Ensemble Performance Research Articles

Probing coherence properties of shallow implanted NV snsembles under different oxygen terminations

Abstract Nitrogen vacancy (NV) color centers in diamond have shown great potential for various applications in quantum technology due to their long coherence times, high sensitivity to magnetic fields and atomic scale resolution. However, one major challenge in utilizing near surface NV centers is the decoherence caused by spins and charges fluctuating on the surface, which affects the spin properties of the sensors. To reduce the induced noise, various oxygen surface treatments such as low power oxygen plasma treatment and annealing under oxygen atmosphere have been explored to terminate the diamond surface and reduce its impact on NV coherence. We showed that the NV center's coherence time can be enhanced up to a factor of 3 over a large spectral range of noise. Double electron electron resonance (DEER) measurements revealed an extra source of decoherence, scaling similarly as the P1 spin bath. The improvement in coherence times is accompanied with an increase in measured ketone/ether content and reduction of sp2 signal in X-ray photoelectron spectroscopy (XPS) measurements. Finally we compared the performance of different NV ensembles and surface treatments for sensing external proton spins. The oxygen annealing is an effective procedure of enhancing the spin coherence times and reducing broad band spin noise experienced by shallow implanted ensemble NV centers in diamond.

Assessing the influence of climate change on multiple climate indices in Nepal using CMIP6 global climate models

Global climate models (GCMs) serve as essential tools for projecting future climate trends, but their coarse resolution limits localized impact assessments in sectors like hydrology, agriculture, and biodiversity. Observation data with a spatial resolution of a few kilometers are crucial for downscaling and bias-correcting GCMs at finer resolutions. However, Nepal's extreme topography and organizational challenges have led to uneven distribution of meteorological stations and inconsistent data quality. Moreover, CMIP6-based climate extremes projections for the entire country are currently unavailable. To tackle these challenges, we developed a comprehensive national database for Nepal, offering high-resolution historical and projected precipitation and temperature data analyzed through 25 climate extreme indices from the Expert Team on Climate Change Detection and Indices (ETCCDI). Initially, observation grid data were prepared at a daily timescale with a spatial resolution of 0.05° × 0.05° for baseline period (1981–2010) using the Asian Precipitation High-Resolved Observational Data Integration Toward Evaluation (APHRODITE), the fifth generation of the European Centre for Medium-Range Weather Forecasts Reanalysis (ERA5), and available good quality observed climate data. This data was then utilized to downscale and bias-correct 18 CMIP6 GCMs for 2015–2100 under four SSPs (1–2.6, 2–4.5, 3–7.0, 5–8.5). Quantile mapping was employed for the bias correction of the CMIP6 GCMs. The performance of the multimodal ensemble (MME) indicated better Nash-Sutcliffe Efficiency (NSE), root mean square error ratio (RSR), and Percent Bias (PBIAS) of climate extreme indices for the historical period. A comparative analysis was conducted across Nepal's major geographic regions to account for spatial variability in regional climate systems. The finer-resolution dataset can be crucial to deepen our understanding of climate impacts, and climate change, and eventually informing the policy-making in Nepal. Moreover, the methodology can be effectively replicated in data-scarce developing nations to promote climate research and adaptation efforts.

A clustering ensemble algorithm for handling deep embeddings using cluster confidence

Abstract Clustering ensemble, which aims to learn a robust consensus clustering from multiple weak base clusterings, has achieved promising performance on various applications. With the development of big data, the scale and complexity of data is constantly increasing. However, most existing clustering ensemble methods typically employ shallow clustering algorithms to generate base clusterings. When confronted with high-dimensional complex data, these shallow algorithms fail to fully utilize the intricate features present in the latent data space. As a result, the quality and diversity of the generated base clusterings are insufficient, thus affecting the subsequent ensemble performance. To address this issue, we propose a novel clustering ensemble algorithm for handling deep embeddings using cluster confidence (CEDECC) to improve the robustness and performance. Instead of simply combining deep clustering with clustering ensembles, we take into consideration that the performance of existing deep clustering methods heavily relies on the quality of low-dimensional embeddings generated during the pre-training stage. The quality of embeddings is unstable due to the influence of different initialization parameters. In CEDECC, specifically, we first construct a cluster confidence measure to evaluate the quality of low-dimensional embeddings. Typically, high-quality low-dimensional embeddings yield accurate clustering results with the same model parameters. Then, we utilize multiple high-quality embeddings to generate the base partitions. In the ensemble strategy phase, we consider the cluster-wise diversity and propose a novel ensemble cluster estimation to improve the overall consensus performance of the model. Extensive experiments on three benchmark datasets and four real-world biological datasets have demonstrated that the proposed CEDECC consistently outperforms the state-of-the-art clustering ensemble methods.

Theoretical Analysis and Practical Exploration of Enhancing Flute Section Ensemble Performance through Positive Interdependence Theory

Theoretical Analysis and Practical Exploration of Enhancing Flute Section Ensemble Performance through Positive Interdependence Theory

Basic research on the effect of distance between performers on ensemble performance

Due to the spread of COVID-19, the performers on stage were required to keep a certain distance among them. Because it was considered that the droplets come from performers rise a risk of infection with COVID-19 when they performed musical instruments. A distance of at least 2 m between wind instrument performers, and 1.5 m between string instrument performers was recommended. However, with these distances, the performers found it difficult to perform. Actually, in previous studies, it has been suggested that difficulties in listening to their performance can occur. However, the specific causes of these problems have not yet been clarified. Therefore, the purpose of this study is to clarify the effects of differences in distance between performers on acoustical properties and auditory perception by focusing on performers in an ensemble. In particular, targeting a group of five performers arranged in a semi-elliptical shape, the various acoustic physical quantities, and conducting subjective evaluation experiments were performed. As a result, it was found that changes in the distance between performers affect the acoustic properties and the auditory perception. This knowledge will contribute to creating a comfortable environment for performers.

Daily river flow simulation using ensemble disjoint aggregating M5-Prime model

Accurate prediction of daily river flow (Qt) remains a challenging yet essential task in hydrological modeling, particularly crucial for flood mitigation and water resource management. This study introduces an advanced M5 Prime (M5P) predictive model designed to estimate Qt as well as one- and two-day-ahead river flow forecasts (i.e. Qt+1 and Qt+2). The predictive performance of M5P ensembles incorporating Bootstrap Aggregation (BA), Disjoint Aggregating (DA), Additive Regression (AR), Vote (V), Iterative classifier optimizer (ICO), Random Subspace (RS), and Rotation Forest (ROF) were comprehensively evaluated. The proposed models were applied to a case study data in Tuolumne County, US, using a dataset comprising measured precipitation (Pt), evaporation (Et), and Qt. A wide range of input scenarios were explored for predicting Qt, Qt+1, and Qt+2. Results indicate that Pt and Qt significantly influence prediction accuracy. Notably, relying solely on the most correlated variable (e.g., Qt-1) does not guarantee robust prediction of Qt. However, extending the forecast horizon mitigates the influence of low-correlation input variables on model accuracy. Performance metrics indicate that the DA-M5P model achieves superior results, with Nash-Sutcliff Efficiency of 0.916 and root mean square error of 23 m3/s, followed by ROF-M5P, BA-M5P, AR-M5P, AR-M5P, RS-M5P, V-M5P, ICO-M5P, and the standalone M5P model. The ensemble M5P modeling framework enhanced the predictive capability of the stand-alone M5P algorithm by 1.2 %–22.6 %, underscoring its efficacy and potential for advancing hydrological forecasting.

A Combined Scheme based on the Multiscale Stochastic Perturbed Parameterization Tendencies and Perturbed Boundary Layer Parameterization for a Global Ensemble Prediction System

Abstract Stochastic representations of model uncertainties are of great importance for the performance of ensemble prediction systems (EPSs). The stochastically perturbed parameterization tendencies (SPPT) scheme with a single-scale random pattern has been used in the operational global EPS of China Meteorological Administration (CMA-GEPS) since 2018. To deal with deficiencies in this operational single-scale SPPT scheme, a combined scheme based on the multiscale SPPT (mSPPT) scheme and the stochastically perturbed parameterization for the planetary boundary layer (SPP-PBL) scheme is developed. In the combined scheme, the mSPPT component aims to expand model uncertainties characterized by SPPT at mesoscale, synoptic scale, and planetary scale. The SPP-PBL component with six vital parameters is used to capture uncertainties in PBL processes, which is underrepresented by SPPT for the tapering treatment within PBL. Comparisons between the operational SPPT scheme and the mSPPT scheme reveal that the mSPPT scheme can generate more improvements in both ensemble reliability and forecast skills mainly in tropics. Besides, additional benefits from SPP-PBL on top of mSPPT are shown to be primarily distributed in tropics at the lower layers below 850 hPa and surface. Furthermore, the combined scheme of mSPPT and SPP-PBL is suggested to yield better spread–error relationships and forecast skills than the operational SPPT scheme in terms of objective verification scores for standard upper-air variables and surface parameters. A case study for the extreme precipitation event on 20 July 2021 in Henan Province of China also demonstrates the better ability of the combined scheme in forecasting the precipitation intensity and location. Significance Statement A comprehensive and reasonable representation of model uncertainties helps to improve the performance of ensemble prediction systems (EPSs). Despite the popular usage in simulating model uncertainties, the stochastically perturbed parameterization tendencies (SPPT) scheme possesses several shortcomings. To overcome this, a combined scheme based on the multiscale SPPT (mSPPT) scheme and the stochastically perturbed parameterization for the planetary boundary layer (SPP-PBL) scheme is proposed. Based on the global EPS of China Meteorological Administration (CMA-GEPS), additional benefits from the independent usage of mSPPT and SPP-PBL are disclosed. And the combined scheme can inherit the merits of mSPPT and SPP-PBL and generate more improvements on ensemble performance than the original single-scale SPPT scheme. This research provides a guideline for future upgradation of CMA-GEPS.

Optimizing Disease Outbreak Forecast Ensembles.

On the basis of historical influenza and COVID-19 forecasts, we found that more than 3 forecast models are needed to ensure robust ensemble accuracy. Additional models can improve ensemble performance, but with diminishing accuracy returns. This understanding will assist with the design of current and future collaborative infectious disease forecasting efforts.

Spatio-temporal forecasting of landslide hazard in Chongqing National Transmission Protection Regions, China

ABSTRACT Previous studies on landslide susceptibility (LS) and hazard (LH) assessments have overlooked a crucial measure for evaluating validation effectiveness, which involves the use of post-temporal landslide inventories instead of solely relying on historical data. Therefore, this study constructed a regional LH prediction and validation framework at different timescales using the landslide data from 2002 to 2021. Firstly, based on updated landslide data and conditioning factors, the datasets for susceptibility modelling were built for various periods. Then, the performances of traditional ma chine learning, ensemble and deep learning models were compared. Finally, the multi-period rainfall data and susceptibility results were used in innovative LH forecasting. Our study results show that the ensemble learning model (random forest) has stronger generalisation ability in different time periods, with all Area Under Curve (AUC) values exceeding 0.9. The hazard modelling framework based on rainfall erosion intensity and susceptibility can effectively forecast LH, and the shortened timescale for rainfall erosion intensity can improve the accuracy of LH forecasting. At the very high hazard level, the percentage of landslides forecast increased from 25.23% to 42.86%. This study comprehensively explores spatio-temporal dynamic changes in LH, accurately identifying areas posing threats to the National Transmission Line Protection Regions (NTLPR).

Dynamic stacking ensemble for cross-language code smell detection.

Code smells refer to poor design and implementation choices by software engineers that might affect the overall software quality. Code smells detection using machine learning models has become a popular area to build effective models that are capable of detecting different code smells in multiple programming languages. However, the process of building of such effective models has not reached a state of stability, and most of the existing research focuses on Java code smells detection. The main objective of this article is to propose dynamic ensembles using two strategies, namely greedy search and backward elimination, which are capable of accurately detecting code smells in two programming languages (i.e., Java and Python), and which are less complex than full stacking ensembles. The detection performance of dynamic ensembles were investigated within the context of four Java and two Python code smells. The greedy search and backward elimination strategies yielded different base models lists to build dynamic ensembles. In comparison to full stacking ensembles, dynamic ensembles yielded less complex models when they were used to detect most of the investigated Java and Python code smells, with the backward elimination strategy resulting in less complex models. Dynamic ensembles were able to perform comparably against full stacking ensembles with no significant detection loss. This article concludes that dynamic stacking ensembles were able to facilitate the effective and stable detection performance of Java and Python code smells over all base models and with less complexity than full stacking ensembles.

Kilometer-scale multi-physics simulations of heavy precipitation events in Northeast China

Despite the fatal impact of heavy precipitation on people’s lives and the social economy, its accurate estimating remains challenging. In this study, we show how to address this issue by kilometer-scale simulations and how to reduce computational costs in Northeast China with the complex terrain and distribution of land and sea. Three typical heavy precipitation events are simulated at 3 km horizontal resolution, and each event is simulated with 24 combinations of schemes (with or without a scale-aware cumulus scheme, three microphysics schemes, and four planetary boundary layer schemes), which are evaluated against gauge observations. Compared to gauge observations, the ensemble mean of simulations of hourly maximum precipitation and average accumulated precipitation outperforms three widely accepted satellite products in the cold vortex and the snowstorm case, and is of comparable accuracy in the typhoon case. Overall, the microphysics scheme significantly impacts the maximum hourly precipitation, whereas the planetary boundary layer scheme has a strong control over the accumulated precipitation. The similarity among different simulations is linked to the level of convective instability's impact on heavy precipitation in each case, which also indicates that conducting 24 simulations can be not necessary. This study uses an ensemble performance estimation technique assuming the impact of different schemes is additive and finds that performing 13 rather than 24 simulations allows finding the best-performing combination of parameterization schemes, which allows for saving almost 50% of computational costs.

블랜디드 러닝 수업을 적용한 칼림바 합주 수업지도 방안 연구: 메타버스 플랫폼 ‘ZEP’을 중심으로

The purpose of this study is to design a Kalimba ensemble teaching plan based on the direction and digital application of the 2022 revised curriculum, and to suggest ways to effectively fulfill the goals of the 2022 revised curriculum in the school setting. The theoretical backgrounds of the Kalimba and the Metaverse were gathered through a review of academic papers and dissertations. The performance domain of the 2022 revised music curriculum was analyzed to design a teaching plan and explore practical methods for implementing a digital-instrument integrated class, as intended by the revised curriculum. The digital elements and music performance classes emphasized in the 2022 revised curriculum were fused so that students could experience the basics of new technologies. To create a student-led participatory class, a virtual reality space and study score were produced directly, enabling students to engage in creative and self-directed learning. To complement this, this study creates a virtual reality space using the Metaverse platform "ZEP" and provides online video and ensemble performance forms using the video link connection function of "ZEP" to foster basic digital literacy and improve music performance. It is hoped that research on instrumental teaching methods using digital media will be further expanded so that students can recognize the sensibility and value of music.

Da Pacem Domine by Arvo Pärt. The Stylistic and Interpretative Analysis – Conductor’s Guide

The piece “Da pacem Domine” (Give us peace, O Lord), by Arvo Pärt was inspired by a Gregorian antiphon from the 9th century. Written in the original tintinnabuli style, the piece uses numerous compositional techniques belonging to the early Renaissance period called Cantus firmus, parallel organum, faux bourdon, Landini cadence or anticipations, but also and even a modern way of vocal scoring: the “pointillistic polyphony”. The work is divided into four sections, corresponding to the four verses of the prayer and the gravitational centre of the music is D. To impart expressive meaning to the musical performance, the interprets, both the conductor or singers can consider the following elements: homogeneity in individual voices and ensemble performance, different singing modalities (legato/non-legato) alternating between moments of cadence and the rest of the piece, the technique of attack and sound placement, finding and maintaining an appropriate inner state reflecting the ideas of the text and the general character of the piece. Keywords: Da pacem Domine, Arvo Pärt, style, interpretation, analyse, conductor, guide

Ensemble Performance: Theoretical, Practical, Aesthetic Dimensions

Ensemble Performance: Theoretical, Practical, Aesthetic Dimensions

Nelder-Mead Optimized Weighted Voting Ensemble Learning for Network Intrusion Detection

The rise in internet usage and data transfer rates has led to numerous anomalies. Hence, anomaly-based intrusion detection systems (IDS) are essential in cybersecurity because of their ability to identify unknown cyber-attacks, especially zero-day attacks that signature-based IDS cannot detect. This study proposes an ensemble classification for intrusion detection using a weighted soft voting system with KNN, XGBoost, and Random Forest base models. The base model weights are optimized using the Nelder-Mead simplex method to improve the overall ensemble performance. We propose a robust intrusion detection framework that uses soft-voting classifier-level weights optimized using the Nelder-Mead algorithm and feature selection. We evaluated the system's performance using the KDD99 and UNSW-NB15 datasets, which demonstrated that the proposed approach exceeded other existing methods in respect of accuracy and provided comparable results with fewer features. The proposed system and its hyperparameter optimization technique were compared with other cyber threat detection and mitigation systems to determine their relative effectiveness and efficiency.

Grand ensemble forecasts verification based on two high resolution (∼12 km) global ensemble prediction systems

The primary objective of this study is to quantitatively assess the skill of grand-ensemble forecasts generated from two high-resolution global ensemble prediction systems (EPSs). We have used the National Centre for Medium Range Weather Forecasting (NCMRWF), India global EPS, denoted as NEPS, and India Meteorological Department (IMD) EPS, known as GEFS. Both of these operational EPSs operate at ∼12 km horizontal grid size and produce ensemble forecast outputs. In this study, these two high-resolution EPSs based grand-ensemble products have been evaluated.Statistical analysis is conducted using seven-day forecasts from NEPS's 22 perturbed members and GEFS's 20 perturbed members. The performance of the global grand ensemble, consisting of 42 members, is evaluated for summer monsoon season, 1st July to 30th September 2019 in comparison to the individual EPS forecasts. The verification metrics are prepared using variables such as Zonal Wind and Temperature at 850 hPa, Geopotential at 500 hPa and Precipitation. These metrics are applied across both the Northern Hemisphere (20°N-90°N) and over the domain located in the South Asia encompassing India and its neighbouring areas (0–40 oN & 50–100°E). The verification metrics employed include ensemble spread, root-mean-square error (RMSE) of ensemble mean, Brier score, relative operating characteristic, area skill score, reliability, rank histogram, ranked probability score, continuous ranked probability score, and relative economic value.We noted that the grand ensemble forecasts in this study carries a higher skill compared to the two constituent models for lead time >3 days and for higher forecast probability for the longer lead times. Lower RMSE in the grand ensemble for longer lead-time forecasts (day 4–7) indicates a better representation when compared to forecasts from individual EPSs. However, it is worth noting that shorter lead-time forecasts (day 1–3) in the grand ensemble could potentially result in over-dispersion. Brier scores further indicate an enhancement in predictability of nearly one day in grand ensemble compared to the individual EPSs for T850, U850 and Z500. RPS of rainfall in a smaller domain centring on India indicates a better score for grand ensemble compared to both the EPS. Grand ensembles demonstrate its ability to provide better reliability and discrimination quality. The economic value of the forecasts based on grand ensemble, is higher with a wider range of cost/loss ratio compared to those in the individual EPSs.

Predicting sales and cross-border e-commerce supply chain management using artificial neural networks and the Capuchin search algorithm

E-commerce provides a large selection of goods for sale and purchase, which promotes regular transactions and commodity flows. Efficient distribution of goods and precise estimation of customer wants are essential for cost reduction. In order to improve supply chain efficiency in the context of cross-border e-commerce, this article combines machine learning approaches with the Internet of Things. The suggested approach consists of two main stages. Order prediction is done in the first step to determine how many orders each merchant is expected to get in the future. In the second phase, allocation operations are conducted and resources required for each retailer are supplied depending on their needs and inventory, taking into account each store’s inventory as well as the anticipated sales level. This suggested approach makes use of a weighted mixture of neural networks to anticipate sales orders. The Capuchin Search Algorithm (CapSA) is used in this weighted combination to concurrently enhance the learning and ensemble performance of models. This indicates that an effort is made to reduce the local error of the learning model at the model level via model weight adjustments and neural network configuration. To guarantee more accurate output from the ensemble model, the best weight for each individual component is found at the ensemble model level using the CapSA method. This method yields the ensemble model’s final output in the form of weighted averages by choosing suitable weight values. With a Root Mean Squared Error of 2.27, the suggested technique has successfully predicted sales based on the acquired findings, showing a minimum decrease of 2.4 in comparison to the comparing methodologies. Additionally, the suggested method’s strong performance is shown by the fact that it was able to minimize the Mean Absolute Percentage Error by 14.67 when compared to other comparison approaches.

The first ensemble of kilometer-scale simulations of a hydrological year over the third pole

An accurate understanding of the current and future water cycle over the Third Pole is of great societal importance, given the role this region plays as a water tower for densely populated areas downstream. An emerging and promising approach for skillful climate assessments over regions of complex terrain is kilometer-scale climate modeling. As a foundational step towards such simulations over the Third Pole, we present a multi-model and multi-physics ensemble of kilometer-scale regional simulations for the hydrological year of October 2019 to September 2020. The ensemble consists of 13 simulations performed by an international consortium of 10 research groups, configured with a horizontal grid spacing ranging from 2.2 to 4 km covering all of the Third Pole region. These simulations are driven by ERA5 and are part of a Coordinated Regional Climate Downscaling EXperiment Flagship Pilot Study on Convection-Permitting Third Pole. The simulations are compared against available gridded and in-situ observations and remote-sensing data, to assess the performance and spread of the model ensemble compared to the driving reanalysis during the cold and warm seasons. Although ensemble evaluation is hindered by large differences between the gridded precipitation datasets used as a reference over this region, we show that the ensemble improves on many warm-season precipitation metrics compared with ERA5, including most wet-day and hour statistics, and also adds value in the representation of wet spells in both seasons. As such, the ensemble will provide an invaluable resource for future improvements in the process understanding of the hydroclimate of this remote but important region.

Simulation testing performance of ensemble models when catch data are underreported

Abstract Ensemble model use in stock assessment is increasing, yet guidance on construction and an evaluation of performance relative to single models is lacking. Ensemble models can characterize structural uncertainty and avoid the conundrum of selecting a “best” assessment model when alternative models explain observed data equally well. Through simulation, we explore the importance of identifying candidate models for both assessment and short-term forecasts and the consequences of different ensemble weighting methods on estimated quantities. Ensemble performance exceeded a single best model only when the set of candidate models spanned the true model configuration. Accuracy and precision depended on the model weighting scheme, and varied between two case studies investigating the impact of catch accuracy. Information theoretic weighting methods performed well in the case study with accurate catch, while equal weighting performed best when catch was underreported. In both cases, equal weighting produced multimodality. Ensuring that an ensemble spans the true state of nature will be challenging, but we observed that a change in sign of Mohn’s rho across candidate models coincided with the true OM being bounded. Further development of protocols to select an objective and balanced set of candidate models, and diagnostics to assess adequacy of candidates are recommended.

A novel dynamic ensemble of numerical weather prediction for multi-step wind speed forecasting with deep reinforcement learning and error sequence modeling

Accurate wind forecasts for one day ahead or longer periods have significant impacts on the safe and efficient dispatch of power grids, where Numerical Weather Prediction (NWP) serves as the essential tool, such as ensemble NWP integrating multiple single simulations. Typically, ensembles include all single members with fixed weights; however, the relative accuracy of each member may change over time. This study introduces an attractive idea: improving ensemble performance by dynamically recognizing and avoiding low-performing members. It proposes a dynamic ensemble strategy based on NWP, reinforcement learning and error sequence correction. The process begins with Weather Research and Forecasting ensemble simulations. A dynamic framework is then constructed by mapping the multi-step ensemble problem into a Markov decision process, which is further solved using deep deterministic policy gradient. Subsequently, a hybrid deep learning model, comprising temporal convolutional network and bidirectional long short-term memory, is constructed for error sequence estimation of dynamic ensemble, using the high-frequency information of NWP as input. Conducting experiments at two wind farms, and focusing on the 24-h wind speed forecast with a 15-min time resolution, the proposed system demonstrates a reliable and stable ensemble throughout the entire forecasting horizon, significantly reducing the probability of large forecasting errors.