Boosted Regression Trees Research Articles

Space-for-time substitutions exaggerate urban bird-habitat ecological relationships.

North American bird abundance has declined by 29% over the last 50 years. These continental population dynamics interact with local landscape changes to affect local bird diversity. Mitigating local declines in cities is particularly significant because (a) such declines greatly impact human-bird relationships since most people live in cities and (b) cities provide levers to create bird-friendly habitat, such as managing yards and gardens, street trees, and urban parks. Yet, the potential for cities to modify habitats to mitigate broader bird declines remains unclear. Studies have been stymied by the difficulty of assembling mutidecadal habitat-bird population datasets. Instead, studies have substituted space for time (e.g. used habitat associations across space at one time point to project future species abundance due to changing land use), but this method may fail amidst nonstationary environments of the Anthropocene. Here, we test the validity of space-for-time substitutions for explaining changes in bird abundance in a North American city over the past two decades by examining the degree to which these changes are explainable by changes in local landcover at multiple spatial scales. Specifically, we use longitudinal urban bird surveys of Metro Vancouver, BC, Canada from 1997 and 2020; deep learning models of remote sensing data to classify contemporaneous landcover; out-of-sample prediction and boosted regression trees to identify multiple spatial scales of landcover that best explained bird abundance (i.e. optimal scale of effect for each species by each habitat); and Bayesian multispecies abundance models in Stan to determine relationships between changes in landcover and bird abundance. We found that total bird abundance declined by 26% over the last two decades. Landcover measured at both 50 m and optimal scales explained spatial variation in bird abundance, but only landcover at the optimal scale explained temporal changes, and only partially. These results suggest that space-for-time substitutions overemphasize habitat-bird ecological relationships, urban habitats only partially determine bird abundance, and measuring habitat at the appropriate scale is important for capturing the most relevant changes in landscapes.

Functional traits mediate the elevational patterns of functional diversity and community structure of mosses in a tropical mountain area

Functional diversity refers to the value, range, and distribution of functional traits within a community, such as the morphological, physiological and behavioral characteristics of species that determine the role a species plays in an ecosystem. Assessing the drivers of elevational pattern of functional diversity is crucial to predict the effects of global change on functional diversity and community structure. In our research, we collected mosses species data from 65 sampling sites and measured 11 functional traits that are related to their ecological functions. We applied double canonical correspondence analysis (DCCA) to analyze species responses to environmental conditions based on their traits. We applied generalized additive models with a Gaussian function of variance to determine the elevational patterns of functional trait composition, diversity and community structure. We applied and compared boosted regression trees (BRT) without considering functional traits and piecewise structural equation modelling (SEM) mediated with functional traits to relate environmental variables with functional diversity and functional community structure, respectively. We found the first DCCA axis accounted for the largest dissimilarities between the two groups of species and correlated mainly with the water-utilization traits. Although both functional diversity and community structure displayed negatively skewed pattern along the elevational gradient, habitat complexity and climatic variables contributed differently to their respective patterns. The SEM approach consistently outperformed the BRT approach in explaining the variations in both functional diversity and community structure. Our findings highlight the important role of functional traits in mediating the relationship between the environment and functional diversity metrics. Both biotic and abiotic processes play a significant role in shaping the community assemblages, with environmental variables having distinct impacts. Traits related to structure maintenance, water absorption, cell hydration, and nutrient acquisition were found to be key drivers of functional diversity, while water-utilization traits were mainly responsible for regulating functional community structure.

The Environmental Niche of the Light Purse Seine Fleet in the Northwest Pacific Ocean Based on Automatic Identification System Data

Ecosystem-based fisheries management requires high-precision fisheries information to provide relevant data for natural resource management, assessment, and marine spatial planning. This study utilizes Automatic Identification System (AIS) data from light purse seine vessels from the Chinese mainland that were collected from May to November between 2020 and 2022, along with the corresponding environmental data. By applying boosted regression trees (BRTs) and generalized additive models (GAMs), this study establishes nonlinear relationships between fishing intensity and predictor variables and explores the ecological and environmental drivers behind the spatial distribution of light purse seine vessels from the Chinese mainland in the Northwest Pacific. This research identifies the key influencing factors and reveals significant seasonal preferences for different marine environments in various months, with chlorophyll-a being the primary influencing factor. The predicted fishing effort closely resembles observed data, providing valuable information to support fisheries resource management and planning.

Characterizing Chromophoric Dissolved Organic Matter Spatio-Temporal Variability in North Andean Patagonian Lakes Using Remote Sensing Information and Environmental Analysis

Chromophoric dissolved organic matter (CDOM) is crucial in aquatic ecosystems, influencing light penetration and biogeochemical processes. This study investigates the CDOM variability in seven oligotrophic lakes of North Andean Patagonia using Landsat 8 imagery. An empirical band ratio model was calibrated and validated for the estimation of CDOM concentrations in surface lake water as the absorption coefficient at 440 nm (acdom440, m−1). Of the five atmospheric corrections evaluated, the QUAC (Quick Atmospheric Correction) method demonstrated the highest accuracy for the remote estimation of CDOM. The application of separate models for deep and shallow lakes yielded superior results compared to a combined model, with R2 values of 0.76 and 0.82 and mean absolute percentage errors (MAPEs) of 14% and 22% for deep and shallow lakes, respectively. The spatio-temporal variability of CDOM was characterized over a five-year period using satellite-derived acdom440 values. CDOM concentrations varied widely, with very low values in deep lakes and moderate values in shallow lakes. Additionally, significant seasonal fluctuations were evident. Lower CDOM concentrations were observed during the summer to early autumn period, while higher concentrations were observed in the winter to spring period. A gradient boosting regression tree analysis revealed that inter-lake differences were primarily influenced by the lake perimeter to lake area ratio, mean lake depth, and watershed area to lake volume ratio. However, seasonal CDOM variation was largely influenced by Lake Nahuel Huapi water storage (a proxy for water level variability at a regional scale), followed by precipitation, air temperature, and wind. This research presents a robust method for estimating low to moderate CDOM concentrations, improving environmental monitoring of North Andean Patagonian Lake ecosystems. The results deepen the understanding of CDOM dynamics in low-impact lakes and its main environmental drivers, enhance the ability to estimate lacustrine carbon stocks on a regional scale, and help to predict the effects of climate change on this important variable.

Identifying ecological factors mediating the spread of three invasive mosquito species: citizen science informed prediction

AbstractDue to their potential role in pathogen transmission, invasive mosquitoes pose considerable threats to human and animal health. Several studies have identified the most important ecological drivers mediating the establishment and spread of key mosquito species (e.g., Aedes aegypti, and Ae. albopictus), and made predictions for future distribution. We evaluated the effect of an exhaustive list of environmental predictors on the distribution of three invasive species in Hungary (Ae. albopictus, Ae. japonicus, and Ae. koreicus) by using the same standards for data collection based on citizen science observations. Current distribution maps of these species were generated from a 5-year survey, then were compared with various predictor maps reflecting climate, habitat type, food supply, traffic, and interspecific competition by using a boosted regression trees approach that resulted in a subset of variables with the strongest impact. The best predictor sets were used to predict the probability of occurrence of the focal species for the whole country, and these predictions based on citizen science were evaluated against the results of an independent recent field surveillance. We uncovered species-specific patterns and found that different predictor sets were selected for the three different species, and only predictions for Ae. albopictus could be validated with direct trapping data. Therefore, citizen science informed distribution maps can be used to identify ecological predictors that determine the spread of invasive mosquitoes, and to estimate risk based on the predicted distribution in the case of Ae. albopictus.

Constructing a Supplementary Benchmark Suite to Represent Android Applications with User Interactions by using Performance Counters

We find existing benchmark suites for smartphone CPU micro-architecture design such as Geekbench 5.0 fail to authentically represent the micro-architecture level performance behavior of widely used real Android applications with interactive operations such as screen sliding. It is therefore crucial to systematically construct a benchmark suite as a supplementary to Geekbench to represent the user interaction behavior of Android applications for CPU micro-architecture design. The key is to identify a small number of representative programs from a large number of real applications. To this end, a set of features used to represent a program need to be constructed, and these features should be fair for different micro-architectures and can be collected efficiently. However, this is extremely difficult for Android applications. For example, the feature collection tools for Android applications are unavailable for benchmark selection. In this paper, we propose a novel benchmark suite construction approach dubbed BEMAP to efficiently build a supplementary benchmark suite from real-world Android applications to represent their user interaction behavior. 1 BEMAP innovates four techniques. The first technique, called two-stage RFC (representative feature construction), constructs program features from performance counters (events) to represent a program for selecting benchmarks from a large number of real Android applications in two stages. The first stage identifies a set of important performance events in terms of IPC (instructions per cycle) by employing a machine learning algorithm named SGBRT (Stochastic Gradient Boosted Regression Tree). The second stage constructs representative features based on the important performance events by using ICA (independent component analysis). The second technique, named SPC-MMA (source performance counters from multiple micro-architectures), collects the performance events from multiple mobile CPUs with different micro-architectures and mixes them as the source of RFC. The goal of these two innovations is to make the program features fair to different mobile CPU micro-architectures. The third technique, called ES (Elbow-Silhouette) approach, artfully leverages the synergy between the elbow method and the silhouette method to determine an optimal K when we use K-Means to group Android applications. The fourth technique is that we design a new tool named AutoProfiler to automatically profile the micro-architecture events (e.g., IPC, L1 Icache misses) of Android applications with interactive operations. Using the proposed BEMAP methodology 2 , we constructed SPBench, a novel benchmark suite supplementary to traditional mobile benchmark suites like Geekbench, for mobile CPU micro-architecture design. It consists of fifteen benchmarks selected from one hundred real Android applications with three common user interaction operations, which is the fifth innovation of this paper. The experimental results on four significantly different micro-architectures show that SPBench can represent the micro-architecture performance behaviors of the one hundred real-world applications with three common user interactive operations on each micro-architecture with significantly higher accuracy than benchmark suites produced by the state-of-the-art approaches.

A comparative study of the effects of urban morphology on land surface temperature in Chengdu and Chongqing, China

Urbanization combined with global climate change, exacerbates the urban thermal environment and hinders sustainable urban development. However, the complex relationships between land surface temperature (LST) and urban morphology are being further understood, particularly in relation to different urban development patterns, distinct topography, and 3D building morphology. Thus, this study conducted a comparative study in Chengdu and Chongqing, Southwest China. We explored the impact of comprehensive factors (including socio-economic factos, topography, land use composition, and building morphology) on LST by employing the methods of linear regression, geographical detector model, and the boosted regression trees. Our results suggest that (1) high LST was mainly observed in the central part of Chengdu but it presented multicenter aggregation trend in Chongqing; (2) Socio-economic factors were the dominant variables affecting LST in both cities; (3) land use composition and building morphology showed distinct contributions to LST among the two cities; and (4) 3D building management was more effective in Chengdu than in Chongqing. A better understanding of the impact of various influencing factors on LST will enable policy makers and planners to develop appropriate strategies for constructing climate-adaptive cities and mitigating urban heat.

Functional traits of Epifagus virginiana (Orobanchaceae) tubers as adaptations to the Mexican beech microenvironment

Epifagus virginiana (Orobanchaceae), known as beechdrops, is a holoparasitic plant that acquires all its resources from a narrow range of host plants, restricted to North American Fagus species. To do so, beechdrops develop a vascular connection with the host via a terminal haustoria that develops as a tuber attached to the host root. We hypothesized that microenvironmental conditions can influence functional traits of the E. virginiana tuber despite this parasite's complete reliance on the host plant for its nutrition. Therefore, the aims of this study were i) to analyze the structure of the tubers of E. virginiana; ii) to assess the variation in tuber functional traits between two E. virginiana populations; and iii) to analyze how microenvironmental factors influence functional traits in the tuber. We detected that functional trait of beechdrops tuber along Mexican beech microenvironmental covaried with traits important for below-ground processes. Boosted regression trees provided a powerful analysis tool, giving substantially superior predictive performance to generalized additive models, despite the fitting of interaction terms in the latter.

The potential for species distribution models to distinguish source populations from sinks.

While species distribution models (SDM) are frequently used to predict species occurrences to help inform conservation management, there is limited evidence evaluating whether habitat suitability can reliably predict intrinsic growth rates or distinguish source populations from sinks. Filling this knowledge gap is critical for conservation science, as applications of SDMs for management purposes ultimately depend on these typically unobserved population or metapopulation dynamics. Using linear regression, we associated previously published population level estimates of intrinsic growth and abundance derived from a Bayesian analysis of mark-recapture data for 17 bird species found in the contiguous United States with SDM habitat suitability estimates fitted here to opportunistic data for these same species. We then used the area under the ROC curve (AUC) to measure how well SDMs can distinguish populations categorized as sources and sinks. We built SDMs using two different approaches, boosted regression trees (BRT) and generalized linear models (GLM), and compared their source/sink predictive performance. Each SDM was built with presence points obtained from eBird (a web-available database) and 10 environmental variables previously selected to model intrinsic growth rates and abundance for these species. We show that SDMs built with opportunistic data are poor predictors of species demography in general; both BRT and GLM explained very little spatial variation of intrinsic growth rate and population abundance (median R2 across 17 species was close to 0.1 for both SDM methods). SDMs, however, estimated higher suitability for source populations as compared to sinks. Out of 13 species which had both source and sink populations, both BRT and GLM had AUC values greater than 0.7 for 7 species when discriminating between sources and sinks. Habitat suitability have the potential to be a useful measure to indicate a population's ability to sustain itself as a source population; however more research on a diverse set of taxa is essential to fully explore this potential. This interpretation of habitat suitability can be particularly useful for conservation practice, and identification of explicit cases of when and how SDMs fail to match population demography can be informative for advancing ecological theory.

Enhanced stereodivergent evolution of carboxylesterase for efficient kinetic resolution of near-symmetric esters through machine learning

Carboxylesterases serve as potent biocatalysts in the enantioselective synthesis of chiral carboxylic acids and esters. However, naturally occurring carboxylesterases exhibit limited enantioselectivity, particularly toward ethyl 3-cyclohexene-1-carboxylate (CHCE, S1), due to its nearly symmetric structure. While machine learning effectively expedites directed evolution, the lack of models for predicting the enantioselectivity for carboxylesterases has hindered progress, primarily due to challenges in obtaining high-quality training datasets. In this study, we devise a high-throughput method by coupling alcohol dehydrogenase to determine the apparent enantioselectivity of the carboxylesterase AcEst1 from Acinetobacter sp. JNU9335, generating a high-quality dataset. Leveraging seven features derived from biochemical considerations, we quantitively describe the steric, hydrophobic, hydrophilic, electrostatic, hydrogen bonding, and π-π interaction effects of residues within AcEst1. A robust gradient boosting regression tree model is trained to facilitate stereodivergent evolution, resulting in the enhanced enantioselectivity of AcEst1 toward S1. Through this approach, we successfully obtain two stereocomplementary variants, DR3 and DS6, demonstrating significantly increased and reversed enantioselectivity. Notably, DR3 and DS6 exhibit utility in the enantioselective hydrolysis of various symmetric esters. Comprehensive kinetic parameter analysis, molecular dynamics simulations, and QM/MM calculations offer insights into the kinetic and thermodynamic features underlying the manipulated enantioselectivity of DR3 and DS6.

Optimized Machine Learning Model for Predicting Compressive Strength of Alkali-Activated Concrete Through Multi-Faceted Comparative Analysis

Alkali-activated concrete (AAC), produced from industrial by-products like fly ash and slag, offers a promising alternative to traditional Portland cement concrete by significantly reducing carbon emissions. Yet, the inherent variability in AAC formulations presents a challenge for accurately predicting its compressive strength using conventional approaches. To address this, we leverage machine learning (ML) techniques, which enable more precise strength predictions based on a combination of material properties and cement mix design parameters. In this study, we curated an extensive dataset comprising 1756 unique AAC mixtures to support robust ML-based modeling. Four distinct input variable schemes were devised to identify the optimal predictor set, and a comparative analysis was performed to evaluate their effectiveness. After this, we investigated the performance of several popular ML algorithms, including random forest (RF), adaptive boosting (AdaBoost), gradient boosting regression trees (GBRTs), and extreme gradient boosting (XGBoost). Among these, the XGBoost model consistently outperformed its counterparts. To further enhance the predictive accuracy of the XGBoost model, we applied four state-of-the-art optimization techniques: the Gray Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), beetle antennae search (BAS), and Bayesian optimization (BO). The optimized XGBoost model delivered superior performance, achieving a remarkable coefficient of determination (R2) of 0.99 on the training set and 0.94 across the entire dataset. Finally, we employed SHapely Additive exPlanations (SHAP) to imbue the optimized model with interpretability, enabling deeper insights into the complex relationships governing AAC formulations. Through the lens of ML, we highlight the benefits of the multi-faceted synergistic approach for AAC strength prediction, which combines careful input parameter selection, optimal hyperparameter tuning, and enhanced model interpretability. This integrated strategy improves both the robustness and scalability of the model, offering a clear and reliable prediction of AAC performance.

Examining the relationship between the built environment and carbon emissions from operating vehicles: enlightenment from nonlinear models.

Carbon emissions from urban transportation significantly contribute to overall transportation emissions and are a major cause of the continuous rise in global temperatures. Understanding the spatial distribution and influencing factors of carbon emissions from operating vehicles can aid in formulating targeted policies and promoting emission reduction. To analyze the factors influencing urban traffic carbon emissions, we calculated emissions using trajectory data from operating vehicles in Shenzhen. We then used gradient boosting regression tree methods, specifically RF, XGBoost, and LightGBM models, to analyze the impact of the built environment on vehicle emissions. We used the XGBoost model for detailed factor analysis by comparing the models. The results indicate that bus stops, intersections, housing density, metro stops, and land use mix are the top five factors influencing emissions. When road density is 0-15 km/km2, the distance from the city center is 0-6 km, and the population exceeds 2000/km2, the built environment significantly reduces vehicle emissions.

How did COVID-19 case distribution associate with the urban built environment? A community-level exploration in Shanghai focusing on non-linear relationship.

Several associations between the built environment and COVID-19 case distribution have been identified in previous studies. However, few studies have explored the non-linear associations between the built environment and COVID-19 at the community level. This study employed the March 2022 Shanghai COVID-19 pandemic as a case study to examine the association between built-environment characteristics and the incidence of COVID-19. A non-linear modeling approach, namely the boosted regression tree model, was used to investigate this relationship. A multi-scale study was conducted at the community level based on buffers of 5-minute, 10-minute, and 15-minute walking distances. The main findings are as follows: (1) Relationships between built environment variables and COVID-19 case distribution vary across scales of analysis at the neighborhood level. (2) Significant non-linear associations exist between built-environment characteristics and COVID-19 case distribution at different scales. Population, housing price, normalized difference vegetation index, Shannon's diversity index, number of bus stops, floor-area ratio, and distance from the city center played important roles at different scales. These non-linear results provide a more refined reference for pandemic responses at different scales from an urban planning perspective and offer useful recommendations for a sustainable COVID-19 post-pandemic response.

Machine Learning-Based Prediction of Aircraft Taxi-In Time: A Case Study at Beijing Capital International Airport

Accurate prediction of flight taxi-in time has a significant meaning in allocating aircraft support resources reasonably and improving airport surface movement efficiency. It can effectively overcome the deficiency of extensive aircraft arrival time prediction in major airports currently. Taking Beijing Capital International Airport as the research object, we analyzed the influence factors of taxi-in time and constructed the feature set; Then we applied linear regression, K-nearest neighbor, support vector regression, decision tree, random forest and gradient boosting regression tree, which were widely used in the prediction of taxi-out time, to predict the taxi-in time. The results show that the prediction accuracy of the six machine learning models is over 90%within \pm3minutes, it means that the construction of feature set and the selection of models are effective; The gradient boosting regression tree model has the best performance based on the prediction results and model fitting evaluation results; The surface traffic flow features have the largest contribution to the prediction model, and the newly introduced cross-regional feature has more contribution to the prediction model than most traditional features, according to the prediction results of gradient boosting regression tree.

New evidence of alternative migration patterns for two Mediterranean potamodromous species

Iberian barbel (Luciobarbus bocagei Steindachner, 1864) and Iberian nase (Pseudochondrostoma polylepis Steindachner, 1864) are two Mediterranean potamodromous fish species known to perform annual upstream migrations to reach spring spawning grounds. In the Mondego River basin, at the Coimbra dam, migratory movement patterns and individual size structure were assessed through a video recording monitoring system installed on an upstream section of a vertical-slot fish pass. Visual census for these target species during two consecutive annual cycles (2013–2014) revealed alternative migratory patterns, with the first peak of upstream movements in autumn, for both barbel (October–November) and nase (November–December). Circadian movements of both species showed a diurnal preference, contrary to what is usually described for these species. Size structure analysis for individuals of both species showed significant intra-annual differences in the size of migrating fish. Boosted regression trees models applied to the 2013–2014 visual count data identified flow and temperature as the most influential environmental predictors, triggering both species’ movements in each direction in the study years. These results provide novel information on the timing of the migratory movements of these potamodromous fish, which can be used to adapt current management and conservation measures to the specificities of their migratory behaviour.

Epidemiology and Ecology of Usutu Virus Infection and Its Global Risk Distribution.

Usutu virus (USUV) is an emerging mosquito-transmitted flavivirus with increasing incidence of human infection and geographic expansion, thus posing a potential threat to public health. In this study, we established a comprehensive spatiotemporal database encompassing USUV infections in vectors, animals, and humans worldwide by an extensive literature search. Based on this database, we characterized the geographic distribution and epidemiological features of USUV infections. By employing boosted regression tree (BRT) models, we projected the distributions of three main vectors (Culex pipiens, Aedes albopictus, and Culiseta longiareolata) and three main hosts (Turdus merula, Passer domesticus, and Ardea cinerea) to obtain the mosquito index and bird index. These indices were further incorporated as predictors into the USUV infection models. Through an ensemble learning model, we achieved a decent model performance, with an area under the curve (AUC) of 0.992. The mosquito index contributed significantly, with relative contributions estimated at 25.51%. Our estimations revealed a potential exposure area for USUV spanning 1.80 million km2 globally with approximately 1.04 billion people at risk. This can guide future surveillance efforts for USUV infections, especially for countries located within high-risk areas and those that have not yet conducted surveillance activities.

Climate change drives fish communities: Changing multiple facets of fish biodiversity in the Northwest Pacific Ocean

Global marine biodiversity is experiencing significant alterations due to climate change. Incorporating phylogenetic and functional diversity may provide novel insights into these impacts. This study used an ensemble model approach (random forest and boosted regression tree), to predict the habitat distribution of 47 fish species in the Northwestern Pacific under contemporary (2000–2014) and future scenarios (2040–2050, 2090–2100). We first examined the relationship between eleven functional traits and habitat changes, predicting the spatial distribution of functional traits within fish communities. A significant correlation was observed between temperature preference and habitat changes, highlighting the vulnerability of cold-water species and potential advantages for warm-water species in the future. Moreover, fish communities exhibited a spatial gradient distribution with southern regions characterized by shorter-lived and earlier maturity, contrasting with longer-lived and later maturity species in the north. Secondly, to assess the impact of climate change on marine biodiversity, we explored the taxonomic, phylogenetic, and functional diversity under contemporary and future scenarios, revealing higher indices in the East China Sea (ECS) and the coastal sea of Japan, with the Taiwan Strait emerging as a contemporary biodiversity hotspot. In future scenarios, the three biodiversity indices would decline in the Yellow Sea and ECS, but increase in the sea beyond the continental shelf, coastal sea of Hokkaido, and Sea of Okhotsk. Lastly, we explored processes and mechanisms in the change of community composition. By quantifying β-diversity, we identified species loss (nestedness) as the primary driver of fish community change by 2040–2050, with species replacement (turnover) predicted to become dominant in the far future. Our results explore the potential changes in multiple facets of fish biodiversity, providing crucial insights for policymakers aiming to protect fish resources and biodiversity.

Optimization of Graphene-based Antenna using Metasurface for THz Applications using Ensemble Learning models

Aims and Background: These days, communication is governed by scaled-down devices with extremely high data transfer rates. The days of data transfer rates in megabytes are long gone and the systems are touching data speeds of hundreds of gigabytes. To cater to this requirement, the evolution of metasurface-based antennas working in the THz frequency range is gaining pace. Objectives and Methodology: Metasurface layers in antennas have unique mechanical and electrical properties that make them feasible. Graphene is a preferred metasurface material when designing antennas. In this paper, two novel designs of graphene-based metasurface antennas are proposed. These patch antennas with graphene metasurface layers have two configurations for slotted patches. Both graphene and gold-slotted patches are tested in this paper, and results are presented and validated for various performance parameters like return loss, peak gain, peak directivity, and radiation efficiency. Results: The design of the proposed Graphene Patch Antennas (GPA) is done in HFSS, and once the design is complete, the data is collected for variations in antenna parameters and is further processed via machine learning for better convergence in terms of return loss using ensemble learning. Optimal tuning of antenna components like substrate length, patch length, slot width, etc., is done using two regressor algorithms viz Histogram-based Gradient Boosting Regression Tree (HBDT) and Random Forest Tree (RFT) in machine learning. The radiation efficiencies of the two designs presented in this work are 89.04%, 97.54%, an average radiation efficiency of of 93.29%. The bandwidth of the two antenna designs is 8.63 THz and 8.69 THz, respectively. Conclusion: Experimental results indicate that the proposed designs are achieved better bandwidth, and radiation efficiencies compared to state-of-art designs.

Ensemble machine learning models for compressive strength and elastic modulus of recycled brick aggregate concrete

This study delivers an in-depth analysis of predicting the compressive strength and elastic modulus of recycled brick aggregate concrete (RBAC). It assembles an extensive database of 633 compression test results and develops five ensemble learning models—random forest (RF), gradient boosting regression trees (GBRT), extreme gradient boosting (XGB), light gradient boosting machine (LGBM) and stacking (St). These models are evaluated against existing empirical formulas with respect to their effectiveness. The findings reveal that machine learning (ML) models outperform existing formulas: for compressive strength prediction, traditional models achieve a maximum determination coefficient R² of 0.38, whereas ML models attain an R² range of 0.91–0.94. For elastic modulus, the highest R² values are 0.44 for traditional models and 0.97 for ML models. Notably, the LGBM and St models excel in predicting compressive strength and elastic modulus, respectively. The study also identifies critical parameters influencing RBAC’s compressive behavior and highlights their impact trends. Remarkably, while the mass-weighted water absorption of coarse aggregates and the replacement ratio of recycled brick aggregates (RBAs) have less impact on compressive strength compared to the effective water-to-cement ratio, they become more influential for elastic modulus. Additionally, the decrease in elastic modulus due to higher RBA replacement ratios or increased mass-weighted water absorption of coarse aggregates exceeds the corresponding reduction in compressive strength. This research not only deepens the understanding of RBAC’s mechanical properties but also provides valuable predictive tools for civil engineering applications.

Hybrid LSTM-GBRT based machine learning technique implementation for electric vehicle sales prediction analysis

ABSTRACT The investigation of machine learning models in Europe and India for predicting future sales of electric cars (EVs) worldwide has been the focus of present research. In this study, Long Short-Term Memory (LSTM), Support Vector Regression (SVR), Autoregressive Integrated Moving Average (ARIMA), Linear Regression, hybrid long- and short-term memory neural network model and gradient boosted regression trees model (LSTM-GBRT) models based machine learning techniques are compared for performance analysis to predict EV sales. Moreover, in this study, a hybrid LSTM-GBRT technique was developed, which forecasts EV sales, particularly for Battery Electric Vehicles (BEVs) and Plug-in Hybrid Electric Vehicles (PHEVs) over the next five years. During the prediction of EV sales, it has been validated that hybrid LSTM-GBRT technique has better predictive power. In addition, the present study attempts to provide estimated sales statistics for the designated locations. The results indicate that EV industry is evolving, with India showing a strong growth rate in BEV sales and establishing itself as a major participant in the global EV scenario by showing a notable increase in its share of worldwide EV sales volume by 2027. Conversely, the performance of EV sales in Europe has been analysed and validated through the proposed LSTM-GBRT model.