to traditional RF for yield estimation, and the performance of RF is evaluated. Accordingly, RFs constructed using various weak learners, as well as a combined RF consisting of different weak learners are assessed by growing weak Gaussian Process Regression (GPR), Decision Tree (DT), Neural Network (NN), and Stepwise Regression (SW) models in the forest. The input data to DTs are also partitioned into leaves in N (e.g., two) dimensional feature space by using clustering in each parent node. In addition, a subset of the training set is randomly sampled with replacement for training a learner in the forest, instead of randomly sampling the whole training set in traditional RF. Using clustering in DTs added flexibility while utilizing NN as a weak learner yielded the most favorable outcomes in our research. The number of input training samples (Itree) to each tree was also identified as a new hyperparameter to the forest, and the prediction results were more influenced by the Itree compared to the known hyperparameters, such as the number of trees in the forest (ntree) and the number of features for each tree (mtry). [ABSTRACT FROM AUTHOR]

An in-depth understanding of a key element such as lake evaporation is particularly beneficial in developing the optimal management approach for reservoirs. In this study, we first aim to evaluate the applicability of regressors Random Forest (RF), Gradient Booting (GB), and Decision Tree (DT), K Nearest Neighbor (kNN), and XGBoost architectures to predict daily lake evaporation of five reservoirs in the Awash River basin, Ethiopia. The best performing models, Gradient Boosting and XGBoost, are then explained through an explanatory framework using daily climate datasets. The interpretability of the models was evaluated using the Shapley Additive explanations (SHAP). The GB model performed better with (RMSE = 0.045, MSE = 0.031, MAE = 0.002, NSE = 0.997, KGF = 0.991, RRMSE = 0.011) for Metehara Station, (RMSE = 0.032, MSE = 0.024, MAE = 0.001, NSE = 0.998, KGF = 0.999, RRMSE = 0.008) at Melkasa Station, and Dubti Station (RMSE = 0.13, MSE = 0.09, MAE = 0.017, NSE = 0.982, KGF = 0.977,RRMSE = 0.022) as the same as of XGBoost. The factors with the greatest overall impact on the daily evaporation for GB and XGboost Architecture were the SH, month, Tmax, and Tmin for Metehara and Melkasa, and Tmax, Tmin, and month had the greatest impact on the daily evaporation for Dubti. Furthermore, the interpretability of the models showed good agreement between the MLAs simulations and the actual hydro-climatic evaporation process. This result allows decision makers to not only rely on the results of an algorithm, but to make more informed decisions by using interpretable results for better control of the basin reservoir operating rules. [ABSTRACT FROM AUTHOR]

Estimating total sediment discharge is challenging. This study aims to assess performances of various data-driven models including empirical equations, machine learning (ML), and ensemble models for such estimations. The ML models include Support Vector Machine (SVM), Artificial Neural Network (ANN), K Nearest Neighbor (KNN), Random Forest (RF), and Decision Tree Regression (DTR). For this purpose, 543 widely-ranged data were collected from the United States Geological Survey (USGS) resources and used to train and test different models. Ranking different models demonstrated that Ackers and White's equation outperformed multiple linear regression (MLR) and SVM, which indicates that all ML models do not necessarily outperform empirical equations. Moreover, despite conducting multiple runs and parameter tuning, the results consistently indicated that increasing the number of hidden layers and neurons in ANN structures did not significantly improve the overall performance of the ANN models. In addition, the nonlinear ensemble model outperformed all methods and placed first in the ranking. Despite a notable difference between metrics obtained by KNN for the train and test data, it outperformed other methods and ranked second, while ANN achieved the third-best ranking place. The obtained result was also confirmed by the reliability analysis and confidence limits. However, due to negative predictions for some small sediment discharges by the nonlinear ensemble method, it did not demonstrate good reliability. Finally, the comparative analysis indicates that selecting a suitable model for estimating sediment discharges with a desirable accuracy is challenging, while further studies are required to assess other ML models or variants of ensemble models. [ABSTRACT FROM AUTHOR]

This paper addresses the issue of the prediction of slope stability with machine learning (ML) applications. Five well-known and popular ML algorithms, namely neural network (NNet), decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN), and random forest (RF), are used to demonstrate the effectiveness of the ML algorithms for predicting binary classification of slope stability based on a case history dataset containing outliers. This study also evaluates the winsorization method used to treat outliers in the dataset by outlining the effect of outliers on the prediction performances of models. To this end, the performance of all the generated ML models is assessed and compared both for unwinsorized (e.g., raw) and winsorized datasets based on performance metrics (i.e., Recall, Precision, Accuracy, and F1-Score) obtained from the confusion matrix. The experimental outputs showed that the application of winsorization enhanced the prediction performance of the models, and thus, all ML models built with winsorized datasets outperformed the unwinsorized ones. In this paper, the RF model achieves the best prediction performance, especially in the case of the winsorized dataset used. Moreover, it is found that SVM is the most sensitive algorithm to outliers as against the other ML algorithms, while the kNN algorithm is the least among the applied algorithms. Results showed that the increment percentage of accuracy nearly reaches 20% for the SVM model and the following 18% for DT, 11% for NNet, 10% for RF, and 4% for kNN, respectively. Furthermore, the results of the study reveal not only the performance of ML algorithms for the slope stability problem but also show how the handling of outliers of a dataset affects the models' prediction performance. [ABSTRACT FROM AUTHOR]

Lithology identification is critical in the interpretation of well-logging data for petroleum exploration and development. However, the limited availability of labeled well-logging data for machine learning model training can lead to compromised accuracy in lithology classification models. Here, we propose a semi-supervised lithology identification model to overcome this challenge. Our framework consists of Bayesian optimization for tuning ensemble algorithms, including random forest, gradient boosting decision tree, extremely randomized trees, and adaptive boosting, to establish a high-quality baseline model for semi-supervised learning. We also employ a self-training strategy to increase the number of labeled samples in the training set and use the predicted label with the highest confidence as a pseudo-label to reduce the accumulation of deviation caused by incorrect pseudo-labels. Our semi-supervised coarse-to-fine framework improves rock classification accuracy, particularly for sandstone. Testing our model on well-logging data from two real regions, we found that the ExtraRF-based semi-supervised model in the HGF area performs the best, with a maximum classification accuracy of 91.6 % , which is 5 % higher than the original coarse-to-fine model without using Bayesian optimization and pseudo-labeling techniques. [ABSTRACT FROM AUTHOR]

Lithofacies identification is critical to energy exploration and reservoir evaluation. Machine learning provides a way to use logging data for lithofacies intelligence identification. However, labeled logging data are usually scarce, which makes the currently used supervised algorithms less effective, so semi-supervised methods have received attention from researchers. In this paper, we propose to apply Tri-Training to the field of lithofacies recognition. The framework used Random Forest (RF), Gradient-Boosted Decision Trees (GBDT), and Support Vector Machine (SVM), as the baseline supervised classifiers, and based on the idea of inductive semi-supervised methods and ensemble learning. Baseline classifiers are trained and iterated using unlabeled data to obtain effect improvement. The final results are output in an ensemble paradigm. We used seven logging parameters from two wells as input and divide the data randomly 10 times for training and testing. With only five samples of each lithology, the prediction accuracy improved by the average of 2.1% and 14.5% in both wells compared to the baseline methods. In addition, we also compared two commonly used semi-supervised methods, label propagation algorithm (LPA) and Co-Training. The experimental results also confirm that Tri-training has the better and more stable performance. The Tri-training method in this paper can be effectively applied to lithofacies identification under scarce labeled logging data. [ABSTRACT FROM AUTHOR]

Drilling costs and time are directly affected by the rate of penetration (ROP). Gas/oil well drilling in challenging environments is a costly operation due to the high cost of wellbore construction, and drilling optimization requires real-time decision-making. Therefore, it is necessary to estimate ROP accurately and thus assist in optimizing the drilling process. In this study, we used total depth, weight on hook, bit, revolutions per minute, torque, standpipe pressure, flow rates, mud weight, mud viscosity, hole size, and formation hardness as input parameters to forecast ROP. Nine machine learning algorithms, i.e., multiple linear regression (MLR), lasso regression, ridge regression, decision tree (DT), bootstrap aggregating (Bagging), random forest (RF), gradient boosting machines (GBM), symbolic regression (SR), and artificial neural networks (ANN) were performed using a dataset consists of 3484 observations. Moreover, several network hyperparameters were adjusted, indicating that using a deep artificial feed-forward network, i.e., [9–11-1] neurons with logarithmic sigmoid transfer function as a predictor model, provided the most accurate model. Results showed that the random forest and artificial neural network models have the highest accuracy, and it estimates ROP with correlation coefficients of 0.93. Overall, the methodology employed in this paper performed well in predicting ROP in the absence of some unavailable parameters such as UCS. Highlights: • Effect of weight on hook (WOH) on rate of penetration (ROP) investigated for the first time by means of multiple (nine) robust machine-learning algorithms. • Multiple linear regression (MLR), lasso regression, ridge regression, decision tree (DT), bootstrap aggregating (Bagging), random forest (RF), gradient boosting machines (GBM), symbolic regression (SR), and artificial neural networks (ANN) intelligent models were proposed for estimating drilling rate of penetration. • The accuracy of the models was ranked as: ANN > RF > GBM > BA > DT > SR > Lasso > MLR > Ridge. • A comprehensive databank of 3484 data points from a gas field in the Zagros basin was used. The predicted rate of penetration is highly influenced by the values of depth, WOH and RPM. [ABSTRACT FROM AUTHOR]

For a long time, elucidating the tectonic setting of unknown rock samples has been a focal point for geologists. Traditional methodologies for this purpose have been scrutinized increasingly due to their inherent limitations. In response to these challenges, this paper applies modern machine learning techniques to analyze the geochemical data of igneous rocks and improve understanding of tectonic settings. By employing a variety of machine learning models, including Decision Trees, K-Nearest Neighbors, Support Vector Machines, Random Forests, Extreme Gradient Boosting, and Artificial Neural Networks, and training with 23 features comprising nine major elements (SiO2, TiO2, Al2O3, CaO, MgO, MnO, Na2O, K2O, and P2O5) along with 14 trace elements (La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, and Lu), the study successfully distinguished between seven different tectonic settings. Among these models, Random Forest, Extreme Gradient Boosting, and Artificial Neural Networks demonstrated superior classification accuracy and recall rates, with accuracies of 0.85, 0.87, and 0.86, respectively. This validates the effectiveness and potential of machine learning technologies in distinguishing the tectonic settings of igneous rocks through their geochemical elements. To enable geologists and researchers to more accurately understand and predict the origins of igneous rocks without the need to master machine learning knowledge, a user-friendly software, GeoTectAI, has been developed. [ABSTRACT FROM AUTHOR]