Systematic Selection Research Articles

Strategies and challenges of artificial forest reproduction in the forest-steppe zone: Experience of the Korsun-Shevchenkivskyi forest enterprise branch

One of the key problems that arise in the reproduction of forests in the paradigm of sustainable development of the forest industry is the volume of reforestation, which requires its correlation. This problem requires attention, since effective afforestation and reforestation determine the stability of the ecosystem and the importance of forest resources for the conservation of biodiversity in the forest sector. The purpose of the study is to investigate the features of artificial forest reproduction in the conditions of the forest-steppe climatic and geographical zone. The methodological basis for organising observations included field survey of planting material plots, monitoring the state of crops on the area, conducting analytical substantiation of progressive experience, and evaluating the final results obtained. The study was conducted in the Korsun-Shevchenkivskyi forest enterprise branch of the state enterprise “Forests of Ukraine”. The dynamics of annual volumes of artificial forest reproduction, considering the predominant tree species during 2012-2021, is presented. Additionally, the advantages and disadvantages of transplanting of main and related species in the presented forest conditions were analysed. During this period, there is a fluctuation in the volume of artificial forest reproduction in the forest districts under study. With regard to the transplanting of main and related species, it is worth noting its advantages in ensuring biodiversity and rapid forest regeneration. However, there are disadvantages, such as the possibility of losing genetic diversity and considering local conditions for effective seating. As a result, the study helped to determine the trends and features of forest reproduction in these forest districts, and to note the advantages and disadvantages of transplanting of the main and related breeds in various forest-growing conditions. The enterprise is actively implementing measures for forest reproduction, focusing on intensive planting of forest crops. This is achieved by placing plantations in areas that have been subjected to continuous sanitary and reforestation logging. One of the key tasks of the enterprise is to ensure high productivity of forest crops in the region. For this purpose, significant amounts of reforestation work are carried out, including systematic soil preparation and careful selection of optimal species for specific conditions. Considering the recommendations of forest management, an integrated approach to reforestation is reflected, which ensures sustainable and productive ecosystems in the region. The developed strategies can serve as an important tool for introducing innovations in the field of forestry

SyS3DS: Systematic Sampling of Large-Scale LiDAR Point Clouds for Semantic Segmentation in Forestry Robotics

Recently, new semantic segmentation and object detection methods have been proposed for the direct processing of three-dimensional (3D) LiDAR sensor point clouds. LiDAR can produce highly accurate and detailed 3D maps of natural and man-made environments and is used for sensing in many contexts due to its ability to capture more information, its robustness to dynamic changes in the environment compared to an RGB camera, and its cost, which has decreased in recent years and which is an important factor for many application scenarios. The challenge with high-resolution 3D LiDAR sensors is that they can output large amounts of 3D data with up to a few million points per second, which is difficult to process in real time when applying complex algorithms and models for efficient semantic segmentation. Most existing approaches are either only suitable for relatively small point clouds or rely on computationally intensive sampling techniques to reduce their size. As a result, most of these methods do not work in real time in realistic field robotics application scenarios, making them unsuitable for practical applications. Systematic point selection is a possible solution to reduce the amount of data to be processed. Although our approach is memory and computationally efficient, it selects only a small subset of points, which may result in important features being missed. To address this problem, our proposed systematic sampling method called SyS3DS (Systematic Sampling for 3D Semantic Segmentation) incorporates a technique in which the local neighbours of each point are retained to preserve geometric details. SyS3DS is based on the graph colouring algorithm and ensures that the selected points are non-adjacent in order to obtain a subset of points that are representative of the 3D points in the scene. To take advantage of the ensemble learning method, we pass a different subset of nodes for each epoch. This leverages a new technique called auto-ensemble, where ensemble learning is proposed as a collection of different learning models instead of tuning different hyperparameters individually during training and validation. SyS3DS has been shown to process up to 1 million points in a single pass. It outperforms the state of the art in efficient semantic segmentation on large datasets such as Semantic3D. We also present a preliminary study on the validity of the performance of LiDAR-only data, i.e., intensity values from LiDAR sensors without RGB values for semi-autonomous robot perception.

TRENDS IN INFLAMMATORY BOWEL DISEASE INCIDENCE AND PREVALENCE ACROSS EPIDEMIOLOGIC STAGES: A GLOBAL SYSTEMATIC REVIEW WITH META-ANALYSIS

Abstract BACKGROUND Rising incidence and prevalence of inflammatory bowel disease (IBD) observed historically in early-industrialized regions now also appear in newly-industrialized and emerging regions. The epidemiology of IBD has been proposed to progress across epidemiologic stages: 1. Emergence (low incidence and prevalence); 2. Acceleration in Incidence (rapid rising incidence); and 3. Compounding Prevalence (stabilizing incidence, rapid rising prevalence). AIM To gather real-world data on the incidence and prevalence of IBD and characterize global regions in each epidemiologic stage by meta-analyses. METHODS Two previous systematic reviews (database inception–2010; 2010–2016) were updated with a search of MEDLINE, Embase, PubMed, and Web of Science (2017–2023) to identify all population-based studies reporting the incidence or prevalence of Crohn’s disease (CD) or ulcerative colitis (UC). International partners provided a secondary review of the included studies from their local regions. Incidence and prevalence rates (per 100,000 population), stratified by epidemiologic stage, were meta-analyzed to determine pooled rates with associated 95% confidence intervals (95%CI). A Cochrane Q test was used to investigate differences between epidemiologic stages for both CD and UC. RESULTS After assessing 1,250 manuscripts, a total of 491 studies (439 incidence, 228 prevalence) from 80 global regions spanning 1920-2022 were identified by the systematic review (Figure 1). All data identified with our search strategy are available to view in an open-access, online interactive data repository (https://gives21.shinyapps.io/dashboard/) created with Shiny for R. The pooled incidence of CD and UC per 100,000 person-years rose from 0.28 (95%CI: 0.21, 0.36) and 0.57 (95%CI: 0.47, 0.69) in Stage 1 to 2.13 (95%CI: 1.88, 2.42) and 4.05 (95%CI: 3.65, 4.50) in Stage 2 to 9.34 (95%CI: 8.73, 9.99) and 14.07 (95%CI: 13.09, 15.12) in Stage 3 (Table 1). Similarly, the pooled prevalence of CD and UC per 100,000 persons rose from 1.96 (95%CI: 1.41, 2.74) and 6.35 (95%CI: 4.45, 9.07) in Stage 1 to 22.18 (95%CI: 17.96, 27.38) and 45.36 (95%CI: 37.84, 54.38) in Stage 2 to 186.18 (95%CI: 163.18, 212.42) and 255.92 (95%CI: 230.60, 284.02) in Stage 3 (Table 1). Subgroup analysis confirmed differences in both incidence and prevalence for CD and UC between epidemiologic stages (p<0.001). DISCUSSION This is the most comprehensive systematic review on the incidence and prevalence of IBD. The amalgamated real-world data from this study highlight the rising global burden of IBD across three distinct epidemiologic stages: 1. Emergence, 2. Acceleration in Incidence, and 3. Compounding Prevalence. Figure 1 Systematic review study selection flowchart including a brief overview of two previous systematic reviews: Molodecky, N.A. et al. Gastroenterology. 2012;142(1):46-54 and Ng, S.C. et al. Lancet. 2017;390(10114):2769-78. Table 1 Pooled incidence and prevalence rates per 100,000 population for Crohn’s disease and ulcerative colitis. Cochrane Q subgroup analysis for difference in estimates between epidemiologic stages. † Represents the number of study-subregion groups used in the calculation of pooled rates and their 95% confidence intervals.

Counteracting climate denial: A systematic review.

Despite scientific consensus on climate change, climate denial is still widespread. While much research has characterised climate denial, comparatively fewer studies have systematically examined how to counteract it. This review fills this gap by exploring the research about counteracting climate denial, the effectiveness and the intentions behind intervention. Through a systematic selection and analysis of 65 scientific articles, this review finds multiple intervention forms, including education, message framing and inoculation. The intentions of intervening range from changing understanding of climate science, science advocacy, influencing mitigation attitudes and counteracting vested industry. A number of divergent findings emerge: whether to separate science from policy; the disputed effects of emotions and the longitudinal impacts of interventions. The review offers guiding questions for those interested in counteracting denialism, the answers to which indicate particular strategies: identify the form of climate denial; consider the purpose of intervention and recognise one's relationship to their audiences.

Impact of urate-lowering therapy on the course of chronic kidney disease in patients with asymptomatic hyperuricemia: a meta-analysis of randomized controlled trials

The presented study has been carried out to identify the effect of urate-lowering therapy with xanthine oxidase inhibitors on glomerular filtration rate and serum uric acid in patients with asymptomatic hyperuricemia and chronic kidney disease. A systematic review of randomized controlled trials has been conducted; its results based on meta-analysis has been evaluated.
 A systematic search and selection of publications in Embase, PubMed, Cochrane Library, and eLibrary databases has been performed. The studied drugs were xanthine oxidase inhibitors: allopurinol and febuxostat. The study considered the following parameters such as efficacy endpoints, namely, glomerular filtration rate and serum uric acid after 3–15 months of follow-up. Clinical and methodological heterogeneity of the included randomized controlled trials has been assessed as well as publication bias and risk of systematic error. Synthesis has been performed using bivariate meta-analysis assessing residual statistical heterogeneity.
 7 selected randomized controlled trials (1203 patients) have been included in the meta-analysis. This analysis revealed that medication urate-lowering therapy (allopurinol or febuxostat) was associated with higher glomerular filtration rate (+3.0 ml/min/1.73 m2; 95% confidence interval +0.4 to +5.6; p = 0.022) compared with the controls (placebo/no urate-lowering therapy) at 3–15 months of follow-up. Along with this, medication urate-lowering therapy (allopurinol or febuxostat) has been found to result in lower serum uric acid (−3.3 mg/dl; 95% confidence interval −3.8 to −2.8; р 0.001) compared to the controls (placebo / no urate-lowering therapy) at 3–15 months of follow-up.
 The results of the meta-analysis have demonstrated a positive role of allopurinol and febuxostat in increasing glomerular filtration rate and decreasing serum uric acid in patients with chronic kidney disease and asymptomatic hyperuricemia. The presented data suggest that therapeutic measures aimed at the elimination of asymptomatic hyperuricemia, including the use of xanthine oxidase inhibitors, may be important in slowing the progression of chronic kidney failure and may be additional factors of nephroprotection.

Diversity assessment of a lesser known buffalo population from Central India and its comparative evaluation reveals presence of sufficient genetic variation and absence of selection

Planned breeding and conservation strategies for a lesser-known population require an assessment of complete genetic diversity and population structure analysis in addition to its morphometric characteristics. In the present study, a comparative analysis of the genetic structure of a rare buffalo population, namely Chhattisgarhi, was extensively studied using a panel of FAO-recommended microsatellite markers along with well-established breeds namely Murrah, Nili-Ravi, Gojri, Kalahandi, and Nagpuri. Mode shift analysis indicated the absence of genetic bottleneck in the recent past. Assessment of genetic diversity indices across all loci indicated the presence of sufficient genetic variation within and between populations. Analysis of molecular variance between the six different buffalo populations attributed 19.05% of the variations to between-population differentiation. Cluster analyses using DAPC and Bayesian approach along with the phylogenetic tree based on UPGMA grouped six populations into three groups. The Chhattisgarhi population was revealed to be genetically closer to Nagpuri and Kalahandi populations. The study reveals the presence of sufficient genetic diversity within the Chhattisgarhi population and indicates the absence of a systematic selection program. We suggest improvement and conservation programs should be planned for this breed in the near future through short-term selection.

Systematic Selection of Antipsychotics in Schizophrenia: A Binary Search Approach Based on Efficacy and Side Effects

Systematic Selection of Antipsychotics in Schizophrenia: A Binary Search Approach Based on Efficacy and Side Effects

我国教育实证研究十年发展趋势——基于大样本系统随机抽样的分析

我国教育实证研究十年发展趋势——基于大样本系统随机抽样的分析

Drug-resistant tuberculosis: integrative review of nursing care in primary health care.

to identify, in the scientific literature, the care that should be provided to individuals with drug-resistant tuberculosis by nurses in primary health care. integrative review, using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses study selection flowchart. Data collection was conducted in November 2022, across ten databases. six studies emphasized that nurses should perform directly observed treatment; two highlighted the importance of integrated care management between tuberculosis and human immunodeficiency virus; two demonstrated comprehensive nursing consultation using the nursing process; one emphasized person-centered care, with discharge planning and improved hospital communication with primary health care services. the care that nurses should provide to individuals with drug-resistant tuberculosis in primary health care, for care resolution, is evidence-based.

Parameter development for Laser Powder Bed Fusion of nickel-based Haynes 282 using diverse density determination methods

To manufacture functional components using laser powder bed fusion (PBF-LB/M), the execution of a parameter development with the specific material and machine is an indispensable step. Typically, in the search for the optimal parameter set, the volumetric energy density (VED) used to melt the material serves as an adjustment variable, while the resulting part density as the target parameter. Although this approach effectively reduces the process parameters search-space, additional criteria concerning part quality should be considered in the development. This paper introduces a systematic parameter selection approach, refining the characterization process for processing the nickel-based superalloy Haynes® 282®. The presented strategy not only incorporates the density as target condition but also considers the surface quality and dimensional accuracy of the manufactured samples, crucial for near-net-shape manufacturing. Additionally, three porosity measurement methods (Archimedes method, microscopy, gaspycnometry) for AM metal parts are compared, and their validity for this purpose is discussed.

Predicting Radiologists' Gaze With Computational Saliency Models in Mammogram Reading

Previous studies have shown that there is a strong correlation between radiologists' diagnoses and their gaze when reading medical images. The extent to which gaze is attracted by content in a visual scene can be characterised as visual saliency. There is a potential for the use of visual saliency in computer-aided diagnosis in radiology. However, little is known about what methods are effective for diagnostic images, and how these methods could be adapted to address specific applications in diagnostic imaging. In this study, we investigate 20 state-of-the-art saliency models including 10 traditional models and 10 deep learning-based models in predicting radiologists' visual attention while reading 196 mammograms. We found that deep learning-based models represent the most effective type of methods for predicting radiologists' gaze in mammogram reading; and that the performance of these saliency models can be significantly improved by transfer learning. In particular, an enhanced model can be achieved by pre-training the model on a large-scale natural image saliency dataset and then fine-tuning it on the target medical image dataset. In addition, based on a systematic selection of backbone networks and network architectures, we proposed a parallel multi-stream encoded model which outperforms the state-of-the-art approaches for predicting saliency of mammograms.

RELAÇÕES ÉTNICO-RACIAIS NA EDUCAÇÃO PROFISSIONAL TÉCNICA DE NÍVEL MÉDIO: UMA REVISÃO INTEGRATIVA

ABSTRACT: This study aims to analyze the scientific evidence on ethnic-racial relations education in the scope of technical professional education at the secondary level. This is an exploratory and qualitative research, whose integrative literature review technique allowed the systematic selection of reports in six stages. Initially, the search of articles through SciELO, CAPES Journal, and Google Scholar from the terms race, ethnicity, race factor, racism, racial prejudice, racial discrimination, ethnic-racial relations, professional and technological education, and professional education, along with Boolean operators, resulted in 11,336 titles, and after screening, 11 articles were included. For discussion, the following categories were used: institutionalization of Law nº 10.639/2003 and curriculum; structural racism; quota law; nucleus of Afro-Brazilian and indigenous studies, research and extension; pedagogical experiences about ethnic-racial diversity; students' and teachers' perceptions of ethnic-racial diversity in the curriculum; and the role of teachers for the professional education of black women. It was found that there is a long way to go for the institutionalization of Laws 10,639/03 and 11,645/08 in the curricula and in the teaching-learning practices of vocational training, reinforced by the negative perceptions of students and teachers about ethnic-racial diversity in the curricula. of professional and technological education institutions, especially when it comes to integrated courses. However, the quota laws, the implementation of NEABI, and the different teaching experiences stood out as affirmative actions that promoted racial equality.

Scientific Mapping of Research on Application of Gamification in Higher Education

Gamification significantly enhances educational objectives, with existing literature affirming its widespread use to improve student performance across various disciplines. This bibliometric mapping analysis investigates the realm of gamification within higher education, utilising the Scopus database as a source for the review. Through a systematic selection process, the study encompasses an examination of 609 scholarly articles. The bibliometric analysis, performed using the VOSviewer tool, aimed to ascertain trends in publications, the contributions of various countries, the most influential authors, journals, articles, and research methodologies employed, as well as the topics that have garnered the most attention and the research areas for future exploration. The results indicate a rising trend in the number of publications since 2016, peaking in 2023 with 146 articles. Spain, the United States, and the United Kingdom made significant contributions to the research output. Moreover, in this field, "Computers and Education" has been recognised as the leading journal, with Juho Hamari emerging as the most frequently cited author. Researchers in this field may find these findings beneficial, offering a comprehensive understanding of the current research landscape.

Design and Implementation of Novel Rotor Side Brushless Controller With Bidirectional Wireless Power Transmission for Doubly-Fed Machine

This paper proposes a novel rotor side brushless controller (RSBC) with bidirectional wireless power transmission (WPT) for a doubly-fed motor (DFM), which can realize the brushless DFM without changing the stator and rotor structures. The WPT-RSBC consists of a grid side converter, a series–series compensated resonant converter, and a rotor side converter. According to the operational characteristics of DFMs, the design requirements of the WPT-RSBC are given in this paper. The systematic selection method for four-quadrant operations of the DFM is introduced, and the variable bus voltage control strategy is proposed to improve its transmission efficiency. The mathematical model and small-signal model of each subsystem in the WPT-RSBC are given, and the stability of the primary and secondary DC bus is analyzed. An experimental platform is implemented to verify the feasibility of the WPT-RSBC. For the prototype, the air-gap length is 1 mm, and the RSBC's transmission efficiency can be up to 92%.

Implikasi Pendidikan Kewirausahaan dalam Membentuk Minat dan Kompetensi Wirausaha

This qualitative literature analysis examines the implications of entrepreneurship education in shaping entrepreneurial interest and competencies. The study aims to gain a comprehensive understanding of how entrepreneurship education influences individuals' interest in entrepreneurship and their development of entrepreneurial competencies. Through a qualitative analysis of relevant literature, the research addresses key research questions regarding the impact of entrepreneurship education, factors contributing to the formation of interest and competencies, and potential cultural variations in these implications.The research methodology involves a systematic selection of credible literature from various sources, including scholarly journals, books, and articles related to entrepreneurship education, entrepreneurial interest, and competencies. Data collected is analyzed qualitatively, identifying major themes and synthesizing the literature to reveal the relationships between entrepreneurship education, entrepreneurial interest, and competencies. The analysis also explores factors within entrepreneurship education that support the formation of interest and competencies, such as curriculum design, teaching methods, learning environment, and social influences. The findings of this study contribute to a deeper understanding of the implications of entrepreneurship education in shaping entrepreneurial interest and competencies. It elucidates the influence of entrepreneurship education on individuals' interest in entrepreneurship and the competencies developed through such education. Additionally, it identifies critical factors that contribute to the formation of entrepreneurial interest and competencies, offering insights for policymakers and education practitioners to enhance the effectiveness of entrepreneurship education in fostering entrepreneurial interest and competencies. By conducting a comparative analysis across different cultural or national contexts, the research examines potential variations in the implications of entrepreneurship education. This analysis sheds light on differences in entrepreneurship education approaches and cultural factors that influence the formation of entrepreneurial interest and competencies. Overall, this research contributes to the field of entrepreneurship education by advancing our understanding of its implications in shaping entrepreneurial interest and competencies. The findings provide valuable insights for the development of effective entrepreneurship education approaches, guide policymakers in formulating education policies, and promote broader awareness and participation in entrepreneurship

The quality of university educational programs on environmental and agrobiological focus in graduates’ opinion

The article presents the opinions of the of universities’ graduates in the South of Russia on the quality of the university educational programs on environmental and agrobiological focus. A brief review of publications conducted on the basis of systematic selection in the main knowledge-intensive databases confirms the relevance of the proposed research question. The assessment of the quality of training of agrobiological and environmental specialists is considered by the scientific community as a significant social and educational problem. The empirical part of the study examines the opinions of graduates of environmental and agrobiological educational programs in the South of Russia in terms of their assessments of the quality of education received. A total of 396 graduates took part in the survey. The results were processed in the SPSS Statistics program (version 24). The strategic vectors of increasing the quality of university educational programs in the field of ecology and agrobiology are: the development of competencies for environmentally safe and responsible entrepreneurship; international standardization of the quality of agricultural education to ensure the sustainable development of agricultural production, food and environmental safety; work with digital process assistants.

Directed work on breeding of high-blooded rabbit litters in the rabbit breeding laboratory of Belgorod GAU

The rabbit is one of the most common types of laboratory animals used in a number of experimental studies in general biology, medicine and veterinary medicine. And today, the most actively discussed strategy is the policy of import substitution as a factor in ensuring the growth of domestic agribusiness, and of course rabbit breeding is the most promising and rapidly developing industry. Therefore, we believe that the creation of crossbred rabbits of domestic selection that are not inferior in their characteristics to their European counterparts is an extremely urgent task, which served as the driver for the development of the issue of creating a highly productive herd of rabbits (high-blooded crossbreeds) in a relatively short time: until 2024. It should be noted that the selection process began in 2013 and systematically developed until the present time, when it became obvious and relevant for the development of the food cluster of the Belgorod region, including the work on the creation of a specialized, fully adapted line of rabbits. As a result of systematic selection work aimed at growth energy, milk production in rabbits and white dermis, we have a rabbit with a given phenotype (white color with a thickness of 9-15 microns in the area of the withers of the epidermis, dermis -250-350 microns, in accordance with the requirements for the production of resorbing membranes from dermis of rabbits for the dental industry), the live weight of male sires over 8 months of age on average is 4.8-5.8 kg, female rabbits - 4.7-5.5 kg. Today, the obtained economically useful characteristics are being stabilized and consolidated in the offspring.

Implementation of cyber counseling in the Merdeka Belajar curriculum in the era of society 5.0

Counselors have an important role in the success of the Merdeka Belajar curriculum. Counselors need to have cyber counseling to support their professionalism in implementing guidance and counseling. This study aims to examine the implementation of cyber counseling in the Merdeka Belajar curriculum. The research uses the systematic literature review method which is carried out in six stages, namely problem formulation, systematic literature search, screening and selection of relevant articles, qualitative analysis and synthesis, quality control, compiling reports. A total of 14 articles that passed the screening were reviewed to identify various strategies that have been used for implementation. The results of this study indicate that the implementation of cyber counseling in Merdeka Belajar curriculum includes technical preparation of hardware and software. The stages that need to be considered are almost the same as counseling in general. First, the preparation stage which includes technical preparation of hardware, software, and evaluation. Second, the counseling process stage which consists of delivery, exploration, interpretation, coaching, and assessment. And the third stage, the post-counseling stage which is marked by the success of counseling with effective client conditions. This research can be a reference for further research to be able to develop more innovative and applicable cyber counseling implementation strategies.

A method for the systematic selection of enzyme panel candidates by solving the maximum diversity problem

Enzymes are being increasingly exploited for their potential as industrial biocatalysts. Establishing a portfolio of useful biocatalysts from large and diverse protein family is challenging and a systematic method for candidate selection promises to aid in this task. Moreover, accurate enzyme functional annotation can only be confidently guaranteed through experimental characterisation in the laboratory. The selection of catalytically diverse enzyme panels for experimental characterisation is also an important step for shedding light on the currently unannotated proteins in enzyme families. Current selection methods often lack efficiency and scalability, and are usually non-systematic. We present a novel algorithm for the automatic selection of subsets from enzyme families. A tabu search algorithm solving the maximum diversity problem for sequence identity was designed and implemented, and applied to three diverse enzyme families. We show that this approach automatically selects panels of enzymes that contain high richness and relative abundance of the known catalytic functions, and outperforms other methods such as k-medoids.

Effects of systematic predictor selection for statistical downscaling of rainfall in Hawai'i

AbstractWhile there has been rapid advancement in the development and application of statistical downscaling methods for climate projection, determining the best predictive large‐scale climate information for the targeted local climate variable remains a challenge. The choice of predictor variables is one of the most influential steps of model development and has the potential to lead to varying results, contributing to the total uncertainty of future projections. Despite being a well‐known problem, predictor selection often does not receive adequate attention and the development of a straightforward and feasible prescreening process is needed to provide guidance to simple (e.g., linear regression) and complex (e.g., machine learning) modeling tools alike. In this project, Akaike information criterion (AIC) and leave one out cross validation are used to evaluate sets of predictor variables common in statistical downscaling models of precipitation (e.g., temperature, geopotential height, moisture transport). Because thousands of predictor sets were found to be competitive in their statistical skill in projecting rainfall, results suggest that an ensemble of predictor sets should be used to account for the resulting variance associated with predictor selection. This ensemble approach is applied to make improvements to the most recent statistical downscaling model developed for rainfall projection in Hawai'i. An ensemble validation study is performed by projecting future wet season rainfall in Hawai'i for scenario RCP4.5 using 17 CMIP5 GCMs with ensembles of highly ranked and poorly ranked predictor sets. Results show significantly less variance and improved agreement in the projected sign of precipitation change for the highly ranked predictor set ensemble. In conclusion, it is recommended that statistical downscaling models are run in an ensemble‐mode with multiple combinations of predictors instead of using a single model, allowing for additional quantification of model uncertainty and a “safety net” for when the true physically best‐suited predictor set is unknown.