Individual Models Research Articles

Integrative deep learning and radiomics analysis for ovarian tumor classification and diagnosis: a multicenter large-sample comparative study.

This study aims to evaluate the effectiveness of combining transvaginal ultrasound (US)-based radiomics and deep learning model for the accurate differentiation between benign and malignant ovarian tumors in large-scale studies. A multicenter retrospective study collected grayscale and color US images of ovarian tumors. Patients were divided into training, internal, and external validation groups. Models including a convolutional neural networks (CNN), optimal radiomics, and a combined model were constructed and evaluated for predictive performance using area under curve (AUC), sensitivity, and specificity. The DeLong test compared model AUCs with O-RADS and expert assessments. 3193 images from 2078 patients were analyzed. The CNN achieved AUCs of 0.970 (internal) and 0.959 (external), respectively. Optimal radiomic model achieved AUCs of 0.949 (internal) and 0.954 (external), respectively. The combined CNN-radiomics model attained the highest AUC of 0.977 (internal) and 0.972 (external), respectively, outperforming individual models, O-RADS, and expert methods (p < 0.05). The combined CNN-radiomics model using transvaginal US images provides more accurate and reliable ovarian tumor diagnosis, enhancing malignancy prediction and offering clinicians a more precise diagnostic tool.

Enhancing prediction of cervical lymph node metastasis in papillary thyroid carcinoma through nodule-oriented quantification: combined S-Detect and ultrasound elastography.

Papillary thyroid carcinoma (PTC) frequently metastasizes to cervical lymph nodes (LNs), with metastasis rates of 20-90%, significantly impacting patient prognosis. Although ultrasound (US) is the primary preoperative assessment tool, its accuracy (Acc) in detecting LN metastasis (LNM) remains insufficient, with conventional US detecting only 50% of confirmed cases. This study aimed to improve the prediction of cervical LNM in PTC by combining quantitative nodule orientation parameters with multi-modal US techniques. Data were retrospectively collected from 117 patients (141 nodules: 85 non-metastasis and 56 metastasis) who underwent PTC resection and cervical LN dissection from September 2023 to May 2024. All patients underwent US, US elastography (UE), and S-Detect examinations before surgery. For each nodule, the angle between the nodule's maximum diameter and the skin was measured. Logistic regression analysis assessed the correlation between each variable and cervical LNM, identified significant predictive factors, and a predictive model presented as a nomogram was constructed. Univariate analysis showed significant differences between non-metastasis and metastasis groups in orientation quantification [-9.3° (-35.2°, 17.2°) vs. 13.9° (-1.6°, 54.0°), P<0.001], age (P=0.002), maximum nodule diameter (P=0.017), boundary (P=0.021), microcalcifications on S-Detect (P=0.014), microcalcifications (P=0.036), and ECI scores (P=0.043). Multivariate analysis identified seven independent predictors for cervical LNM, with S-Detect-detected microcalcifications showing the highest odds ratio (OR) [OR =4.159; 95% confidence interval (CI): 1.545-11.199]. The combined predictive model incorporating conventional US, UE, S-Detect, and orientation quantification demonstrated superior diagnostic performance [area under the curve (AUC) =0.861; 95% CI: 0.803-0.919] compared to individual models (P<0.001), achieving sensitivity (Sen) of 0.911 and specificity (Spe) of 0.659. The nomogram showed good calibration with no significant deviation (χ2=3.271; P=0.926). S-Detect accurately identifies the direction of the maximum diameter of thyroid nodules, and quantification of the longitudinal section orientation can be used as an independent predictor for LNM in PTC.

Enhancing Bipolar Disorder Detection Using Heterogeneous Ensemble Machine Learning Techniques

This paper introduces a novel Heterogeneous Ensemble Machine Learning (HEML) approach designed to detect bipolar disorder, a significant healthcare challenge that demands precise and prompt diagnosis for effective treatment. The HEML method integrates multiple machines learning models, incorporating various physiological, behavioral, and contextual data from patients. By using a comprehensive feature selection technique, relevant features are extracted from each data source and utilized to train individual classifiers for detecting mental disorders. The classifiers include Adaboost, Decision Tree, K-nearest neighbors, Multilayer Perceptron, Random Forest, Relevance Vector Machine, and XGB, with Logistic Regression serving as the meta-model. This ensemble of classifiers enhances overall performance by capturing a wider range of characteristics related to mental disorders. The research evaluates the HEML method across three bipolar disorder datasets: Dataset1 (a multimodal dataset), Dataset2 (a sensor-based dataset), and Dataset3 (a real-time dataset). The HEML approach surpasses traditional methods, achieving superior accuracy rates of 95.21% with Dataset 1, 99.28% with Dataset 2, and 99% with Dataset 3. It outperforms individual models in detecting bipolar disorder, delivering the best Precision, Recall, F1 score, and Kappa Score. This comparative analysis advances the field of mental health diagnosis by leveraging the strengths of ensemble machine learning to improve accuracy and reliability in detection methods.

Predictive model for converting leads into repeat order customer using machine learning

In the competitive business landscape, customer relationship management (CRM) is pivotal for managing customer relationships. Lead generation and customer retention are critical aspects of CRM as they contribute to sustaining business growth and profitability. Also, identifying and converting leads into repeat customers is essential for optimizing revenue and minimizing promotional costs. This study focuses on developing a predictive model using machine learning techniques to convert leads into repeat order customers in conventional businesses. Leveraging data from a motorcycle distribution company in Jakarta and Tangerang, the study compares the performance of various models for predicting repeat orders. This includes individual models like DeepFM, random forest, and gradient boosting decision tree models. Additionally, it explores the effectiveness of stacking these models using logistic regression as a meta-learner. Furthermore, the study implements backward feature elimination for feature selection and hyperband for hyperparameter tuning to enhance model performance. The results indicate that Stacking model using base model default configuration stands out as the most robust, achieving the highest scores in accuracy (0.95), area under the curve receiver-operating characteristic curve (AUC-ROC) (0.67), log loss (0.19), weighted average precision (0.95), weighted average recall (0.95), and weighted average F1- score (0.92), effectively handling the imbalanced dataset.

Long-term prediction for karst spring discharge and petroleum substances concentration based on the combination of LSTM and Transformer models.

Long-term prediction for karst spring discharge and petroleum substances concentration based on the combination of LSTM and Transformer models.

Non-experimental rapid identification of lower respiratory tract infections in patients with chronic obstructive pulmonary disease using multi-label learning.

Non-experimental rapid identification of lower respiratory tract infections in patients with chronic obstructive pulmonary disease using multi-label learning.

Combining machine learning models and rule engines in clinical decision systems: Exploring optimal aggregation methods for vaccine hesitancy prediction.

Combining machine learning models and rule engines in clinical decision systems: Exploring optimal aggregation methods for vaccine hesitancy prediction.

Ensemble approach to rumor detection with BERT, GPT, and POS features

As vast amounts of rumor content are transmitted on social media, it is very challenging to detect them. This study explores an ensemble approach to rumor detection in social media messages, leveraging the strengths of advanced natural language processing (NLP) models. Specifically, we implemented three distinct models: (i) generative pre-trained transformer (GPT) combined with a bidirectional long short-term memory (BiLSTM) network; (ii) a model integrating part-of-speech (POS) tagging with bidirectional encoder representations from transformers (BERT) and BiLSTM, and (iii) a model that merges POS tagging with GPT and BiLSTM. We included additional features from the dataset in all these models. Each model captures different linguistic, syntactical, and contextual features within the text, contributing uniquely to the classification task. To enhance the robustness and accuracy of our predictions, we employed an ensemble method using hard voting. This technique aggregates the predictions from each model, determining the final classification based on the majority vote. Our experimental results demonstrate that the ensemble approach significantly outperforms individual models, achieving superior accuracy in identifying rumors. To determine the performance of our model, we used PHEME and Weibo datasets available publicly. We found our model gave 97.6% and 98.4% accuracy, respectively, on the datasets and has outperformed the state-of-the-art models.

Enhancing Credit Card Fraud Detection using Ensemble Techniques

Abstract: Credit card fraud is one of the major detriments and a growing concern in the financial sector, causing enormous financial loss and a breakdown in confidence in digital payment systems. The motivation of this paper is to solve the challenge of having an accurate detection of fraudulent transactions and reducing false positives that inconvenience valid customers and strain financial institutions. The challenge is that there is an increase in sophistication regarding the techniques, which makes fraud hard to detect with traditional systems. It proposes an ensemble machine learning technique for credit card fraud detection, aiming at enhancing accuracy and the robustness of fraud detection systems. In this paper, we implement our methodology on a publicly available credit card transaction dataset with different ensemble learning models, namely, Random Forests, Gradient Boosting Machines, and XGBoost. We compare the performance of such models with classical machine learning approaches in terms of accuracy, precision, recall, and F1-score in order to decide their efficiency in detecting fraud cases. Our results prove that the performance of ensemble methods is much better as compared to individual machine learning models, therefore giving a high rate of detection of fraudulent transactions with lower false positive rates. For that reason, the implication of this research is very serious, as it will provide a better and more effective fraud-detection method for financial organizations that might prevent huge losses and inspire customer confidence by minimizing service disruption due to false alarms.

Development and validation of multi-sequence magnetic resonance imaging radiomics models for predicting tumor response to radiotherapy in locally advanced non-small cell lung cancer.

The significant heterogeneity of locally advanced non-small cell lung cancer (LA-NSCLC) poses challenges for clinical decision-making. Although various predictive methods currently exist, there remains a lack of an accurate and comprehensive approach effectively assessing the response of LA-NSCLC patients to radiotherapy. Therefore, the objective of this study was to develop a model based on multisequence magnetic resonance imaging (MRI) radiomics features to predict tumor response following radiotherapy in patients with LA-NSCLC and to evaluate its clinical utility. Data was retrospectively collected from stage III non-small cell lung cancer (NSCLC) who underwent radiotherapy and had MRI scans performed prior to treatment from November 2018 to April 2024. The patients were randomly divided into a training set and a testing set in a ratio of 7:3. Tumor response, assessed using Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, classified complete or partial responses as regression sensitive (RS) and stable or progressive disease as regression resistant (RR). A total of 3,045 radiomic features were extracted and integrated from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Feature selection was conducted using the maximum relevance minimum redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO). Four machine learning algorithms, including logistic regression (LR), support vector machine (SVM), k-nearest neighbor (KNN), and random forest, were utilized to construct radiomic models for individual and combined sequences, with the optimal model selected. The models were evaluated with receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). A total of 86 patients were included in this study, with 60 patients (RS: n=32, RR: n=28) in the training set and 26 patients (RS: n=14, RR: n=12) in the testing set. Among them, there were 45 males in the training set and 16 males in the testing set. Four, eight, six, and nine features were selected from the T1, T2, DWI sequences, and combined sequences, respectively. Among the four machine learning algorithms, the LR model demonstrated high accuracy and stability. The combined sequence model exhibited the highest predictive performance. The area under the curve (AUC) of the training set was 0.888 [95% confidence interval (CI): 0.803-0.974], and the accuracy, sensitivity, and specificity were 83.3%, 92.9% and 75%. The AUC of the testing set was 0.815 (95% CI: 0.648-0.983), and the accuracy, sensitivity, and specificity were 73.1%, 91.7% and 57.1%. Calibration curve and DCA demonstrated that the combined sequence model possessed good predictive performance and clinical utility. The radiomics model developed using multisequence MRI demonstrates strong potential in predicting the radiotherapy response in patients with LA-NSCLC. Notably, the combined sequence model outperforming individual sequence models in both predictive accuracy and clinical applicability.

Defect Detection and Classification on Wind Turbine Blades Using Deep Learning with Fuzzy Voting

Wind turbine inspections are traditionally performed by certified rope teams, a manual process that poses safety risks to personnel and leads to operational downtime, resulting in revenue loss. To address some of these challenges, this study explores the use of deep learning and drones for automated inspections. Three Mask R-CNN models, leveraging different convolutional neural network (CNN) backbones—VGG19, Xception, and ResNet-50—were constructed and trained on a novel dataset of 3000 RGB images (size 300 × 300 pixels) annotated with defects, including cracks, holes, and edge erosion. To improve defect detection performance, a multi-variable fuzzy (MVF) voting system is proposed. This method demonstrated superior accuracy compared to the individual models. The best-performing standalone model, Mask R-CNN with Xception, achieved an mAP of 77.48%, while the MVF system achieved an mAP of 80.10%. These findings highlight the effectiveness of combining fuzzy voting systems with Mask R-CNN models for defect detection on wind turbine blades, offering a safer and more efficient alternative to traditional inspection methods.

Perceived Importance of Counseling Among Patients Receiving Methadone Treatment

ABSTRACT We examined the perceived importance of counseling and its correlates among patients receiving methadone treatment (MT). Participants were 345 patients attending MT who completed 7-point Likert-type scales from 1 (“Strongly Disagree”) to 7 (“Strongly Agree”) to rate agreement with perceived importance of counseling, opioid use disorder (OUD) illness models, and OUD treatment beliefs. We examined predictors of perceived importance of counseling using hierarchical linear regression; steps 1, 2, and 3 were demographics, OUD illness models, and OUD treatment beliefs, respectively. Most (76%) agreed counseling was important (Mean = 5.6, SD = 1.7). Demographics did not contribute significantly to the regression model, F(4, 340) = 0.88, p > .05). R2 was significant for Step 2 (F = 2.89, p < .05) but individual OUD illness model variables did not make a significant contribution (F(3, 337) = 1.76, p > .05). The addition of OUD treatment beliefs on Step 3 (positive overall treatment expectation, importance of daily methadone, life-saving benefit of methadone medication, and importance of mutual aid) explained an additional 51% of the variation in perceived importance of counseling and this change in R2 was significant, F(4, 333) = 31.17, p < .001. We conclude that most participants perceived counseling to be important and OUD treatment beliefs independently predicted perceived importance of counseling.

Development of a Predictive Maintenance Algorithm for a Diesel Generator using Machine Learning

This study develops a predictive maintenance framework for a 500kVA diesel generator using advanced machine learning techniques, aiming to enhance reliability and operational efficiency. The research involves the collection of real- world operational data at one-minute intervals over two months, focusing on critical parameters such as bearing temperature, engine vibration, and coolant temperature. Two machine learning models—XGBoost and Multi-Layer Perceptron (MLP)—were trained to classify generator conditions into distinct maintenance categories with high accuracy. A meta-learning ensemble approach was implemented, integrating the predictions from these models to leverage their complementary strengths and enhance robustness. The results demonstrate exceptional performance, with both individual and ensemble models achieving precision, recall, and F1-scores near 1.00 across multiple fault scenarios. The meta-learning framework proved particularly effective, showcasing improved reliability over standalone models. This study’s contributions are twofold: it advances the state of predictive maintenance by employing hybrid modelling techniques and addresses a critical gap in the proactive management of high-capacity diesel generators. The research underscores the practical applicability of machine learning in industrial contexts, offering a scalable and sustainable solution to minimise downtime, reduce maintenance costs, and optimise equipment longevity. By integrating robust data analysis with cutting- edge machine learning, this framework establishes a foundation for proactive, data-driven maintenance strategies in industrial settings, aligning with the broader goals of Industry 4.0 and sustainable industrial practices.

An ensemble approach improves the prediction of the COVID-19 pandemic in South Korea.

Modelling can contribute to disease prevention and control strategies. Accurate predictions of future cases and mortality rates were essential for establishing appropriate policies during the COVID-19 pandemic. However, no single model yielded definite conclusions, with each having specific strengths and weaknesses. Here we propose an ensemble learning approach which can offset the limitations of each model and improve prediction performances. We generated predictions for the transmission and impact of COVID-19 in South Korea using seven individual models, including mathematical, statistical, and machine learning approaches. We integrated these predictions using three ensemble methods: stacking, average, and weighted average ensemble (WAE). We used train and test errors to measure a model's performance and selected the best covariate combinations based on the lowest train error. We then evaluated model performance using five error measures (r2, weighted mean absolute percentage error (WMAPE), autoregressive integrated moving average (ARIMA), mean squared error (MSE), root mean squared error (RMSE), and mean absolute percentage error (MAPE)) and selected the optimal covariate combination accordingly. To validate the generalisability of our approach, we applied the same modelling framework to USA data. Booster shot rate + Omicron variant BA.5 rate was the most commonly selected combination of covariates. For raw data evaluated using the WMAPE, individual models achieved the following: Generalised additive modelling (GAM) reached a value of 0.244 for the daily number of confirmed cases, a value of 0.172 for the time series Poisson for the daily number of confirmed deaths, and a value of 0.022 for both ARIMA and time series Poisson for the daily number of ICU patients. For smoothed data, the Holt-Winters model achieved a value of 0.058 for daily confirmed cases, while ARIMA attained a value of 0.058 for the daily number of confirmed deaths and 0.013 for the daily number of ICU patients. Among ensemble models, the SVM-based stacking ensemble achieved error values of 0.235 for the daily number of confirmed cases, 0.118 for the daily number of deaths, and 0.019 for the daily number of ICU patients on raw data. For smoothed data, the average ensemble and weighted average ensemble achieved 0.060 for the daily number of confirmed cases and 0.013 for daily ICU patients. The ensemble models also generalised well when applied to data from the USA.Booster shot rate + Omicron variant BA.5 rate was the most commonly selected combination of covariates. For raw data, GAM (0.244) predicted daily confirmed cases best, time series Poisson (0.172) predicted daily confirmed deaths, and both ARIMA and time series Poisson (0.022) predicted daily ICU patients, based on WMAPE. For smoothed data, time series Poisson predicted daily confirmed cases (0.065) best, while ARIMA best predicted daily confirmed deaths (0.058) and ICU patients (0.013). For ensemble models, stacking ensemble using SVM was the best model for predicting daily confirmed cases (0.228), deaths (0.11), and ICU patients (0.02). With smoothed data, average ensemble and WAE were the best models for predicting daily confirmed cases (0.058) and ICU patients (0.011). The performance of ensemble models was generalised to other countries using the USA data for predictive performance. No single model performed consistently. While the ensemble models did not always provide the best predictions, a comparison of first-best and second-best models showed that they performed considerably better than the single models. If an ensemble model was not the best performing model, its performance was always not far from the best single model: a look at the mean and variance of the error measures shows that ensemble models provided stable predictions without much variation in their performances compared to single models. These results can be used to inform policymaking during future pandemics.

The association of air pollution with new-onset epilepsy.

Air pollution has been associated with certain neurological disorders, but its association with epilepsy has been insufficiently explored. The study's objective was to estimate the association of long-term exposure to fine particulate matter (PM2.5), nitrogen dioxide (NO2), and ozone (O3) with the risk of new-onset epilepsy among adults in Ontario, Canada. We used a nested case-control study design and linked health and environmental databases, including Ontario residents ages 18 to 80 as of January 1, 2010, without prior diagnoses of seizures or epilepsy. We identified cases as those who developed epilepsy by December 31, 2016, and matched each with up to five controls on age and sex. We used individual- and multi-pollutant conditional logistic regression models to estimate the associations between interquartile range (IQR) increases in each pollutant and new-onset epilepsy. We included 24 761 cases and 118 692 controls. The median (IQR) pollutant concentrations were 7.9 (1.3) μg/m3 for PM2.5, 9.6 (9.2) ppb for NO2, and 42.7 (5.4) ppb for O3. In the individual pollutant models, we observed significant associations with epilepsy for PM2.5 (incident rate ratio [IRR] = 1.055, 95% confidence interval [CI]: 1.034-1.076), NO2 (IRR = 0.938, 95% CI: 0.903-0.974), and O3 (IRR = 1.096, 95% CI: 1.074-1.119). In the multi-pollutant model, we observed significant associations with epilepsy for NO2 (IRR = 0.928, 95% CI: 0.891-0.965) and O3 (IRR = 1.090, 95% CI: 1.060-1.121). Although the association for NO2 was negative overall, the association was positive among individuals 65 and older. PM2.5 and O3 may be associated with an increased risk of new-onset epilepsy. We also observed a negative association for NO2. However, residual confounding may have occurred. Future research should continue exploring the associations between specific air pollutants and new-onset epilepsy.

Exploration of geo-spatial data and machine learning algorithms for robust wildfire occurrence prediction

Wildfires play a pivotal role in environmental processes and the sustainable development of ecosystems. Timely responses can significantly reduce the damages and consequences caused by their spread. Several critical issues in wildfire behavior analysis include fire occurrence forecasting, early detection, and spread prediction. In this study, we focus on wildfire occurrence forecasting, which is a valuable tool for facilitating earlier intervention. Conventional approaches primarily rely on the computation of fire indices based on weather conditions. However, solutions that utilize more comprehensive environmental data, remote sensing information, and artificial intelligence (AI) algorithms may offer substantial advantages for rapid decision-making and extensive territory monitoring. The wide variety of spatial environmental parameters and the great diversity of geographical regions that influence wildfire occurrence complicate this task. Consequently, there is no unified approach for predicting wildfire occurrences using remote sensing data and AI techniques. The goal of this study is to explore the potential of predicting wildfire occurrences using various available environmental parameters - meteorological, geo-spatial, and anthropogenic - and machine learning (ML) algorithms. We developed a unified pipeline for data acquisition and subsequent ML-based algorithm development. The comprehensive analysis includes the following algorithms: Random Forest, XGBoost, Autoencoder, ConvLSTM, Attention Multilayer Perceptron, and RegNetX. In addition, we explore several metrics to assess the quality of developed models in case of highly imbalanced spatio-temporal data. To conduct the study, we collected a unique dataset covering several large regions in central Russia, incorporating more than 17,000 verified wildfire events over a period of 10 years. The findings underscore the necessity of developing individual ML models tailored to each region, taking into account the specific environmental features correlated with the probability of fire occurrence. The quality of the achieved models, as measured by F1-score, varies from 0.7 to 0.87 depending on the region, demonstrating the potential of integrating such algorithms into emergency response systems.

Harnessing Ensemble Techniques for Sentiment Analysis and Toxic Comment Classification

The rapid growth of user-generated content on digital platforms has raised concerns over toxic comments, which can disrupt online interactions. Sentiment analysis and toxic comment classification play a crucial role in moderating such content; however, traditional models often struggle with class imbalance, contextual ambiguity, and linguistic complexity, leading to inaccurate predictions. While machine learning and deep learning models have been widely applied, individual models frequently lack generalizability across diverse comment structures and sentiments. This research introduces FusionBoost, an ensemble learning approach that integrates Logistic Regression (LR) and XGBoost, leveraging their complementary strengths for improved predictive performance. The dataset undergoes rigorous preprocessing, including tokenization, stopword removal, and FastText embeddings, ensuring effective feature representation. Experimental results indicate that FusionBoost outperforms individual classifiers, significantly reducing false negatives in toxicity detection and improving sentiment classification accuracy. The study underscores the effectiveness of ensemble learning in addressing contextual challenges and enhancing model interpretability. Future research may explore transformer-based architectures like BERT to further refine classification performance. This work contributes to the development of more robust and interpretable natural language processing (NLP) models, facilitating safer and more meaningful digital interactions.

Wind farm sites selection using a machine learning approach and geographical information systems in Türkiye

This research highlights the importance of integrating machine learning algorithms with Geographical Information Systems (GIS) applications in the field of renewable energy by finding a suitable site for wind farms due to their importance in preserving the environment to achieve efficiency and cost-effectiveness and reduce the environmental impact of fossil fuel energy sources. Using GIS various factors affecting wind energy localization were processed and analyzed including natural, socio-economic and environmental criteria. Ensemble learning of four supervised machine learning algorithms (Random Forest, K-Nearest Neighbor, Support Vector Machines, Naive Bayes) was used to classify suitable and unsuitable data representing geo-referenced points on the ground with three criteria for each site (wind speed, elevation and slope). The results of the algorithms varied in terms of accuracy and variance, then the results were collected, and the intersection between them was found so that the location classification would be agreed upon in the results of the algorithms used. The aim of using this technique is to reduce the error, increase the accuracy and avoid the bias or variance present in individual models. Accuracy of the algorithms result was respectively (K-Nearest Neighbor, Random Forest, Support Vector Machines, Naive Bayes) (93.022%, 93.018%, 95.095%, 89.553%). The final result is a map using GIS showing the suitable and unsuitable sites of wind farms in the study area (Türkiye) has been chosen as a study area in the research due to several factors that make it suitable for wind energy projects, including its geographical location, which gives it great climatic and terrain diversity, as it is surrounded by seas (Black Sea, Aegean Sea, and Mediterranean Sea), which leads to the activity of seasonal and continuous winds, which contributes to the activity of seasonal and permanent winds. Its drive to develop investment in renewable energy due to economic and population growth has increased the demand for energy and consequently the development of renewable and sustainable energy sources. This research contributes to supporting the global transition to sustainable energy by providing a new methodology for integrating multiple technologies to support a sustainable energy future.

Assessing the Impact of Climate Change on Hippophae neurocarpa in China Using Biomod2 Modeling

Hippophae neurocarpa is a relatively new member of the Rhamnus genus that has various potential edible and medicinal values, but still needs to be further developed. To better develop H. neurocarpa, it is crucial to determine its current and future population distribution. This study utilized the “Biomod2” package in R to integrate five individual models and investigate the effects of climate change on the potential distribution of H. neurocarpa, as well as the key climatic factors influencing its distribution. The results indicated that, under the current scenario, the potential distribution of H. neurocarpa is mainly concentrated in the eastern parts of the Loess Plateau and the Qinghai–Tibet Plateau. In the future, its potential suitable habitats will undergo varying degrees of change: the area of medium/low suitability will decrease, while the area of high suitability will shift westward and increase. In the analysis of area changes, it was found that some potential suitable habitats in Sichuan and Shaanxi will directly transition from highly suitable to unsuitable areas. Key environmental variable analysis showed that temperature, particularly low temperature, is a crucial factor affecting the distribution of H. neurocarpa. Additionally, altitude also has a significant impact on its distribution. This study predicted the potential suitable habitats of H. neurocarpa, which will aid in its future development and provide reference for selecting regions suitable for its cultivation.

AI exposure predicts unemployment risk: A new approach to technology-driven job loss.

Is AI disrupting jobs and creating unemployment? This question has stirred public concern for job stability and motivated studies assessing occupations' automation risk. These studies used readily available employment and wage statistics to quantify occupational changes for employed workers. However, they did not directly examine unemployment dynamics primarily due to the lack of data across occupations, geography, and time. Here, we overcome this barrier using monthly occupation-level unemployment data from each US state's unemployment insurance office from 2010 to 2020 to assess AI exposure models, job separations, and unemployment through a new measure called unemployment risk. We demonstrate that standard employment statistics are inadequate proxies for occupations' unemployment risk and find that individual AI exposure models are poor predictors of occupations' unemployment risk states' total unemployment rates, and states' total job separation rates. However, an ensemble approach exhibits substantial predictive power, accounting for an additional 18% of variation in unemployment risk across occupations, states, and time compared to a baseline model that controls for education, occupations' skills, seasonality, and regional effects. These results suggest that competing models may capture different aspects of AI exposure and that automation shapes US unemployment. Our results demonstrate the power of occupation-specific job disruption data and that efforts using only one AI exposure score will misrepresent AI's impact on the future of work.