Data Analysis Methods Research Articles

Hands-on training about data clustering with orange data mining toolbox.

Data clustering is a core data science approach widely used and referenced in the scientific literature. Its algorithms are often intuitive and can lead to exciting, insightful results that are easy to interpret. For these reasons, data clustering techniques could be the first method encountered in data science training. This paper proposes a hands-on approach to data clustering training suitable for introductory courses. The education approach features problem-based training that starts with the data and gradually introduces various data processing and analysis methods, illustrating them through visual representations of data and models. The proposed training is suitable for a general audience, does not require a background in statistics, mathematics, or computer science, and aims to engage the audience through practical examples, an exploratory approach to data analysis with visual analysis, experimentation, and a gentle learning curve. The manuscript details the pedagogical units of the training, motivates them through the sequence of methods introduced, and proposes data sets and data analysis workflows to be explored in the class.

Effectiveness of "SAFETYPOLY" Learning Media in Improving Public Knowledge of Chemical Hazards in the Printing Industry

In today's development, many games are played by all groups, from small children to adults and older people. This game can be used for fun or as a learning medium. This game can also be used to increase public knowledge, one of which is regarding occupational safety and health. There is a game that can be used to improve understanding in society, namely monopoly. Therefore, this research aims to determine the effectiveness of monopoly learning media, which contains occupational safety and health "safetypoly", in increasing public knowledge regarding Occupational Safety and Health. This study used a quantitative research approach with a pre-experimental type of research. The research design used in this study was the One Group Pretest-Posttest Control Design. Data collection methods include questionnaires, observation, and interviews. The data analysis methods used in this research are the Validity Test, Reliability Test, Normality Test, and Wilcoxon Test. The "Test Statistics" output is known as Asymp based on the research results.Sig. (2-tailed) is worth 0,000. The value of 0.000 is smaller than <0.05, so there is a difference between the pre-test and post-test results. Apart from that, there was an increase in workers from 20% to 80%. It can be concluded that the safetypoly game influences students' level of knowledge regarding the dangers of chemicals, so this game is effectively used as an educational medium related to occupational safety and health.

Examining the Influence of the Perceived Parental Involvement on Teachers' Sense of Self-Efficacy, Work Commitment, and Job Satisfaction

Developing strategies for more collaborative models of school-parent relationships is essential for supporting teachers and, ultimately, enhancing student learning outcomes worldwide. The relationship between parents and teachers is crucial in the educational process and can significantly influence teachers' professional identity. This study examined the impact of parental involvement on teachers' professional identity, focusing on self-efficacy, work commitment, and job satisfaction. A quantitative approach was employed using linear data collection and analysis methods. Data were collected through questionnaires from a representative sample of teachers from various schools. Descriptive statistics were used to outline the characteristics of the dataset. In addition, a correlational design measured the relationship between the variables and identified the variables of parental involvement that best predict teachers' self-efficacy, work commitment, and job satisfaction. The results revealed a small negative correlation between parental involvement and self-efficacy. In contrast, communication with parents positively influenced teachers' work commitment. These findings could inform educational policy by fostering collaboration between parents and teachers, thus enhancing the overall educational environment.

INFLUENCE OF ANOMALOUS VALUES ON THE ACCURACY OF FORECASTING LOSSES IN DISTRIBUTION NETWORKS

The relevance of the study is determined by modern trends in managing the operation modes of distribution electrical networks using Smart Grid technologies, as well as the need to reduce the costs incurred by distribution system operators for purchasing electricity. Accurate load forecasting results at network nodes for different forecasting horizons are crucial for this purpose. Sudden changes in network topology can increase the errors in loss forecasts as a single time series, negatively impacting network management efficiency and increasing the costs of electricity procurement to cover losses. The study proposes using forecasting methods based on artificial neural networks for the calculation and prediction of electricity losses, along with a comparison of these methods. The calculations were performed using data from one of Ukraine's distribution system operators, and the test electrical network was adapted based on the CIGRE scheme for modeling electricity losses. Since the nodal load data contained gaps and anomalies, a two-step data analysis algorithm was employed using the DBSCAN clustering method for detection and correction. As a result of loss calculations based on cleaned data, the error was reduced threefold compared to calculations based on load factors. Applying data analysis methods and forecasting methods based on artificial neural networks significantly improves the accuracy of loss calculations and minimizes errors.

Quantum Distance Approximation for Persistence Diagrams

Abstract Topological Data Analysis methods can be useful for classification and clustering
tasks in many different fields as they can provide two dimensional persistence dia-
grams that summarize important information about the shape of potentially complex
and high dimensional data sets. The space of persistence diagrams can be endowed
with various metrics, which admit a statistical structure and allow to use these summaries for machine learning algorithms, e.g. the Wasserstein distance.

However, computing the distance between two persistence diagrams involves finding an opti-
mal way to match the points of the two diagrams and may not always be an easy
task for classical computers. Recently, quantum algorithms have shown the po-
tential to speedup the process of obtaining the persistence information displayed on
persistence diagrams by estimating the spectra of persistent Dirac operators. So,
in this work we explore the potential of quantum computers to estimate the distance
between persistence diagrams as the next step in the design of a fully quantum frame-
work for TDA. In particular we propose variational quantum algorithms for the
Wasserstein distance as well as the dcp distance. Our implementation is a weighted
version of the Quantum Approximate Optimization Algorithm that relies on control
clauses to encode the constraints of the optimization problem.

Soil information system of the Ukrainian Carpathians

The theoretical aspects and practical approaches to the creation of a soil information system on the example of the Ukrainian Carpathians, which is based on the use of vectorised large-scale soil mapping materials and GIS tools, are considered. The study is devoted to the development of a soil information system for the Ukrainian Carpathians, which integrates vectorised large-scale soil maps and GIS technologies to ensure efficient collection, storage and monitoring of soil data. The scientific novelty of the work is the creation of a multi-level information platform that combines data of different granularity and allows monitoring of soil transects, profiles, and genetic horizons, as well as determining spatial relationships between point and polygonal objects. Particular attention was paid to collecting cartographic materials reflecting the soil cover of the Ukrainian Carpathians and formalising the data for further integration into the soil information system. The system supports analytical tools that allow calculating various geometric, physical and chemical parameters of soil objects. The use of modern GIS tools enables accurate monitoring and forecasting of changes in soil cover under the influence of natural and anthropogenic factors, making it an important tool for the rational management of soil resources in the Carpathians. The developed system allows storing and updating information, which ensures its adaptability to changes in data analysis and processing methods. This not only increases the efficiency of monitoring, but also ensures the flexibility of the system for the specific needs of users. The practical significance lies in the possibility of using this system for soil protection, sustainable land management, and environmental safety. Expansion of this system to the entire territory of Ukraine will provide additional opportunities for effective monitoring and forecasting of changes in soil cover on a national scale, contributing to sustainable development and environmental protection. Key words: soil information systems; Ukrainian Carpathians; remote sensing; soil database.

SURGICAL INTERVENTION IN SEVERE POSTPARTUM HAEMORRHAGE

Postpartum haemorrhage (PPH) is one of the major causes of maternal mortality and morbidity, defined as haemorrhage occurring within 24 h of childbirth. Postpartum haemorrhage can be categorized into primary, which takes place within the first one day after childbirth, and secondary, which happens anytime from 24 hours after birth up to six weeks after delivery. Among the cases of PPH, some are severe and fatal and hence need to be treated effectively and on time. Conservative methods are to some extent useful in controlling PPH but surgical management involves the use of special operations to address the problem. Objective: This proposed study aims to finally summarize the evidence about surgical interventions in the management of postpartum haemorrhage, including the effectiveness and side effect profile of various surgical techniques. Methods: This study type used a retrospective cohort design and the sample consisted of patients with severe PPH that needed surgical management. This paper used quantitative data and the data was gathered from the records of hospitals for five years. Some of the surgical management activities considered in the study were uterine artery ligation, B-Lynch suture, and hysterectomy. The variables measured were success rates, early clinical outcomes, late clinical recovery and early complications. Quantitative methods of data analysis used in this study include survival analysis tests and chi-square tests. Results: The study enrolled 150 patients with severe manifested PPH; 60% of the patients underwent uterine artery ligation; 25% of the patients required a B-Lynch suture performed; and 15% of the patients required a hysterectomy. Short-term effects revealed that both techniques provided effective control of bleeding, in 85% of cases did not require additional surgery in the form of a B-Lynch suture. It was also shown that 70% of the cases with uterine artery ligation were associated with long-term preservation of fertility. Hysterectomy had the highest complication rates; infection, organ damage, and higher maternal mortality of 5%. Conclusion: Uterine artery ligation as well as B-Lynch suture should be used in cases of severe PPH because during this procedure no tubal sterilization occurs and fertility can be preserved when selecting the right cases. Although hysterectomy remains the surgical option of choice, the procedure is fraught with some significant risks. The study confirms the necessity for early surgical management and the collaboration of multiple specialists to optimise maternal results in grave cases of PPH. More clinical research is required to optimize surgical approaches and to define the role of non-operative interventions to improve the patient’s prognosis.

Single-cell RNA sequencing in stroke and traumatic brain injury: Current achievements, challenges, and future perspectives on transcriptomic profiling.

Single-cell RNA sequencing (scRNA-seq) is a high-throughput transcriptomic approach with the power to identify rare cells, discover new cellular subclusters, and describe novel genes. scRNA-seq can simultaneously reveal dynamic shifts in cellular phenotypes and heterogeneities in cellular subtypes. Since the publication of the first protocol on scRNA-seq in 2009, this evolving technology has continued to improve, through the use of cell-specific barcodes, adoption of droplet-based systems, and development of advanced computational methods. Despite induction of the cellular stress response during the tissue dissociation process, scRNA-seq remains a popular technology, and commercially available scRNA-seq methods have been applied to the brain. Recent advances in spatial transcriptomics now allow the researcher to capture the positional context of transcriptional activity, strengthening our knowledge of cellular organization and cell-cell interactions in spatially intact tissues. A combination of spatial transcriptomic data with proteomic, metabolomic, or chromatin accessibility data is a promising direction for future research. Herein, we provide an overview of the workflow, data analyses methods, and pros and cons of scRNA-seq technology. We also summarize the latest achievements of scRNA-seq in stroke and acute traumatic brain injury, and describe future applications of scRNA-seq and spatial transcriptomics.

Value System Formation Through Project and Research Activities Part of Science Lessons

More effective methodologies are still needed to achieve a system that can inspire students' interest and motivation and guide them toward science and research. This results in a need for more robust value system formation among students in educational settings. The study's main objective was to develop and implement a value system formation technology for school children in the context of active teaching, focusing on biology education. This research is a qualitative study involving biology teachers and schoolchildren in a school's educational environment. The data collection methods used in this study were interviews, observation, and document analysis. The instrument used was an observation sheet. The data analysis methods used in this research are thematic and content analysis. The results showed that Monakhov's axiom technology effectively increased students' involvement and interest in project and research activities and assisted teachers in achieving educational goals oriented towards the holistic development of students' values. In conclusion, the findings of this study show a significant increase in the number of scientific and research works conducted by students of schools participating in competitions such as DARYN and MAN over the past three years. This research is expected to inform educational policy and curriculum development, promoting the integration of project and research activities to develop individuals with solid scientific thinking, ethical values, and a sense of responsibility towards their environment.

Audit Risks and Countermeasures of Fresh Food E-commerce under the New Retail Model

Driven by the new retail model, the fresh food e-commerce field has witnessed rapid development, attracting numerous enterprises to rush in. However, as the market is gradually becoming saturated and the growth rate is slowing down, the competition among enterprises has become increasingly fierce, and the operating pressure has accordingly increased, which has, to some extent, raised the risk of fraud among fresh food e-commerce enterprises. Under the new retail model, certain changes have taken place in aspects such as the operating environment, business activities, and internal control of fresh food e-commerce, presenting characteristics like multi-channel sales and a large amount of structured and unstructured data. All of these pose certain challenges for auditing. This article analyzes the auditing risks that fresh food-e-commerce has under the new retail model and also discusses the corresponding auditing countermeasures. Because only when auditors have a clear understanding of these risks can they formulate appropriate strategies to deal with them. For example, in the face of complex business models and massive data, auditors need to master advanced auditing techniques and data analysis methods to identify potential risks accurately. Moreover, understanding the internal control changes in fresh food e-commerce enterprises is crucial for auditors to assess whether the existing control systems can effectively prevent and detect possible fraud behaviors, so as to ensure the authenticity and reliability of financial information and safeguard the legitimate rights and interests of stakeholders.

Evaluating a transitional housing program for people who use substances (PWUS) who experience homelessness and live with a mental health issue: a mixed-methods study protocol in Sudbury Ontario

BackgroundA new transitional housing program was established in Sudbury, Ontario, Canada, in response to the escalating global prevalence of substance use and homelessness, and the specific challenges faced in Northern Ontario. This protocol outlines a comprehensive program evaluation to assess its impact on patient outcomes, healthcare utilization, and client perspectives.MethodsWe will conduct a parallel mixed-method study that includes the analysis of single-center-level administrative health data and primary data collection. This includes a longitudinal observational study (target n = 1,200), pre- and post-admission quantitative interviews (target n = 40), and qualitative interviews (target n = 40). We will implement a participatory approach to this evaluation collaborating with people who use substances, frontline staff, and decision-makers. Data analysis methods include a range of statistical techniques, including logistic regression models, Cox proportional hazards models, Kaplan-Meier curves, Generalized Estimating Equations, and thematic qualitative analysis, ensuring a robust evaluation of patient outcomes and healthcare utilization.DiscussionThis protocol underpins a comprehensive assessment aimed at providing insights into the program’s effectiveness in addressing substance use-related challenges, reducing healthcare disparities, and improving patient outcomes, such as stable housing and increased social capital. All study procedures adhere to the ethical principles outlined in the Tri-Council Policy Statement: Ethical Conduct for Research Involving Humans. Findings will be disseminated progressively through established committees and working groups and subsequently published in peer-reviewed journals. Anticipated outcomes include informing evidence-based healthcare decision-making and driving improvements in addiction treatment practices within healthcare settings.

The Low Level of Digital Literacy in Indonesia: An Analysis of Online Media Content

Background of the study: The low level of digital literacy among Indonesians poses a significant challenge in the era of global digitization, particularly due to the lack of access to and understanding of information technology required to make effective use of digital libraries. Purpose: Identify factors causing low digital literacy, evaluate policies that have been implemented, and formulate effective strategies to increase digital library utilization in Indonesia. Method: This study uses a qualitative approach by analyzing online news using the keyword ‘digital literacy’, to explore the factors that lead to low digital literacy in Indonesia. Data analysis methods included coding, theme building, data reduction, and data display to identify patterns and reasons behind this phenomenon. Findings: This research reveals that Indonesia's low digital literacy is caused by a lack of infrastructure, a lack of educational focus, and low awareness of social media ethics. Collaboration between the government, academic institutions, and society is needed through technology investment, education reform, and awareness campaigns. Conclusion: Recommended follow-up includes training, digital infrastructure development, and effective awareness campaigns to improve digital literacy in Indonesia.

Особенности организации оказания медицинской помощи в частных медицинских организациях дерматологического профиля.

The population’s need for dermatological care requires the creation of a new level of organization of medical care based on medical information systems capable of improving the activities of private medical organizations and improving the quality of services provided in the dermatological profile. Purpose of the study is to reveal the features and directions of the formation of high–quality dermatological care in private medical organizations. Materials and methods. In the process of achieving this goal, statistical data, legislation, and the medical information system were studied. Methods of observation, generalization, comparison, grouping, and data analysis were used. Subject. An algorithm for organizing dermatological medical care, focused on improving quality through the introduction of a narrowly specialized medical information system. Results. The basic algorithms for the implementation of a medical information system for a private clinic of a dermatological profile based on the construction of a scheme of medical and social characteristics of dermatological diseases and focused on nosological forms of the most common etiologies are proposed. A distinctive feature of the organization of the provision of medical services by private dermatological clinics is the quality, which allows not only to provide a highly effective service to the population, but also to gain a competitive advantage in the market. In the process of development and implementation, the basic principles of an information system focused on achieving the set goals were determined. The version of the medical information system implemented in practice, based on the research materials, made it possible to integrate. Conclusion. The specific features of the implementation of a narrowly specialized medical information system in private medical organizations are determined. Directions of improvement have been formed within the framework of the state implementation of a common electronic database of patients through EGISZ.

Implementation of the Village Fund Allocation (ADD) Management Policy in Kon Tumere Village, Kabawo Sub-district, Muna Regency

Village, Kabawo District, Muna Regency and to find out the factors that influence the Implementation of the Village Fund Allocation Policy (ADD). In this research, data collection was carried out in the following way, collecting data or information through: observation, semi-structured interviews (open interviews), documentation. Data analysis methods include data reduction, data presentation, and drawing conclusions. When viewed from the perspective of achieving objectives, the results of this research can be concluded that the implementation of the Village Fund Allocation Policy in Kontumere Village, Kabawo District, Muna District has not been achieved comprehensively or optimally. This is influenced by several inhibiting factors, namely (1) communication, the inhibiting factor in this communication is socialization to the public regarding the non-existent ADD policy (weakness). This results in the difficulty of inviting community participation in implementing ADD and in monitoring activities (treatment/threats). (2) resources, lack of ability of implementers to operate computers (Weakness), and lack of adequate village income support (Treatment/Threat), (3) Attitude of Implementers, The inhibiting factor in the attitude of implementers is the lack of responsiveness of ADD implementers ( Weakness/Weakness) which considers the ADD policy to be a mere routine policy (Treatment/Threat). (4) Bureaucratic structure, namely the lack of coordination between policy implementers.

Functional Concurrent Regression Mixture Models Using Spiked Ewens-Pitman Attraction Priors.

Functional concurrent, or varying-coefficient, regression models are a form of functional data analysis methods in which functional covariates and outcomes are collected concurrently. Two active areas of research for this class of models are identifying influential functional covariates and clustering their relations across observations. In various applications, researchers have applied and developed methods to address these objectives separately. However, no approach currently performs both tasks simultaneously. In this paper, we propose a fully Bayesian functional concurrent regression mixture model that simultaneously performs functional variable selection and clustering for subject-specific trajectories. Our approach introduces a novel spiked Ewens-Pitman attraction prior that identifies and clusters subjects' trajectories marginally for each functional covariate while using similarities in subjects' auxiliary covariate patterns to inform clustering allocation. Using simulated data, we evaluate the clustering, variable selection, and parameter estimation performance of our approach and compare its performance with alternative spiked processes. We then apply our method to functional data collected in a novel, smartphone-based smoking cessation intervention study to investigate individual-level dynamic relations between smoking behaviors and potential risk factors.

Constructing phylogenetic trees for microbiome data analysis: A mini-review

As next-generation sequencing technologies advance rapidly and the cost of metagenomic sequencing continues to decrease, researchers now face an unprecedented volume of microbiome data. This surge has stimulated the development of scalable microbiome data analysis methods and necessitated the incorporation of phylogenetic information into microbiome analysis for improved accuracy. Tools for constructing phylogenetic trees from 16S rRNA sequencing data are well-established, as the highly conserved regions of the 16S gene are limited, simplifying the identification of marker genes. In contrast, metagenomic and whole genome shotgun (WGS) sequencing involve sequencing from random fragments of the entire gene, making identification of consistent marker genes challenging owing to the vast diversity of genomic regions, resulting in a scarcity of robust tools for constructing phylogenetic trees. Although bacterial sequence tree construction tools exist for upstream bioinformatics, many downstream researchers—those integrating these trees into statistical models or machine learning—are either unaware of these tools or find them difficult to use due to the steep learning curve of processing raw sequences. This is compounded by the fact that public datasets often lack phylogenetic trees, providing only abundance tables and taxonomic classifications. To address this, we present a comprehensive review of phylogenetic tree construction techniques for microbiome data (16S rRNA or whole-genome shotgun sequencing). We outline the strengths and limitations of current methods, offering expert insights and step-by-step guidance to make these tools more accessible and widely applicable in quantitative microbiome data analysis.

Features of the chemical composition of water in lake Ebeyty Omsk region and characteristics of soil cover

Relevance. Lake Ebeyty is the largest salt lake in the Omsk region, located in the south-west of the region, at the junction of the borders of three regions: Poltava, Moskalensky and Isilkulsky, and has huge reserves of medicinal mud. The purpose of the research is to study the characteristics of the chemical composition of Lake Ebeyty water over the years of research (data from 2011, 2019, 2022 and 2023) and soil cover.Material and Methodology. The paper presents the results of studies of the chemical composition of the water of Lake Ebeyty in the period 2011-2019-2022-2023. In this work, satellite data analysis methods were used to identify relief features and changes in the area of the water surface (archive of satellite images for 10 years) of the study area in the QGIS software product. Water samples were taken during the daytime for chemical analysis using generally accepted methods.Results. An assessment of the ecological state of the lake was carried out. As a result of the research, it was established: an increase in oxidation from 53.04 mgO2/l in 2011 to 208.0 mgO2/l in 2022, in 2023 the figure decreases to 150.4 mgO2/l, which indicates a deterioration in the ecological situation of the water body. Mineralization increases over the years of research from 128054 to 268691 mg/l (respectively). The soil cover is rep-resented by soils of the saline series - solonchaks and solonetzes.

Pengaruh Literasi Keuangan, Sikap Keuangan, dan Gaya Hidup Terhadap Pengelolaan Keuangan Pribadi Mahasiswa Perguruan Tinggi

This study aims to analyze the influence of financial literacy, financial attitudes, and lifestyle on personal financial management among university students in West Jakarta. Using a quantitative associative causal approach, primary data were collected through an online questionnaire with a Likert scale. The data analysis methods included descriptive statistics, data quality tests, classical assumption tests, multiple linear regression, and hypothesis testing. The results of the study indicate that simultaneously, financial literacy, financial attitudes, and lifestyle have a significant influence on personal financial management among students. However, partial analysis reveals that only financial attitudes and lifestyle have a positive and significant impact, while financial literacy does not show a significant influence on personal financial management.

Investigating the Influence Factors of Quality of Life in Thyroid Eye Disease: Insights from Machine Learning Approaches.

Thyroid eye disease (TED) is an autoimmune orbital disorder that diminishes the quality of life (QOL) for affected individuals. The Graves' ophthalmopathy (GO)-QOL questionnaire effectively assesses TED's impact on patients. This study aims to investigate factors influencing visual functioning (QOL-VF) and physical appearance (QOL-AP) scores in Chinese TED patients using innovative data analysis methods. This cross-sectional study included 211 TED patients whose initial visit to our clinic was from July 2022 to March 2023. Patients with previous ophthalmic surgery or concurrent severe diseases were excluded. GO-QOL questionnaires, detailed medical histories, and clinical examinations were collected. The distribution of GO-QOL scores was analyzed, and linear regression and machine learning algorithms were utilized. The median QOL-VF and QOL-AP scores were 64.29 and 62.5, respectively. Multivariate linear regression analysis revealed age (p=0.013), ocular motility pain (p=0.012), vertical strabismus (p<0.001), and diplopia scores as significant predictors for QOL-VF. For QOL-AP, gender (p=0.013) and clinical activity (p=0.086) were significant. The XGBoost model demonstrated superior performance, with an R2 of 0.872 and an Root Mean Square Error (RMSE) of 11.083. SHapley Additive exPlanations (SHAP) analysis highlighted the importance of vertical strabismus, diplopia score, and age in influencing QOL-VF, and age, clinical activity, and sex in QOL-AP. TED significantly impacts patient QOL. The study highlights the efficacy of XGBoost and SHAP analyses in identifying key factors influencing QOL in TED patients. Identifying impactful interventions and considering specific demographic characteristics are essential to improving the QOL of patients with TED.

Enhancing precision nitrogen management for cotton cultivation in arid environments using remote sensing techniques

Context or problemRemote sensing, particularly through unmanned aerial vehicles (UAVs), has emerged as a pivotal tool in precision agriculture, especially for nitrogen (N) management. Traditional methods, while effective in quantifying crop N status using the Nitrogen Nutrition Index (NNI), fall short in providing quantitative fertilization strategies. MethodsThis study bridges this gap by developing a comprehensive method that leverages multispectral remote sensing data from UAVs to refine N fertilizer management in cotton cultivation within arid environments. By integrating both field observations and UAV-derived multispectral data, we established robust models capable of estimating both leaf and overall cotton nitrogen contents (CNC-leaf and CNC-all), as well as NNI, throughout the growing season. This facilitated real-time calculation of required N fertilizer doses in cotton fields. ResultsWe uniquely applied covariance diagnosis and full subset screening techniques, underscoring the efficacy of vegetation index categories (VIs) in enhancing prediction accuracy. The Random Forest (RF) model exhibited superior performance in predicting plant nitrogen content, particularly in CNC-leaf prediction (Calibration: R²=0.92, RMSE=7.7 g m⁻², MAE=5.5 g m⁻²; Validation: R²=0.60, RMSE=16.5 g m⁻², MAE=12.2 g m⁻²) as opposed to CNC-all prediction (Calibration: R²=0.78, RMSE=117.0 g m⁻², MAE=154.3 g m⁻²; Validation: R²=0.34, RMSE=138.4 g m⁻², MAE=190.4 g m⁻²). The RF model also demonstrated optimal performance in NNI prediction (Calibration: R²=0.93, RMSE=0.05, MAE=0.04; Validation: R²=0.73, RMSE=0.12, MAE=0.10), surpassing the predictions for CNC. ConclusionsUtilizing CNC and NNI estimates derived from the optimized RF model, this study succeeded in generating a comprehensive map detailing the N fertilizer requirement across cotton Fertilization zones were established for different treatments, revealing that biochar application levels primarily determine nitrogen fertilizer needs. As biochar application increases, nitrogen fertilizer demand decreases. Moreover, nitrogen application rates typically increase when irrigation levels reach either 120 % ETc or 60 % ETc. Implications or significanceThis innovative approach not only empowers farmers with intuitive and accurate tools for real-time cotton N management but also fosters enhanced agricultural practices by integrating advanced remote sensing technologies with sophisticated data analysis methods. The findings of this study have significant implications for sustainable and efficient agricultural practices, particularly in arid regions, setting a new precedent in precision nitrogen management.