Search Results (365)

Multi-source fusion techniques have emerged as cutting-edge approaches for spatial precipitation estimation, yet they face persistent accuracy limitations, particularly under extreme conditions. Machine learning offers new opportunities to improve the precision of these estimates. To bridge this gap, we propose a hybrid artificial neural network–geographically weighted regression (ANN–GWR) model that synergizes event recognition and quantitative estimation. The ANN module dynamically identifies precipitation events through nonlinear pattern learning, while the GWR module captures location-specific relationships between multi-source data for calibrated rainfall quantification. Validated against 60-year historical data (1960–2020) from China’s Yongding River Basin, the model demonstrates superior performance through multi-criteria evaluation. Key results reveal the following: (1) the ANN-driven event detection achieves 10% higher accuracy than GWR, with a 15% enhancement for heavy precipitation events (>50 mm/day) during summer monsoons; (2) the integrated framework improves overall fusion accuracy by more than 10% compared to conventional GWR. This study advances precipitation estimation by introducing an artificial neural network into the event recognition period. Full article

The escalating threat of climate change has intensified the global urgency to accurately predict carbon dioxide (CO₂) emissions for sustainable development, particularly in developing economies experiencing rapid industrialization and globalization. Traditional Extreme Learning Machines (ELMs) offer rapid learning but often yield unstable performance due to random parameter initialization. This study introduces a novel hybrid model, Red-Billed Blue Magpie Optimizer-tuned ELM (RBMO-ELM) which harnesses the intelligent foraging behavior of red-billed blue magpies to optimize input-to-hidden layer weights and biases. The RBMO algorithm is first benchmarked on 15 functions from the CEC2015 test suite to validate its optimization effectiveness. Subsequently, RBMO-ELM is applied to predict Indonesia’s CO₂ emissions using a multidimensional dataset that combines economic, technological, environmental, and globalization-driven indicators. Empirical results show that the RBMO-ELM significantly surpasses several state-of-the-art hybrid models in accuracy (higher R²) and convergence efficiency (lower error). A permutation-based feature importance analysis identifies social globalization, GDP, and ecological footprint as the strongest predictors underscoring the socio-economic influences on emission patterns. These findings offer both theoretical and practical implications that inform data-driven Artificial Intelligence (AI) and Machine Learning (ML) applications in environmental policy and support sustainable governance models. Full article

Objective: Shoulder dystocia (ShD) is a rare but serious obstetric emergency associated with significant neonatal morbidity. This study aimed to evaluate the predictive performance of machine learning (ML) models based on fetal biometric ratios and clinical characteristics for the identification of ShD in pregnancies without clinical suspicion of macrosomia. Methods: We conducted a retrospective case-control study including 284 women (84 ShD cases and 200 controls) who underwent spontaneous vaginal delivery between 37 and 42 weeks of gestation. All participants had an estimated fetal weight (EFW) below the 90th percentile according to Hadlock reference curves. Univariate and multivariate logistic regression analyses were performed on maternal and neonatal parameters, and statistically significant variables (p < 0.05) were used to construct adjusted odds ratio (aOR) models. Supervised ML models—Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGB)—were trained and tested to assess predictive accuracy. Performance metrics included AUC-ROC, sensitivity, specificity, accuracy, and F1-score. Results: The BPD/AC ratio and AC/FL ratio markedly enhanced the prediction of ShD. When added to other features in RF models, the BPD/AC ratio got an AUC of 0.884 (95% CI: 0.802–0.957), a sensitivity of 68%, and a specificity of 83%. On the other hand, the AC/FL ratio, along with other factors, led to an AUC of 0.896 (95% CI: 0.805–0.972), 68% sensitivity, and 90% specificity. Conclusions: In pregnancies without clinical suspicion of macrosomia, ML models integrating fetal biometric ratios with maternal and labor-related factors significantly improved the prediction of ShD. These models may support clinical decision-making in low-risk deliveries where ShD is often unexpected. Full article

Accurately hindcasting waves in semi-enclosed, fetch-limited basins remains challenging for reanalysis models, which tend to underestimate storm peaks near the coast. We developed interpretable ML models for Rijeka Bay (northern Adriatic) using only wind observations from two land-based wind stations to predict buoy H_m0 measurements spanning 2009–2011 (testing) and 2019–2021 (training and validation). The tested tree-based models included Random Forest, XGBoost, and Explainable Boosting Machine. This study introduces a novel approach in the literature by employing weighted schemes and feature engineering to enhance the predictive performance of interpretable, low-complexity machine learning models in hindcasting waves. Representing wind direction as sine–cosine components generally reduced RMSE and BIAS relative to traditional speed–direction inputs, while an exponential sample weight scheme that emphasized storm waves halved extreme H_m0 underprediction without inflating overall RMSE. The best-performing model, a Random Forest model, achieved an RMSE of 0.096 m and a correlation of 0.855 on the unseen test set—30% lower overall RMSE and 50% lower extreme wave RMSE than the MEDSEA and COEXMED hindcasts. Additionally, the underprediction was reduced by 90% compared to these reanalysis models. The method offers a computationally lightweight, transferable supplement to numerical wave guidance for coastal engineering and harbor operations. Full article

Modern energy storage systems for both power and transportation are highly related to lithium-ion batteries (LIBs). However, their safety depends on a potentially hazardous failure mode known as thermal runaway (TR). Predicting and classifying TR causes can widely enhance the safety of power and transportation systems. This paper presents an advanced machine learning method for forecasting and classifying the causes of TR. A generative model for synthetic data generation was used to handle class imbalance in the dataset. Hyperparameter optimization was conducted using Optuna for four classifiers: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), tabular network (TabNet), and Extreme Gradient Boosting (XGBoost). A three-fold cross-validation approach was used to guarantee a robust evaluation. An open-source database of LIB failure events is used for model training and testing. The XGBoost model outperforms the other models across all TR categories by achieving 100% accuracy and a high recall (1.00). Model results were interpreted using SHapley Additive exPlanations analysis to investigate the most significant factors in TR predictors. The findings show that important TR indicators include energy adjusted for heat and weight loss, heater power, average cell temperature upon activation, and heater duration. These findings guide the design of safer battery systems and preventive monitoring systems for real applications. They can help experts develop more efficient battery management systems, thereby improving the performance and longevity of battery-operated devices. By enhancing the predictive knowledge of temperature-driven failure mechanisms in LIBs, the study directly advances thermal analysis and energy storage safety domains. Full article

In complex environments where satellite signals may be interfered with, it is difficult to achieve precise positioning of high-speed aerial vehicles solely through the inertial navigation system. To overcome this challenge, this paper proposes an NGO-ELM geomagnetic matching-assisted navigation algorithm, in which the Northern Goshawk Optimization (NGO) algorithm is used to optimize the initial weights and biases of the Extreme Learning Machine (ELM). To enhance the matching performance of the NGO-ELM algorithm, three improvements are proposed to the NGO algorithm. The effectiveness of these improvements is validated using the CEC2005 benchmark function suite. Additionally, the IGRF-13 model is utilized to generate a geomagnetic matching dataset, followed by comparative testing of five geomagnetic matching models: INGO-ELM, NGO-ELM, ELM, INGO-XGBoost, and INGO-BP. The simulation results show that after the airborne equipment acquires the geomagnetic data, it only takes 0.27 µs to obtain the latitude, longitude, and altitude of the aerial vehicle through the INGO-ELM model. After unit conversion, the average absolute errors are approximately 6.38 m, 6.43 m, and 0.0137 m, respectively, which significantly outperform the results of four other models. Furthermore, when noise is introduced into the test set inputs, the positioning error of the INGO-ELM model remains within the same order of magnitude as those before the noise was added, indicating that the model exhibits excellent robustness. It has been verified that the geomagnetic matching-assisted navigation algorithm proposed in this paper can achieve real-time, accurate, and stable positioning, even in the presence of observational errors from the magnetic sensor. Full article

Background/Objectives: Differentiated Thyroid Cancer (DTC), comprising papillary and follicular carcinomas, is the most common type of thyroid cancer. This is highly infectious and increasing at a higher rate. Some patients experience recurrence even after undergoing successful treatment. Early signs of recurrence can be hard to identify, and the existing health care system cannot always identify it on time. Therefore, predicting its recurrence accurately and in its early stage is a significant clinical challenge. Numerous advanced technologies, such as machine learning, are being used to overcome this clinical challenge. Thus, this study presents a novel approach for predicting the recurrence of DTC. The key objective is to improve the prediction accuracy through hyperparameter optimization. Methods: In order to achieve this, we have used a metaheuristic algorithm, the whale optimization algorithm (WOA) and its modified version. The modifications that we introduced in the original WOA algorithm are a piecewise linear chaotic map for population initialization and inertia weight. Both of our algorithms optimize the hyperparameters of the Extreme Gradient Boosting (XGBoost) model to increase the overall performance. The proposed algorithms were applied to the dataset collected from the University of California, Irvine (UCI), Machine Learning Repository to predict the chances of recurrence for DTC. This dataset consists of 383 samples with a total of 16 features. Each feature captures the critical medical and demographic information. Results: The model has shown an accuracy of 99% when optimized with WOA and 97% accuracy when optimized with the modified WOA. Conclusions: Furthermore, we have compared our work with other innovative works and validated the performance of our model for the prediction of DTC recurrence. Full article

Metal-organic frameworks (MOFs) have been extensively studied for hydrogen storage due to their unique properties. This paper aims to develop several regression-based machine learning models to predict the hydrogen storage capacity of MOFs, including artificial neuron network (ANN), support vector regression (SVR), random forest (RF), extreme learning machine (ELM), kernel extreme learning machine (KELM), and generalized regression neural network (GRNN). An improved population-based metaheuristic optimization algorithm, the artificial lemming algorithm (ALA), is employed to select the hyperparameters of these machine learning models, enhancing their performance. All developed models are trained and tested using experimental data from multiple studies. The performance of the models is evaluated using various statistical metrics, complemented by regression plots, error analysis, and Taylor graphs to further identify the most effective predictive model. The results show that the ALA-RF model obtains the best performance in predicting hydrogen storage, with optimal values of coefficient of determination (R²), root mean square error (RMSE), Willmott’s index (WI), and weighted average percentage error (WAPE) in both training and testing phases (0.9845 and 0.9840, 0.2719 and 0.2828, 0.9961 and 0.9959, and 0.0667 and 0.0714, respectively). Additionally, pressure is identified as the most significant feature for predicting hydrogen storage in MOFs. These findings provide an intelligent solution for the selection of MOFs and optimization of operational conditions in hydrogen storage processes. Full article

The increasing concentration of greenhouse gases is amplifying the global risk of drought on crop productivity. This study sought to investigate the effects of drought on the growth of maize (Zea mays L.) seedlings. A total of 78 maize hybrids were employed in this study to replicate drought conditions through the potting method. The maize seedlings were subjected to a 10-day period of water breakage following a standard watering cycle until they reached the third leaf collar (V3) stage. Parameters including plant height, stem diameter, chlorophyll content, and root number were assessed. The eight phenotypic traits include the fresh and dry weights of both the aboveground and underground parts. Three machine learning methods—random forest (RF), K-nearest neighbor (KNN), and extreme gradient boosting (XGBoost)—were employed to systematically analyze the relevant traits of maize seedlings’ drought tolerance and to assess their predictive performance in this regard. The findings indicated that plant height, aboveground weight, and chlorophyll content constituted the primary indices for phenotyping maize seedlings under drought conditions. The XGBoost model demonstrated optimal performance in the classification (AUC = 0.993) and regression (R² = 0.863) tasks, establishing itself as the most effective prediction model. This study provides a foundation for the feasibility and reliability of screening drought-tolerant maize varieties and refining precision breeding strategies. Full article

Drought and temperature extremes are major abiotic stressors limiting legume productivity worldwide. This study investigates the germination and early seedling responses of six cultivars belonging to three Vicia species (V. sativa, V. pannonica, and V. narbonensis) under varying levels of polyethylene glycol (PEG)-induced drought and temperature conditions (12 °C, 18 °C, and 24 °C) in vitro. Significant cultivar-dependent differences were observed in the germination rate (GR), shoot and root length (SL and RL), fresh and dry weight (FW and DW), and vigor index (VI). The Ayaz cultivar exhibited superior performance, particularly under severe drought (10% PEG) and optimal temperature (24 °C), while Özgen and Balkan were most sensitive to stress. Principal component and correlation analyses revealed strong associations between the vigor index, shoot height, and fresh and dry weight, particularly in high-performing genotypes. To further model and predict stress responses, four machine learning (ML) algorithms—Random Forest (RF), k-Nearest Neighbors (k-NNs), Multilayer Perceptron (MLP), and Support Vector Machines (SVMs)—were employed. Based on model performance metrics, and considering high R² values along with low RMSE and MAE values, the MLP model demonstrated the most accurate predictions for the GR (R² = 0.95, RMSE = 0.06, MAE = 0.05) and VI (R² = 0.99, RMSE = 0.02, MAE = 0.01) parameters. In contrast, the RF model yielded the best results for the SL (R² = 0.98, RMSE = 0.02, MAE = 0.02) and DW (R² = 0.93, RMSE = 0.06, MAE = 0.04) parameters, while the highest prediction accuracy for the RL (R² = 0.83, RMSE = 0.09, MAE = 0.07) and FW (R² = 0.97, RMSE = 0.05, MAE = 0.03) parameters was achieved using the SVM model. Comparative analysis with recent studies confirmed the applicability of ML in stress physiology and genotype screening. This integrative approach offers a robust framework for genotype selection and stress tolerance modeling in legumes, contributing to developing climate-resilient crops. Full article

The battery management system (BMS) is crucial for the efficient operation of batteries, with state of health (SOH) prediction being one of its core functions. Accurate SOH prediction can optimize battery management, enhance utilization and range, and extend battery lifespan. This study proposes an SOH estimation model for lithium-ion batteries that integrates the Crested Porcupine Optimizer (CPO) for parameter optimization, Extreme Learning Machine (ELM) for prediction, and Adaptive Bandwidth Kernel Function Density Estimation (ABKDE) for uncertainty quantification, aiming to enhance the long-term reliability and sustainability of energy storage systems. Health factors (HFs) are extracted by analyzing the charging voltage curves and capacity increment curves of lithium-ion batteries, and their correlation with battery capacity is validated using Pearson and Spearman correlation coefficients. The ELM model is optimized using the CPO algorithm to fine-tune input weights (IWs) and biases (Bs), thereby enhancing prediction performance. Additionally, ABKDE-based probability density estimation is introduced to construct confidence intervals for uncertainty quantification, further improving prediction accuracy and stability. Experiments using the NASA battery aging dataset validate the proposed model. Comparative analysis with different models demonstrates that the CPO-ELM-ABKDE model achieves SOH estimation with a mean absolute error (MAE) and root-mean-square error (RMSE) within 0.65% and 1.08%, respectively, significantly outperforming other approaches. Full article

Accurate renewable energy forecasting is crucial for grid stability and efficient energy management. This study introduces a hybrid model that combines signal decomposition and artificial intelligence to enhance the prediction of solar radiation and wind speed. The framework uses a one-stage decomposition strategy, applying variational mode decomposition and an improved empirical mode decomposition method with adaptive noise. This process effectively extracts meaningful components while reducing background noise, improving data quality, and minimizing uncertainty. The complexity of these components is assessed using entropy-based selection to retain only the most relevant features. The refined data are then fed into advanced predictive models, including a bidirectional neural network for capturing long-term dependencies, an extreme learning machine, and a support vector regression model. These models address nonlinear patterns in the historical data. To optimize forecasting accuracy, outputs from all models are combined using a least-squares regression technique that assigns optimal weights to each prediction. The hybrid model was tested on datasets from three geographically diverse locations, encompassing varying weather conditions. Results show a notable improvement in accuracy, achieving a root mean square error as low as 2.18 and a coefficient of determination near 0.999. Compared to traditional methods, forecasting errors were reduced by up to 30%, demonstrating the model’s effectiveness in supporting sustainable and reliable energy systems. Full article

In subsurface geological mapping, it is more than advisable to compare different solutions obtained with neural and other algorithms. Here, for such comparison, we used the previously published and well-prepared dataset of subsurface data collected from the Bjelovar Subdepression, a 2900 km² large regional macrounit in the Croatian part of the Pannonian Basin System. Data on depth were obtained for the youngest (the shallowest) Lonja Formation (Pliocene, Quaternary) and mapped using neural network (NN), inverse distance weighting (IDW), and ordinary kriging (OK) algorithms. The obtained maps were compared based on square error (using k-fold cross-validation) and the visual interpretation of isopaches. Two other algorithms were also tested, namely, random forest (RF) and extreme gradient boosting (XGB) algorithms, but they were rejected as inappropriate for this purpose solely based on the visuals of the obtained maps, which did not follow any interpretable geological structures. The results showed that NN is a highly adjustable method for interpolation, with adjustment for numerous hyperparameters. IDW showed its strength as one of the classical interpolators, and its results are always located close to the top if several methods are compared. OK is the relative winner, showing the flexibility of variogram analysis regarding the number of data points and possible clustering. The presented variogram model, even with a relatively high sill and occasional nugget effect, can be well fitted into OK, giving better results than other methods when applied to the presented area and datasets. This was not surprising because kriging is a well-established method used exclusively for interpolation. In contrast, NN and machine learning algorithms are used in many fields, and these algorithms, particularly the fitting of hyperparameters in NN, simply cannot be the best solution for all. Full article

Background/Objectives: Adverse pregnancy outcomes (APOs), which include hypertensive disorders of pregnancy (gestational hypertension, preeclampsia, and related disorders), gestational diabetes, preterm birth, fetal growth restriction, low birth weight, small-for-gestational-age newborn, placental abruption, and stillbirth, are health risks for pregnant women that can have fatal outcomes. This study’s aim is to investigate the usefulness of artificial intelligence (AI) in improving these outcomes and includes changes in the utilization of ultrasound, continuous monitoring, and an earlier prediction of complications, as well as being able to individualize processes and support clinical decision-making. This study evaluates the use of AI in improving at least one APO. Methods: PubMed, Web of Science, and Scopus databases were searched and limited to the English language, humans, and between 2020 and 2024. This scoping review included peer-reviewed articles across any study design. However, systematic reviews, meta-analyses, unpublished studies, and grey literature sources (e.g., reports and conference abstracts) were excluded. Studies were eligible for inclusion if they described the use of AI in improving APOs and the associated ethical issues. Results: Five studies met the inclusion criteria and were included in this scoping review. Although this review initially aimed to evaluate AI’s role across a wide range of APOs, including placental abruption and stillbirth, the five selected studies focused primarily on preterm birth, hypertensive disorders of pregnancy, and gestational diabetes. None of the included studies addressed placental abruption or stillbirth directly. The studies primarily utilized machine-learning models, including extreme gradient boosting (XGBoost) and random forest (RF), showing promising results in enhancing prenatal care and supporting clinical decision-making. Ethical considerations, including algorithmic bias, transparency, and the need for regulatory oversight, were highlighted as critical challenges. Conclusions: The application of these tools can improve prenatal care by predicting obstetric complications, but ethics and transparency are pivotal. Empathy and humanization in healthcare must remain fundamental, and flexible training mechanisms are needed to keep up with rapid innovation. AI offers an opportunity to support, not replace, the doctor–patient relationship and must be subject to strict legislation if it is to be used safely and fairly. Full article

To overcome the limitations of characteristic parameter identification and inadequate fault recognition rates in bearings, a bearing fault diagnosis method combining the improved whale optimization algorithm (IWOA), variational mode decomposition (VMD), and kernel extreme learning machine (KELM) is proposed. Firstly, to improve the convergence behavior and global search capability of the WOA, we introduced adaptive weight, a variable spiral shape parameter, and a Cauchy neighborhood perturbation strategy to improve the performance of the original algorithm. Secondly, to enhance the effectiveness of feature extraction, the IWOA was used to optimize the number of modal components and penalty coefficients in the VMD algorithm; then, we could obtain the optimal modal components and construct feature vectors based on the optimal modal components. Next, we used the IWOA to optimize the two key parameters, the regularization coefficient C and kernel parameter γ of KELM, and the feature vector was used as the input of KELM to achieve fault diagnosis. Finally, data collected from different experimental platforms were used for experimental analysis. The results indicate that the IWOA-VMD-KELM bearing fault diagnosis model significantly improved its accuracy compared to other models, achieving accuracies of 98.8% and 98.4% on the CWRU dataset and Southeast University dataset, respectively. Full article