Classification And Regression Tree Research Articles

Evaluating missing data handling methods for developing building energy benchmarking models

This study explored methods for handling missing data in the development of machine learning-based energy benchmarking models, assessing their training time, performance, and variance. Unlike the common assumption of missing completely at random, this study adopted a missing at random (MAR) perspective, which is more appropriate for building data. We compared the inherent missing data handling method of extreme gradient boosting (XGBoost) with the Median, k-nearest neighbors (KNN), and classification and regression trees (CART) methods, alongside Shapley additive explanation (SHAP) method for model interpretability. The findings indicate that, despite its computational demands, the CART method most accurately mirrors the original data distribution, thereby enhancing model performance and stability. The KNN method is effective, while the XGBoost method is viable under computational time constraints. This work highlights the importance of reliable test data for performing accurate evaluations of imputation methods. These results offer guidelines for the selection of imputation methods in model development, contributing to the improved accuracy of energy benchmarking models. The MAR-based approach for missing data analysis holds promise for future research on building energy data, providing crucial insights for accurate energy benchmark model performance assessments.

Decision tree learning with random forest models using agricultural and ecological field data incorporating multi-factor studies and covariate structure

Decision tree learning with random forest models using agricultural and ecological field data incorporating multi-factor studies and covariate structure

Identifying suitable boreholes for irrigation in the bedrock regions of the Sahel

AbstractThis study addresses the critical challenge of optimizing borehole drilling techniques and predictive models to improve groundwater utilization for irrigation in Burkina Faso. Initially, the analysis involved drilling 22 boreholes as part of a photovoltaic micro‐sprinkler irrigation project (PRECIS), with only 11 deemed suitable for irrigation, highlighting the difficulty in achieving the required flow rate of 5 m3/h. To enhance the robustness of the study, additional data from 205 high‐yield boreholes provided by the Office National de l'Eau et de l'Assainissement (ONEA) were incorporated. These boreholes, primarily intended for potable water supply, had flow rates often exceeding 5 m3/h. This extensive dataset was crucial in identifying significant predictors of the project flow rate (Qproj), including the flow rate at the end of drilling (QEndBorh) and lithological factors. The predictive model combining QEndBorh and lithological data explained 73.7% of the variance in Qproj, with an adjusted coefficient of determination (R2adj) of 72.4%. The CART (classification and regression tree) regression model effectively identified branches with flow rates suitable for irrigation, such as Terminal Node 3 with a predicted Qproj of 6.67 m3/h and Terminal Node 4 with a predicted Qproj of 10.5 m3/h, demonstrating the model's robustness. These findings underscore the necessity of detailed lithological assessments and advanced predictive modelling to ensure efficient and reliable borehole drilling for irrigation purposes in regions with complex geological conditions.

Decision Tree Regression vs. Gradient Boosting Regressor Models for the Prediction of Hygroscopic Properties of Borassus Fruit Fiber

This research focuses on the environmental-friendly production of Borassus fruit fibers (BNF), its characterization, and hygroscopic properties determination via Dynamic Vapor Sorption (DVS). The experimental results obtained from the hygroscopic behavior analysis were used to create a primary dataset to train and test Decision Tree Regression (DTR) and Gradient Boosting Regressor (GBR) models. The created primary dataset comprised 294 observations, from which 80% were used to train the models, and the remaining 20% were used for the testing of the two models. The models exhibited high accuracy, easy interpretability on the small-size dataset, and flexibility with regards to the nature of the relationship between the input and output variable. Both models successfully predicted the hygroscopic behavior with the Gradient Boosting Regressor outperforming Decision Tree Regression by indicating values of 0.012, 0.109, 0.059, and 0.999 for MSE, RMSE, MAE, and R2, respectively, during the desorption of the BNF, and values of 0.012, 0.109, 0.059, and 0.999 for MSE, RMSE, MAE, and R2, respectively, during the desorption of the BNF. This suggests that the Gradient Boosting Regressor illustrated the maximum accuracy. The outcomes can be utilized to provide an alternative for traditional methods, which can often be costly and time-consuming by improving the engineering properties of BNF. The models can be used in the construction sector to lower costs as they are able to pinpoint elements influencing the characteristics for specific applications to grasp its various properties through the prediction of its hygroscopic properties.

Automatic recognition of active landslides by surface deformation and deep learning

Catastrophic landslides are generally evolved from potential active landslides, and early identification of active landslides over an extensive region is vital to effective prevention and control of disastrous landslides in urban areas. Interferometric Synthetic Aperture Radar (InSAR) has immense potential in mapping active landslides. However, artificial interpretation of InSAR measurements and manual recognition of active landslides are very laborious and time-consuming, with a relatively high missing and false alarms. That hinders the application of InSAR technique and the identification of active landslides in wide areas. Automatic recognition of active landslides has always been a great challenge and has been relatively rarely investigated by previous studies. This work establishes comprehensive identification indices of geoenvironmental, disaster-triggering, and surface deformation features. Moreover, it suggests a novel deep learning algorithm of SDeepFM to conduct automatic identification of active landslides across a vast and landslide-serious area of Hualong County. Some new viewpoints are suggested as follows. (1) The identification indices consist of disaster-controlling, disaster-inducing, and active deformation characteristics and are constructed in terms of the cause characteristics of active landslides. Thus, it can effectively decrease the false alarms of active landslide identification. (2) The proposed SDeepFM algorithm features a spatial-perception ability and can adequately extract and fuse the low-level and high-level semantic features. It outperforms the classification and regression tree (CART), multi-layer perceptron (MLP), convolutional neural network (CNN), and deep neural network (DNN) algorithms. The test accuracy attains 0.91, 99.73%, 90.21%, 0.92, 0.96, and 0.91 in F1-score, Accuracy, Precision, Recall, AUC, and Kappa, respectively. (3) A total of 164 active landslides are exactly recognized, and 39 active landslides are newly identified in this work. (4) In Hualong County, the characteristics of slope deformation, spatial context, lithology, tectonic movement, human activity, and topography play important roles in active landslide identification. River distribution and rainfall also contribute to active landslide recognition.

The cold temperature associated with new-onset heart failure after incorporating dynamic status of multimorbidity: nationwide cohort, Taiwan 2012-2019.

Cold temperatures are known to affect heart failure (HF) hospitalizations, but the dynamic status of multi-morbidity of HF was rarely incorporated. We investigated the relationship between temperature and new-onset HF by risk strata. This nationwide cohort study analysed daily data on ambient temperature, the dynamic status of risk factors (age, diabetes, chronic obstructive pulmonary disease, coronary artery disease, chronic kidney disease, hypertension, myocardial infarction, and atrial fibrillation), and new-onset HF among the Taiwan population from 2012 to 2019. Poisson regression, Austin's algorithm, and classification and regression tree (CART) were used to determine risk strata and obtain the predicted HF rate. 148 708 patients developed new-onset HF over 152.52 million person-years. Three risk strata for HF were identified: Stratum 1 was predominantly those without any comorbidity (89.9%); Stratum 2 was those aged 60-69 with 2-3 comorbidities or aged 70+ with 1-2 comorbidities (9.0%), and Stratum 3 was those aged 70+ and had four or more comorbidity (1.1%). The HF incidence rates for these three strata were 25.54, 555.27, and 2315.52 per 100 000 person-years, respectively. The R2 of the Poisson regression with the three risk strata and the daily minimum temperature on the ln HF incidence rates was 77.99%. The risk of HF increased as temperatures decreased, and the slopes were 1.032, 1.040, and 1.034 for Strata 1-3, respectively. The rate ratios of HF at the winter median temperature of 17°C vs. the summer median temperature of 29°C were 1.45, 1.58, and 1.49 for Strata 1-3, respectively. Cross-validation reveals a good fit and predicted HF rates by ambient temperature for the three strata were provided. Cold temperatures are associated with an increased risk of new-onset HF. Stratum 2 (aged 60-69 with 2-3 comorbidities or aged 70+ with 1-2 comorbidities) are particularly susceptible to cold-related new-onset HF.

Integrating Proteomic Analysis and Machine Learning to Predict Prostate Cancer Aggressiveness

Prostate cancer (PCa) poses a significant challenge because of the difficulty in identifying aggressive tumors, leading to overtreatment and missed personalized therapies. Although only 8% of cases progress beyond the prostate, the accurate prediction of aggressiveness remains crucial. Thus, this study focused on studying retinoblastoma phosphorylated at Serine 249 (Phospho-Rb S249), N-cadherin, β-catenin, and E-cadherin as biomarkers for identifying aggressive PCa using a logistic regression model and a classification and regression tree (CART). Using immunohistochemistry (IHC), we targeted the expression of these biomarkers in PCa tissues and correlated their expression with clinicopathological data of the tumor. The results showed a negative correlation between E-cadherin and β-catenin with aggressive tumor behavior, whereas Phospho-Rb S249 and N-cadherin positively correlated with increased tumor aggressiveness. Furthermore, patients were stratified based on Gleason scores and E-cadherin staining patterns to evaluate their capability for early identification of aggressive PCa. Our findings suggest that the classification tree is the most effective method for measuring the utility of these biomarkers in clinical practice, incorporating β-catenin, tumor grade, and Gleason grade as relevant determinants for identifying patients with Gleason scores ≥ 4 + 3. This study could potentially benefit patients with aggressive PCa by enabling early disease detection and closer monitoring.

Ground motion parameters and damage correlation in plan irregular L-shape steel structure with BRB

Irregularly designed structures frequently experience greater damage compared to regular buildings as a result of elevated torsional reactions and stress concentration, as indicated by evaluations of damage carried out subsequent to past seismic events. The irregularities in the plan configuration provide significant issues for building seismic design. One example of an irregularity is the re-entrant corners found in L-shaped structures, which can lead to early collapse by causing stress concentration from abrupt changes in stiffness and torsional response amplification. More than ever, a thorough investigation into the relationship between the issue of ground motion parameters (GMPs) and Damage is required because of the complex way that L-shaped buildings respond to earthquakes. The current study examines the relationship between a large number of commonly used GMPs and the associated damage for three-, six-, nine-, and twelve-story 3D buildings—that is, low-, mid, and high-rise structures—with asymmetric L-shaped plan layouts. The system of lateral load resistance that was used was Buckling Restrained Brace Frames (BRBFs). To assess a building's seismic performance, 15 bidirectional earthquake ground motions were applied using Nonlinear Time History Analysis (NTHA) for incident angles of 0°, 45°, 135°, 225°, and 315°. The structural response is reported in terms of the average and maximum inter-story drift as well as the total Park-Ang damage index. The relationship between GMPs and structural damage was then investigated using Pearson's correlation coefficient. The results indicate that the highest link with damage measurements is found for 3- and 6-story structures when looking at the spectral acceleration at the fundamental period, Sa(T1). However, PGD and SMV exhibit a stronger correlation than other GMPs for structures with nine and twelve stories. Additionally, Classification and Regression Trees (CART) is a decision tree algorithm used for predictive modeling. In this study suggested using CART (Classification and Regression Trees) algorithms to estimate the link between GMPs and Damage Indices. The findings demonstrate the ability of CART algorithms to extract the rules and correlations governing earthquake damage.

Gender inequalities in oral medicine and pathology research: Temporal trends of two decades.

To analyze gender inequities and trends in the authorship of articles published in high-impact factor journals of the field of Oral Medicine and Pathology. The gender and country of first and last authors were retrieved from original articles published between 2000 and 2022. Poisson regression models and classification and regression tree (CART) analysis were performed. A total of 6595 studies were analyzed for first authorship, and 6627 for last authorship. Only 39.2% (CI 95% 38.0-40.3) of the first authors and 24.1% (CI 95% 23.1-25.1) of the last authors were females. Females consistently faced underrepresentation throughout the 23-year evaluation. The only region where female first authors are not a minority is Latin America. Having a female as the last author increased the prevalence of females in the first author position by 42% (PR = 1.42, CI 95% [1.30-1.54]). The most important discriminant variable by CART was the first author region. Although a slight decrease in underrepresentation was noted over the period, after 2020, the gender gap tended to widen for both first and last authors. It is crucial to implement measures aimed at attracting, retaining, and advancing women in the field of science, while also actively monitoring advancements toward achieving gender equity.

A user guide of CART and random forests with applications in FinTech and InsurTech

In the realm of financial data analytics, machine learning techniques, particularly classification and regression trees (CARTs) and random forests, have shown remarkable efficiency. This article serves as a user guide for these methods, with an emphasis on their applicability and effectiveness in analyzing datasets in FinTech and InsurTech. In particular, we present several numerical examples and empirical studies, and demonstrate their superiority in handling data with a variety of input features, offering insights into their potential applications in the industries.

Modeling of land use and land cover changes using google earth engine and machine learning approach: implications for landscape management

A precise and up-to-date Land Use and Land Cover (LULC) valuation serves as the fundamental basis for efficient land management. Google Earth Engine (GEE), with its numerous machine learning algorithms, is now the most advanced open-source global platform for rapid and accurate LULC classification. Thus, this study explores the dynamics of the LULC changes between 1993 and 2023 using Landsat imagery and the machine learning algorithms in the Google Earth Engine (GEE) platform. Focus group discussion and key informant interviews were also used to get further data regarding LULC dynamics. Support Vector Machine (SVM), Random Forest (RF), and Classification and Regression Trees (CART) were demonstrated for LULC classification. Six LULC types (agricultural land, grazingland, shrubland, built-up area, forest and bareland) were identified and mapped for 1993, 2003, 2013, and 2023. The overall accuracy and kappa coefficient demonstrated that the RF using images comprising auxiliary variables (spectral indices and topographic data) performed better than SVM and CART. Despite being the most common type of LULC, agricultural land shows a trend of shrinking during the study period. The built-up area and bareland exhibits a trend of progressive expansion. The amount of forest and shrubland has decreased over the last 20 years, whereas grazinglands have exhibited expanding trends. Population growth, agricultural land expansion, fuelwood collection, charcoal production, built-up areas expansion, illegal settlement and intervention are among causes of LULC shifts. This study provides reliable information about the patterns of LULC in the Robit watershed, which can be used to develop frameworks for watershed management and sustainability.

A Machine Learning Prediction Model for Myelitis and Multiple Sclerosis Based on Fourier Transform Features from MRI Images

Myelitis is a neurodegenerative disease positioned in the spinal cord, with multiple sclerosis (MS) being a common subtype. Radiological indicators enable the diagnosis of these diseases. This study proposes a classification framework to detect myelitis, MS, and healthy control (HC) groups using magnetic resonance imaging (MRI) images. The feature extraction step involves applying the fast Fourier transform (FFT) to MRI images. FFT is important because it converts spatial data into the frequency domain, making it easier to identify patterns and abnormalities that indicate these diseases. Then, statistical features (mean, minimum, maximum, standard deviation, skewness, kurtosis, and total energy) are extracted from this frequency information. These features are then used to train support vector machine (SVM), k-nearest neighbor (KNN), and decision tree algorithms. In multi-class classification (myelitis vs. MS vs. HC), the proposed method achieves a classification accuracy of 99.31% with SVM, with average precision, recall, and F1-score values of 99.27%, 99.21%, and 99.24%, respectively, indicating effective classification across all classes. In the binary class classification (HC vs. MS, MS vs. myelitis, HC vs. myelitis), the SVM achieves an outstanding classification accuracy of 99.36%, 99.71%, and 100% respectively. This study highlights the efficiency of FFT-based feature extraction in forming detection patterns for classifying HC, MS, and myelitis classes.

Numerical and machine learning modeling of GFRP confined concrete-steel hollow elliptical columns

This article investigates the behavior of hybrid FRP Concrete-Steel columns with an elliptical cross section. The investigation was carried out by gathering information through literature and conducting a parametric study, which resulted in 116 data points. Moreover, multiple machine learning predictive models were developed to accurately estimate the confined ultimate strain and the ultimate load of confined concrete at the rupture of FRP tube. Decision Tree (DT), Random Forest (RF), Adaptive Boosting (ADAB), Categorical Boosting (CATB), and eXtreme Gradient Boosting (XGB) machine learning techniques were utilized for the proposed models. Finally, these models were visually and quantitatively verified and evaluated. It was concluded that the CATB and XGB are standout models, offering high accuracy and strong generalization capabilities. The CATB model is slightly superior due to its consistently lower error rates during testing, indicating it is the best model for this dataset when considering both accuracy and robustness against overfitting.

Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study.

The number of elderly patients with trauma is increasing; therefore, precise models are necessary to estimate the mortality risk of elderly patients with trauma for informed clinical decision-making. This study aimed to develop machine learning based predictive models that predict 30-day mortality in severely injured elderly patients with trauma and to compare the predictive performance of various machine learning models. This study targeted patients aged ≥65 years with an Injury Severity Score of ≥15 who visited the regional trauma center at Chungbuk National University Hospital between 2016 and 2022. Four machine learning models-logistic regression, decision tree, random forest, and eXtreme Gradient Boosting (XGBoost)-were developed to predict 30-day mortality. The models' performance was compared using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, specificity, F1 score, as well as Shapley Additive Explanations (SHAP) values and learning curves. The performance evaluation of the machine learning models for predicting mortality in severely injured elderly patients with trauma showed AUC values for logistic regression, decision tree, random forest, and XGBoost of 0.938, 0.863, 0.919, and 0.934, respectively. Among the four models, XGBoost demonstrated superior accuracy, precision, recall, specificity, and F1 score of 0.91, 0.72, 0.86, 0.92, and 0.78, respectively. Analysis of important features of XGBoost using SHAP revealed associations such as a high Glasgow Coma Scale negatively impacting mortality probability, while higher counts of transfused red blood cells were positively correlated with mortality probability. The learning curves indicated increased generalization and robustness as training examples increased. We showed that machine learning models, especially XGBoost, can be used to predict 30-day mortality in severely injured elderly patients with trauma. Prognostic tools utilizing these models are helpful for physicians to evaluate the risk of mortality in elderly patients with severe trauma.

Temporal-Spatial Fluctuations of a Phytoplankton Community and Their Association with Environmental Variables Based on Classification and Regression Tree in a Shallow Temperate Mountain River.

The effects of environmental factors on phytoplankton are not simply positive or negative but complex and dependent on the combination of their concentrations in a fluctuating environment. Traditional statistical methods may miss some of the complex interactions between the environment and phytoplankton. In this study, the temporal-spatial fluctuations of phytoplankton diversity and abundance were investigated in a shallow temperate mountain river. The machine learning method classification and regression tree (CART) was used to explore the effects of environmental variables on the phytoplankton community. The results showed that both phytoplankton species diversity and abundance varied fiercely due to environmental fluctuation. Microcystis aeruginosa, Amphiprora sp., Anabaena oscillarioides, and Gymnodinium sp. were the dominant species. The CART analysis indicated that dissolved oxygen, oxidation-reduction potential, total nitrogen (TN), total phosphorus (TP), and water temperature (WT) explained 36.00%, 13.81%, 11.35%, 9.96%, and 8.80%, respectively, of phytoplankton diversity variance. Phytoplankton abundance was mainly affected by TN, WT, and TP, with variance explanations of 39.40%, 15.70%, and 14.09%, respectively. Most environmental factors had a complex influence on phytoplankton diversity and abundance: their effects were positive under some conditions but negative under other combinations. The results and methodology in this study are important in quantitatively understanding and exploring aquatic ecosystems.

Lung ultrasound to predict the duration of respiratory support in newborn infants with respiratory distress.

Lung ultrasound (LU) and clinical parameters evaluated during the first postnatal hour potentially predict the length of CPAP therapy in newborns with respiratory distress. In a single-centre, prospective observational pilot study, 130 newborns ≥36 weeks gestational age were assessed using standardised LU at 30 and 60 min postnatally. Various clinical parameters were evaluated influencing CPAP duration (<1 vs. ≥1 h) using univariate and multivariate analyses. Lung ultrasound score >5, FiO2 > 0.21 and respiratory acidosis 30 min postnatally were associated with CPAP ≥1 h. Our model showed good diagnostic quality (ROC AUC = 0.87) and was confirmed by classification and regression tree (CART) analysis. Additional LU findings like double lung point and pleural line abnormalities were frequently observed, with good interrater reliability for LU interpretation (ICC = 0.76-0.77). Newborns with postnatal respiratory distress at risk for prolonged CPAP therapy can be identified based on specific LU and clinical parameters assessed 30 min postnatally. Despite the need for validation in an independent sample, these findings may lay the groundwork for a prediction tool. LU proved feasible and reliable for assessing respiratory status in this population, highlighting potential utility in clinical practice.

Organizational and patient factors associated with positive primary care experiences for veterans with current or recent homelessness.

To identify organizational service features associated with positive patient ratings of primary care within primary care clinics tailored to accommodate persons with ongoing and recent experiences of homelessness (PEH). PEH receiving primary care in 29 United States Veterans Health Administration homeless-tailored clinics were surveyed about their primary care experience using the validated Primary Care Quality-Homeless (PCQ-H) survey. Characteristics of the clinics were assessed through surveys of clinic staff using a new organizational survey developed through literature review, site visits, statistical analysis, and consensus deliberation. Cross-sectional examination of patients' ratings of care based on surveys of patients, and of clinic characteristics, analyzed with Classification and Regression Tree (CART) analysis, a form of machine learning. Patient surveys (n = 3394) were obtained from a random sample of enrolled patients by both mail and telephone by an external survey contractor. Staff (n = 52 from 29 clinics) were interviewed by telephone. This analysis identified service features that impact patient experience favorably, including aspects of patient-centeredness, team identity, strong external leadership support, and service that reach beyond traditional primary care clinic confines. Results varied according to the patient experience scale analyzed. Individual characteristics of PEH, such as degree of social support, general health, and unsheltered status, were also correlated with how they rate care. Organizational characteristics correlate with ratings of primary care from patients with recent and ongoing homelessness. Primary care programs serving homeless individuals can assure better care based on who they hire, how they foster team identity, what services they provide, and the strength of leadership support to protect a homeless-focused mission.

Object-oriented multi-scale segmentation and multi-feature fusion-based method for identifying typical fruit trees in arid regions using Sentinel-1/2 satellite images

Fruit tree identification that is quick and precise lays the groundwork for scientifically evaluating orchard yields and dynamically monitoring planting areas. This study aims to evaluate the applicability of time series Sentinel-1/2 satellite data for fruit tree classification and to provide a new method for accurately extracting fruit tree species. Therefore, the study area selected is the Tarim Basin, the most important fruit-growing region in northwest China. The main focus is on identifying several major fruit tree species in this region. Time series Sentinel-1/2 satellite images acquired from the Google Earth Engine (GEE) platform are used for the study. A multi-scale segmentation approach is applied, and six categories of features including spectral, phenological, texture, polarization, vegetation index, and red edge index features are constructed. A total of forth-four features are extracted and optimized using the Vi feature importance index to determine the best time phase. Based on this, an object-oriented (OO) segmentation combined with the Random Forest (RF) method is used to identify fruit tree species. To find the best method for fruit tree identification, the results are compared with three other widely used traditional machine learning algorithms: Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), and Classification and Regression Tree (CART). The results show that: (1) the object-oriented segmentation method helps to improve the accuracy of fruit tree identification features, and September satellite images provide the best time window for fruit tree identification, with spectral, phenological, and texture features contributing the most to fruit tree species identification. (2) The RF model has higher accuracy in identifying fruit tree species than other machine learning models, with an overall accuracy (OA) and a kappa coefficient (KC) of 94.60% and 93.74% respectively, indicating that the combination of object-oriented segmentation and RF algorithm has great value and potential for fruit tree identification and classification. This method can be applied to large-scale fruit tree remote sensing classification and provides an effective technical means for monitoring fruit tree planting areas using medium-to-high-resolution remote sensing images.

Analysis of passenger perception heterogeneity and differentiated service strategy for air-rail intermodal travel

Air-rail intermodal services (ARISs) represent a highly promising multimodal solution within the transportation sector. Nonetheless, various uncertainties and challenges persist across multiple dimensions of air-rail interline travel, with discrepancies in passenger perceptions being a notable aspect. In an effort to pinpoint the pivotal factors contributing to these disparities among distinct passenger profiles, this study employs the Structural Equation Modeling-Multiple Indicator Multiple Cause-Artificial Neural Network (SEM-MIMIC-ANN) methodology. This approach explores the impact of numerous attributes on passenger perceptions in the context of air-rail intermodal travel, leveraging questionnaire data gathered from Shijiazhuang multimodal passengers. Furthermore, the study utilizes the Classification and Regression Tree (CART) decision tree algorithm to categorize actual passengers into distinct characteristic groups. Subsequently, the perception levels of these diverse passenger groups are quantified through the calculation of comprehensive evaluation function values. In conclusion, taking into account the real-world conditions of air-rail interline travel, this research formulates a tailored service strategy aimed at enhancing the overall passenger experience.

Characterisation of the ringed seal (Pusa hispida) acoustic repertoire during spring in the Western Canadian Arctic

ABSTRACT Understanding the acoustic repertoire of a species is crucial for comprehending its ecology and can also provide a valuable tool in the analysis of passive acoustic monitoring data. Despite being the most abundant seal species in the Arctic, the call repertoire of ringed seals (Pusa hispida) remains poorly studied. This paper aims to provide a comprehensive and quantitative description of the calls produced by ringed seals. Data collection occurred in May 2022 near Ulukhaktok in the Western Canadian Arctic. Acoustic recorders were deployed in cracks in the sea ice that were regularly used by ringed seals as haul-out areas. All calls were counted and classified into one of three categories: yelps, barks and growls. High-quality calls were further analysed with ten acoustic parameters calculated for each signal. Cluster and classification and regression tree (CART) analyses were used to assess if the visual classification of calls was supported by the acoustic parameters calculated. The cluster and CART analyses affirmed the presence of all three distinct call types in the ringed seal acoustic repertoire. Classification of unseen calls using the CART model demonstrated an accuracy of 98%. The findings presented here serve as foundational information on the acoustic repertoire of ringed seals.