Historical Data Research Articles

Analyses of Variation Trends of Winter Cold Snaps in Subarctic and Arctic Alaska

Arctic Alaska is warming at twice the rate of the rest of the nation, severely impacting infrastructure built on permafrost. As winters warm, the effectiveness of thermosyphons used to stabilize foundations diminishes, increasing the risk of infrastructure failure. Because thermosyphons operate with the highest efficiency during winter cold snaps, studying the variation trends and patterns of winter cold snaps in Alaska is particularly important. To address this issue, this study analyzes the historical temperature data of four selected locations in Subarctic and Arctic Alaska, including Bethel, Fairbanks, Nome, and Utqiagvik. The winter cold snap is defined as a period when the average daily temperature drops below a specific site’s mean winter air temperature. The frequency, duration, and intensity of the winter cold snaps are computed to reveal their trends. The results indicate that the mean annual air temperature (MAAT) shows a warming trend, accompanied by sudden warming after 1975 for all study sites. The long-term average monthly air temperature also indicates that the most significant warming occurs in the winter months from December to March. While the frequencies of winter cold snaps remain relatively unchanged, the mean intensity and duration of cold snaps show a declining trend. Most importantly, the most intense cold snap during which the thermosyphons are the most effective is becoming much milder over time for all study sites. This study focuses specifically on the impact of changes in winter cold spells on thermosyphon effectiveness while acknowledging the complexity of other influencing factors, such as temperature differences, design features, coolant properties, and additional climatic parameters (e.g., wind speed, precipitation, and humidity). The data for this study were obtained from the NOAA NCEI website. The findings of this study can serve as a valuable reference for the retrofit or design of foundations and for decision making in selecting appropriate foundation stabilizing measures to ensure the long-term stability and resilience of infrastructure in permafrost regions. Moreover, the insights gained from this research on freeze–thaw dynamics, which are also relevant to black soils, align with the journal’s focus on sustainable soil utilization and infrastructure resilience.

An optimized informer model design for electric vehicle SOC prediction.

SOC prediction is of great value to electric vehicle status assessment. Informer model is better than other models in SOC prediction, but there is still a gap in practical application. Therefore, based on the health assessment algorithm, a new optimized Informer model is proposed to predict SOC. Firstly, the health assessment is carried out through the historical running data of the electric vehicle to obtain the health matrix. Then, the health matrix is used to improve Encoder and Decoder modules and improve the prediction accuracy and speed of Informer model. Subsequently, the health matrix is utilized to optimize the prediction logic, reduce the influence of truncation error, and further improve the SOC prediction accuracy. Finally, using the Informer model before and after optimization, SOC prediction is performed using four different datasets. The results indicate that after optimizing the En-De module of Informer, prediction accuracy improved by approximately 15%, with prediction speed increasing by about 100%. Furthermore, optimizing the prediction logic to reduce truncation error further enhanced Informer's prediction accuracy by around 20%.

Genomic Insights Into the Origin, Decline and Recovery of the Once Critically Endangered Iberian Lynx.

The Iberian lynx was at the brink of extinction by the year 2000 but has since then, and thanks to intensive conservation measures, gone through a remarkable recovery, providing a much-welcomed and encouraging conservation success story. Genetic issues have probably contributed to the decline in the past, and the genetic management of inbreeding and genetic diversity is likely contributing to its recent recovery. The species was an early adopter of genetic and genomic approaches, and the combination of an extreme decline, an intensive monitoring and management programme and extensive genomic resources and data makes the Iberian lynx an excellent model for conservation genomics. Here, we review how genetic and genomic data have contributed to the knowledge of the species evolutionary and demographic history, the evaluation of the genetic status of the species through time, including historical and ancient data, and how this information has prompted and guided conservation actions. In the process, genomics provided valuable insights into the dynamics of functional variation in bottlenecked populations and the consequences of intraspecific and interspecific admixtures. In more applied terms, the species is subjected to an ambitious genetic monitoring and management programme, covering captive, remnant and reintroduced populations, which has succeeded in improving the genetic status of the species and thereby contributed to its recovery. Current genomic work aims at expanding these contributions with novel genomic resources and data whilecapitalising on extensive demographic and genealogical data provided by the ongoing non-invasive genetic monitoring programme.

Signal-Based Trading Strategy for SPY ETF: A Multiple Linear Regression Approach

This study develops a signal-based trading strategy for the SPDR S&P 500 ETF Trust (SPY) using a multiple linear regression framework to analyze interrelationships between SPY and global equity indices across U.S., European, Asian, and Australian markets. By synthesizing historical pricing data from these major benchmarks, the model generates systematic trading signals through predicted price trajectories. In controlled training scenarios, the strategy achieved superior risk-adjusted returns compared to passive buy-and-hold approaches, demonstrating the value of cross-market signal integration. While the framework shows promise for algorithmic trading systems, the study acknowledges limitations in generalizing historical patterns to evolving market conditions. The findings highlight opportunities to enhance predictive accuracy through machine learning architectures capable of processing nonlinear market dynamics. These insights advance quantitative trading research by establishing methodologies for cross-market signal synthesis and proposing pathways to develop adaptive models for volatile capital markets.

AI-Based Credit Scoring Models in Microfinance: Improving Loan Accessibility, Risk Assessment, and Financial Inclusion

AI has made a huge impact in micro financing through the introduction of credit scoring models that have made loans easily accessible, reduced risks associated with lending while increasing the number and population covered by micro finance. The key traditional credit scoring measures that form the basis of conventional credit scoring models mainly base their decision on historical financial data, thus locking out people who do not have formal records with banks in the society. Symbolic models apply new sources of data, like use of mobile phones, transactions, social media accounts, and biometric data to make new credit scores for borrowers. The application of machine learning models will enhance lending decisions at the microfinance institutions, lower costs of operations, and reduce default risks. Nevertheless, there are certain drawbacks that are associated with the use of big data; issues such as data privacy, algorithms bias, meeting regulatory requirements, and technical constraints for MFIs. This paper aims at reviewing the advancement in credit scoring in the microfinance market, the techniques used to couple credit assessment using Artificial Intelligence, and the concerns towards the ethical practice of deploying Artificial Intelligence. It also provides examples of good practice in AI adoption and explores the potential of AI to increase financial inclusion. Despite the benefits that may be brought about by AI in assisting the process of micro financing, it is crucial to ensure fairness, transparency, and responsible use of the technology in microfinance.

IoT-Based SCADA System Used in Generation Forecasting

With the substantial increase in global renewable energy production, real-time data has become essential for the efficient management of these resources particularly offshore and distant installations. A supervisory control and data acquisition system is a system that sends individual messages or directives to the external world. In this research paper, we introduce a SCADA system integrated with the Internet of Things (IoT) to monitor a hybrid system that includes hydropower, solar energy, wind, and tidal power. It provides a range of control functions for supervisors to manage and configure settings effectively. The goal is to achieve energy autonomy and promote sustainable economic growth. This technology makes it easier to administer the warning system, data logging, data monitoring and control system, and generated capacity, among other features of the station’s information. Additionally, a data packet and WiFi analyzer are used to measure the communication parameters and overall performance of the Internet of Things-based SCADA system. In addition, historical energy generation data is used to evaluate and identify what factors are impacting the output of hydropower stations. This data is then utilized to forecast the production levels for the upcoming year through the application of time series analysis.

A practical method for developing future joint probabilities of riverine and coastal flood risk in complex tidal river systems – a case study

ABSTRACT The effects of sea level rise and extreme rainfall have drastically increased the risk of compound storm surge, tidal, and riverine flooding. This study addresses the complexity of assessing flood probability at a site faced with the complexity of a tidal river discharging to another tidal river, incorporating extreme riverine flows, tidal effects, and storm surges. It uses a copula-based joint probability analysis to assess compound current and future flood risk. It also includes a practical method to explore the significant impacts on future flood elevations of climate and hydrology projections and sea level rise. The urban site in Philadelphia, USA, was previously affected by severe flooding during Hurricane Ida. Utilizing historical data, future projections, and defined flood thresholds, the method yields actionable insights, including probabilistic water elevations under current and future scenarios. A current return period estimated using only a riverine flood model of a 50-year return interval is reduced to only 27 years when considering the effects of compound coastal and riverine flooding. The findings show that increases in current riverine water elevations range from 0.3 to 0.9 m, while sea level rise can add up to 1.2 m of water at the site.

Resolving the Cold-Start Issue in Recommender Systems with Reinforcement Learning

The cold-start problem faced by recommender systems is a serious problem, mainly because of the lack of historical data for new users or items. Traditional recommendation techniques, such as collaborative filtering and content-based filtering, are prone to fail in making good recommendations under such conditions. This paper explores the use of reinforcement learning (RL) as a remedy for cold-start problems based on active learning methods and multi-armed bandit models. We propose a novel RL-based approach that learns user preferences incrementally from interaction and improves recommendations in an exploration-exploitation setting. The setting shows improved performance in personalization and user engagement compared to baseline methods. This paper also provides the first-order implications of the cold-start problem in the real world and assesses the challenges faced by industries impacted by this problem. Keywords - Recommender systems, cold-start problem, reinforcement learning, Markov decision processes, deep reinforcement learning, user modelling

Photovoltaic Power Prediction Technology Based on Multi-Source Feature Fusion

With the increase in photovoltaic installed capacity year by year, accurate photovoltaic power prediction is of great significance for photovoltaic grid-connected operation and scheduling planning. In order to improve the prediction accuracy, this paper proposes a photovoltaic power prediction combination model based on Pearson Correlation Coefficient (PCC), Complete Ensemble Empirical Mode Decomposition (CEEMDAN), K-means clustering, Variational Mode Decomposition (VMD), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory (BiLSTM). By making full use of the symmetric structure of the BiLSTM algorithm, one part is used to process the data sequence in order, and the other part is used to process the data sequence in reverse order. It captures the characteristics of sequence data by simultaneously processing a ‘symmetric’ information. Firstly, the historical photovoltaic data are preprocessed, and the correlation analysis of meteorological factors is carried out by PCC, and the high correlation factors are extracted to obtain the multivariate time series feature matrix of meteorological factors. Then, the historical photovoltaic power data are decomposed into multiple intrinsic modes and a residual component at one time by CEEMDAN. The high-frequency components are clustered by K-means combined with sample entropy, and the high-frequency components are decomposed and refined by VMD to form a multi-scale characteristic mode matrix. Finally, the obtained features are input into the CNN–BiLSTM model for the final photovoltaic power prediction results. After experimental verification, compared with the traditional single-mode decomposition algorithm (such as CEEMDAN–BiLSTM, VMD–BiLSTM), the combined prediction method proposed reduces MAE by more than 0.016 and RMSE by more than 0.017, which shows excellent accuracy and stability.

Leveraging Machine Learning Techniques to Study The Stock Market Dynamics in India

This abstract explores the application of time series analysis, machine learning, and deep learning methods in forecasting long-term stock market trends in the Indian financial market. Even though short-term forecasting is challenging due to the complexities of the markets and the emotional factors it has involved, long-term trends become more predictable in data science techniques. Recent studies have been able to showcase that time series analysis happens to be an effective technique in recognizing patterns and predicting future movements based on historical data. One may also observe the inter-stock relationships and understand how those relate to market trends or potential investments. Ongoing advancements in statistical and analytical methods are driving significant progress in stock market analysis. As machine learning techniques keep improving, they will help make forecasting models better, giving investors and financial experts more useful information to make smarter decisions. These developments are poised to improve stock market prediction and offer crucial insights into market behaviour, benefiting stakeholders in the financial sector

Transitioning to Multi‐Purpose Reservoirs: Advancing Performance With Forecast‐Based Pre‐Release Operations

ABSTRACTThis study investigates various operational strategies to enhance flood control in reservoirs, addressing the challenges of balancing flood mitigation and water supply demands in multi‐purpose reservoirs. A comprehensive framework is introduced, which includes a pre‐release model categorizing reservoirs based on system characteristics and simulates multiple operational scenarios. Using historical data and simulations for 11 reservoirs managed by the USACE Louisville District, the effectiveness of different operational policies is evaluated. Key findings indicate that pre‐release operations, particularly with a 72‐h lead time, significantly improve reservoir flood control by reducing end‐of‐flood water levels and shortening the recovery times for design seasonal flood events. A 24‐h pre‐release policy is identified as a practical solution, offering substantial improvements with low adverse impacts, making it suitable for regular implementation. Additionally, other operational strategies are assessed, and pre‐release is suggested as the optimal approach for facilitating the transition of reservoirs from single to multi‐purpose functions. This study underscores the importance of integrating flood forecasting with reservoir operational strategies, advocating for the refinement of release policies to account for unique reservoir conditions. These insights provide a foundation for optimizing reservoir operations, contributing to improved flood and water resource management.

THE IMPACT OF SENTIMENT ANALYSIS AND AI IN STOCK PRICE PREDICTION

Stock price prediction owes much to sentiment analysis and AI, which offer a holistic view of market sentiment and pattern detection in massive datasets. Through sentiment analysis, textual data is processed from various sources, such as social media, news articles, and financial statements, to capture the public's mood toward a company or the market in general. Such insights are then used to develop an understanding of stock price movements from the perspective of investor behaviour and market trends; this gives credence to traditional modes of analysis. Machine learning algorithms and neural networks in AI serve to analyze the vast datasets, finding previously unknown patterns, thus enhancing the prediction of stock price values. AI can sift through enormous volumes of historical price data, economic indicators, and other information of pertinent interest to an analyst. Identification of complex patterns and interrelationships among the data could potentially enhance the accuracy of predictions. Adaptability is where AI scores above any traditional mechanism.

Pacific Meridional Mode implicated as a prime driver of decadal summer temperature variation over Taiwan

Abstract The Pacific Meridional Mode (PMM) is a climate phenomenon in the eastern Pacific, characterized by strong wind-sea surface temperature (SST) interactions. During its positive phase, an atypical north-south SST gradient develops in the northeastern subtropical Pacific, leading to significant global teleconnections, which refers to the mutual influence or correlation between atmospheric or oceanic changes in two distant regions of the Earth. This study examines the relationship between historical summer temperature data for Taiwan (June-August) and PMM indices over a 59-year period (1960-2018), revealing a significant correlation between the two. Regressed large-scale circulations indicate the eastward propagation of a wave train across the Northern Pacific into East Asia, inducing anticyclonic circulations near southeastern China and Taiwan, accompanied by subsidence, which refers to the vertical downward movement of air masses in the atmosphere, typically associated with high-pressure systems and dry weather conditions, that stabilizes the atmosphere. This stabilization reduces the influence of seasonal southwesterly winds while increasing shortwave radiation at the surface, thereby raising surface temperatures in Taiwan. Our findings are further supported by LBM experiments featuring PMM-like heating forcing and by large-scale responses to PMM-related SST patterns simulated in CMIP6 historical runs. While these results suggest that the PMM could be a valuable tool for predicting Taiwan's summer climate on decadal timescales, we also observe model uncertainties in simulating the teleconnection patterns of PMM-related SSTs in East Asia, including Taiwan's summer temperature response. These findings underscore the need for further investigation into the complex interplay between PMM circulation responses, seasonal monsoons, and other components of climate systems simulated in climate models.

Dataset for multi-model comparison and ensemble simulations of canola growth and yield across global sites

This paper describes the dataset that was used to test the reliability of eight crop models in simulating growth and yield of canola in response to sowing dates, nitrogen inputs and climate variability across five countries. The dataset includes four spring cultivars and three winter cultivars across six sites, which represents a diverse range of canola production areas around the world. Model calibration and validation were conducted in the framework of the Agricultural Model Intercomparison and Improvement Project for canola (AgMIP-Canola). Field experimental datasets include site characterization, soil profile characterization, initial soil conditions (soil water and mineral nitrogen contents), in-season and end-season crop measurements (phenology, LAI, biomass, and nitrogen content in leaves, stems and pods, some with seed oil content), and daily weather data. Simulation datasets include the simulation results generated by ten individual model frameworks (eight crop models, APSIM and DSSAT respectively by two groups) for the experimental periods, and scenario simulations using 30 years historical weather data (1981 – 2010) together with a full multi-factorial combinations of temperature (-3, 0, +3, +6, +9 oC), rainfall (-25%, -10%, 0, +10%, +25%), CO2 concentrations (360, 450, 540, 630, 720 ppm) and nitrogen input rates (0, +25%, +50%, +100%, +150%).

Supply chain performance evaluation model for integrated circuit industry based on fuzzy analytic hierarchy process and fuzzy neural network

Abstract To foster the advancement of telecommunications enterprise supply chains and facilitate their transition toward global market competitiveness, the author advocates for a novel performance evaluation framework tailored for the integrated circuit industry supply chain. This framework integrates the fuzzy analytic hierarchy process and fuzzy neural network methodologies to devise a comprehensive supplier performance assessment model. Leveraging extensive historical supplier data, the author employs MATLAB’s neural network toolbox for model training and simulation. The results indicate that the error value output after running the validation sample is relatively small. This indicates that the model can be effectively applied to the performance evaluation of common integrated circuit product suppliers in CM company. According to the performance results of the model application, all participating suppliers have performance scores greater than 0.7, indicating that in the supply and service process of butterfly integrated circuit products, the performance evaluation scores of each supplier meet the requirements of qualified suppliers, among them, suppliers DS1, DS8, and DS9 with a comprehensive performance score greater than 0.8 are relatively excellent suppliers. The model’s effectiveness and accuracy have been confirmed, demonstrating its practical applicability to CM Company. Moreover, its insights provide valuable guidance for establishing supplier performance evaluation systems across various product categories within telecommunications enterprises.

Multi-century mean summer temperature variations in the Southern Rhaetian Alps reconstructed from Larix decidua blue intensity data

Abstract. Ongoing climate change is likely to cause a worldwide temperature increase of 1.5 °C by the mid-century. To contextualize these changes in a long-term context, historical climatological data extending beyond data obtained from instrumental records are needed. This is even more relevant in remote areas characterized by complex climatic influences and where climate sensitivity is pronounced, such as the European Alps. Considering their high temporal resolution, dendrochronological data have been recognized as a fundamental tool for reconstructing past climate variations. In this study, we present a comprehensive dendroclimatic analysis in which blue intensity (BI) data derived from European larch (Larix decidua Mill.) trees in the Southern Rhaetian Alps were employed. By establishing the relationships between BI patterns in tree rings and climate variables, we explored the possibility of using the obtained data for constructing a high-resolution, long-term climate record. The results in the high-frequency domain showed that BI data from European larches explained up to 38.4 % (26.7 %–48.5 %) of the June–August mean temperature variance in the study area; this result is 70 % greater than the mean temperature variance percentages explained by total ring width measurements for the same period in the area. Moreover, the correlation values between the BI data and June–August mean temperature are stable over time, ranging between 0.40 and 0.71 (mean value of 0.57), considering a moving window of 50 years, and at spatial scale, with significant values over the western and central Mediterranean areas returned for all the considered time windows. In fine, the regression performance using BI data is comparable to that using data from more expensive methods of analysis. The results from this investigation will extend the current knowledge on the applicability of using BI data to study the European larch, and the reconstruction described herein is the first attempt to determine whether this proxy can be used for dendroclimatic aims. Thus, BI data represent a suitable tool for extending our knowledge beyond that obtained from instrumental records and for facilitating a more robust evaluation of climate models and future climate scenarios in the Alpine region.

Rapid Source Identification of Mine Water Inrush Using Spectral Data Combined with BA-RBF Modeling

Coal mine safety is vital not only for maintaining production operations but also for ensuring the industry’s sustainable development. The threat posed by mine water hazards is especially severe, growing more critical as mining activities become more intense and reach greater depths. Currently, common methods for identifying water sources mainly depend on hydrochemical data, supplemented by analyses of water level and temperature changes. However, due to constraints in cost, time, and the complexity of mining conditions, there is still significant potential for enhancing water source identification techniques. To advance water source identification, this study introduces a novel approach that uses a spectrophotometer to gather spectral data from water sources. These data are then integrated with a bat algorithm (BA)-optimized radial basis function (RBF) neural network to develop a model for identifying water inrush sources. At Baode Coal Mine in China, 105 water samples from four different sources were collected and analyzed using spectral data. The baseline was corrected using the second derivative technique to ensure the data’s integrity. Additionally, 54 sets of historical hydrochemical data were collected for comparison with the spectral data-based model. Theoretical analysis and experimental results show that both hydrochemical and spectral data are effective for identifying water inrush sources. The hydrochemical data model achieved an accuracy of about 90%, whereas the model based on spectral data reached an average accuracy of 95%. Among the tested models: RBF, GA-RBF, PSO-RBF, BA-RBF, and the BA-RBF model demonstrated superior performance, providing the most rapid and accurate identification of water inrush.

Comparison of Artificial Neural Network Models for Rainfall Prediction in Palu City

Rainfall prediction is crucial to support natural disaster mitigation and water resource management, especially in areas like Palu City with dynamic rainfall patterns. This study evaluated the performance of three Artificial Neural Network (ANN) models with different architectures to identify the most accurate model in predicting rainfall in 2023. To obtain the model, the historical data of nine meteorological parameters in Palu City from 2018 to 2022 was processed using the Python programming language through pre-processing, processing, post-processing, and verification stages. All three models obtained are designed with hidden layers and different nodes. The best model obtained was Model A with one hidden layer, 8 nodes, and a MAPE value of 9.42%, putting it in the excellent category. Meanwhile, Model B and Model C are in a suitable category with MAPE values of 14.43% and 10.23%. The challenge of using the ANN method in predicting rainfall is its tendency to equalize extreme rain. Therefore, complete data is needed to improve ANN performance.

Genomic Characterization of High-Grade Serous Ovarian Carcinoma Reveals Distinct Somatic Features in Black Individuals

Abstract Black individuals experience worse survival after a diagnosis of high-grade serous ovarian carcinoma (HGSC) than White individuals and are underrepresented in ovarian cancer research. To date, the understanding of the molecular and genomic heterogeneity of HGSC is based primarily on the evaluation of tumors from White individuals. In the present study, we performed whole exome sequencing on HGSC samples from 211 Black patients to identify significantly mutated genes and characterize mutational signatures, assessing their distributions by gene expression subtypes. The occurrence and frequency of somatic mutations and signatures by self-reported race were compared to historical data from The Cancer Genome Atlas (TCGA). Despite technical differences (e.g., formalin-fixed vs. fresh-frozen tissue), the distribution of mutations and their variant classifications for major HGSC genes were nearly identical across study populations. However, de novo significantly mutated gene analysis identified genes not previously reported in the TCGA analysis, including the oncogene KRAS and the potential tumor suppressor OBSCN. The prevalence of the homologous recombination deficiency signature was higher among Black individuals with the immunoreactive gene expression subtype compared with the mesenchymal and proliferative subtypes. These findings were confirmed by comparing the data from Black patients to 123 White patients with identical tissue collection and processing. Overall, this study suggests that, while most features of HGSC tumor phenotypes are similar in Black and White populations, there may be clinically-relevant differences. If validated, these phenotypes may be important for clinical decision-making and would have been missed by characterizing tumors from White individuals only.

Predictive Analytics and Machine Learning in Healthcare: A Comprehensive Framework for Clinical Implementation

Predictive analytics and machine learning models are revolutionizing healthcare management by enabling proactive intervention strategies through sophisticated data analysis. This article explores the integration of machine learning algorithms with historical health data to forecast potential health events and risks, providing healthcare providers with powerful tools for anticipatory care. Examining the fundamental architecture, implementation challenges, and clinical validation methods of these predictive models, it demonstrates their transformative impact on healthcare delivery. This article highlights the importance of robust model development, seamless clinical workflow integration, and adherence to regulatory requirements while addressing critical concerns regarding data privacy and ethical considerations. It suggests the successful deployment of predictive analytics in healthcare settings can significantly enhance patient outcomes and resource allocation efficiency while establishing a framework for future advancements in personalized medicine.