Artificial Gradient Research Articles

Effects of Artificial Soil Fertility Gradient Strategy on the Soil Fertility, Nutrient Uptake and Growth Attributes of Chakravarthi Keerai (Chenopodium album)

The effect of artificial soil fertility gradient techniques on crop growth attributes, nutrient uptake, soil fertility and soil biological properties were studied in a field trial conducted in 2023 at Horticulture Research Station, Ooty, Nilgiris, Tamil Nadu. It was done using an inductive methodology. The field was split into three equal strips, with three graded levels of fertilizers viz., N (Urea), P2O5 (Single Super phosphate) and K2O (Muriate of Potash) applied to strip I (N0P0K0), II (N1P1K1) and III (N2P2K2). The N1 level has been determined on the basis of the blanket recommendation to Chakravarthi keerai, while the P1 and the K1 levels have been determined based on the fixing capacity of the soil phosphorus (250 kg ha-1) and the potassium (100 kg ha-1). Gradient crop, Chakravarthi keerai variety Ooty 1 was cultivated and green yield of Chakravarthi keerai was observed at the time of harvesting. At the time of harvesting, plant samples were taken and examined for N, P & K content and the uptake of N, P & K was calculated. The results showed that graded levels of fertilizer N, P2O5, K2O had a significant impact on soil fertility status and NPK uptake, as well as plant growth parameter. The article clearly shows a significant influence of the organic carbon, chlorophyll content, soil enzymes activity, microbial population, and Microbial biomass carbon.

Risk prediction of computer investment database information management system based on machine learning algorithms

In recent years, with the continuous development of the financial market, the risk prediction of computer investment database information management systems (IMS) has high practical value. At present, there are risk issues in the information management system, which may cause drawbacks to investment data processing. To address these issues, this article used Machine Learning (ML) algorithms to analyze the risk prediction of computer investment database IMS. This article introduced and utilized typical Self-Organizing Map (SOM) and Artificial Neural Network (ANN) combination algorithms, regression algorithms, and Gradient Boosting Decision Tree (GBDT) algorithms to compare and analyze the prediction accuracy of these three algorithms. This article found that the GBDT algorithm has the highest prediction accuracy. Through a large amount of experimental data, it has been proven that the average testing accuracy using regression algorithms was 3.5% higher than that using neural network algorithms. It was found that the average test accuracy using the GBDT algorithm was 7.2% higher than the average test accuracy using the regression algorithm. The study also explores the combination of physiological and behavioral data collected by wearable devices to provide more comprehensive risk assessment and decision support, which provides an important reference for the optimization of enterprise risk management. Through this innovative data source integration, this paper provides a new perspective for the application and development of machine learning algorithms in computer investment database IMS.

Predicting Deep Venous Thrombosis Using Artificial Intelligence: A Clinical Data Approach.

Deep venous thrombosis is a critical medical condition that occurs when a blood clot forms in a deep vein, usually in the legs, and can lead to life-threatening complications such as pulmonary embolism if not detected early. Hospitalized patients, especially those with immobility or post-surgical recovery, are at higher risk of developing deep venous thrombosis, making early prediction and intervention vital for preventing severe outcomes. In this study, we evaluated the following eight machine learning models to predict deep venous thrombosis risk: logistic regression, random forest, XGBoost, artificial neural networks, k-nearest neighbors, gradient boosting, CatBoost, and LightGBM. These models were rigorously tested using key metrics, including accuracy, precision, recall, F1-score, specificity, and receiver operating characteristic curve, to determine their effectiveness in clinical prediction. Logistic regression emerged as the top-performing model, delivering high accuracy and an outstanding receiver operating characteristic curve score, which reflects its strong ability to distinguish between patients with and without deep venous thrombosis. Most importantly, the model's high recall underscores its ability to identify nearly all true deep venous thrombosis cases, significantly reducing the risk of false negatives-a critical concern in clinical settings, where delayed or missed diagnoses can result in life-threatening complications. Although models such as random forest and eXtreme Gradient Boosting also demonstrated competitive performances, logistic regression proved the most reliable across all metrics. These results suggest that machine learning models, particularly logistic regression, have great potential for early deep venous thrombosis detection, enabling timely clinical interventions and improved patient outcomes.

Machine Learning and Cointegration for Wind Turbine Monitoring and Fault Detection: From a Comparative Study to a Combined Approach

Data-driven models have become powerful tools for structural and condition monitoring of engineering systems, particularly wind turbines. This paper presents a comparative analysis of common machine learning (ML) algorithms (artificial neural networks, linear regression, random forests, and gradient boosting) and a cointegration-based approach for fault detection using Supervisory Control and Data Acquisition (SCADA) data. While ML models offer early fault prediction, the cointegration method is simpler, requires less training data, and has lower computational costs. However, it is less effective for early detection. To balance these trade-offs, we propose a cascading monitoring framework, where the ML model provides long-term predictions (outer monitoring process) and the cointegration model offers short-term verification (inner monitoring process). The cointegration model serves to confirm anomalies flagged by the ML model. By combining both models in a cascade structure, the system reduces the risk of false alarms triggered by uncertainties in the ML model alone. Furthermore, the short-term cointegration-based prediction model helps pinpoint immediate risks and mitigate the issue of prolonged downtime. This combination enhances both accuracy and reliability, as demonstrated through testing on a five-year SCADA dataset from a commercial wind turbine with a known gearbox fault.

Comprehensive Analysis of Bile Medicines Based on UHPLC-QTOF-MSE and Machine Learning.

Based on UHPLC-QTOF-MSE analysis and quantized processing, combined with machine learning algorithms, data modeling was carried out to realize digital identification of bear bile powder (BBP), chicken bile powder (CIBP), duck bile powder (DBP), cow bile powder (CBP), sheep bile powder (SBP), pig bile powder (PBP), snake bile powder (SNBP), rabbit bile powder (RBP), and goose bile powder (GBP). First, 173 batches of bile samples were analyzed by UHPLC-QTOF-MSE to obtain the retention time-exact mass (RTEM) data pair to identify bile acid-like chemical components. Then, the data were modeled by combining support vector machine (SVM), random forest (RF), artificial neural network (ANN), gradient boosting (GB), AdaBoost (AB), and Naive Bayes (NB), and the models were evaluated by the parameters of accuracy (Acc), precision (P), and area under the curve (AUC). Finally, the bile medicines were digitally identified based on the optimal model. The results showed that the RF model constructed based on the identified 12 bile acid-like chemical constituents and random forest algorithm is optimal with ACC, P, and AUC > 0.950. In addition, the accuracy of external identification verification of 42 batches of bile medicines detected at different times is 100.0%. So based on UHPLC-QTOF-MSE analysis and combined with the RF algorithm, it can efficiently and accurately realize the digital identification of bile medicines, which can provide reference and assistance for the quality control of bile medicines. In addition, hyodeoxycholic acid, glycohyodeoxycholic acid, and taurochenodeoxycholic acid, and so forth are the most important bile acid constituents for the identification of nine bile medicines.

Analyzing Supervised Machine Learning Models for Classifying Astronomical Objects Using Gaia DR3 Spectral Features

In this paper, we present an analysis of the effectiveness of various machine learning algorithms in classifying astronomical objects using data from the third release (DR3) of the Gaia space mission. The dataset used includes spectral information from the satellite’s red and blue spectrophotometers. The primary goal is to achieve reliable classification with high confidence for symbiotic stars, planetary nebulae, and red giants. Symbiotic stars are binary systems formed by a high-temperature star (a white dwarf in most cases) and an evolved star (Mira type or red giant star); their spectra varies between the typical for these objects (depending on the orbital phase of the object) and present emission lines similar to those observed in PN spectra, which is the reason for this first selection. Several classification algorithms are evaluated, including Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), Gradient Boosting (GB), and Naive Bayes classifier. The evaluation is based on different metrics such as Precision, Recall, F1-Score, and the Kappa index. The study confirms the effectiveness of classifying the mentioned stars using only their spectral information. The models trained with Artificial Neural Networks and Random Forest demonstrated superior performance, surpassing an accuracy rate of 94.67%.

Lateral Heterostructures Fabricated via Artificial Pressure Gradient.

Hydrostatic conditions are generally pursued in high-pressure research, maintained to prevent the intrinsic pressure gradient on the culets of diamond anvil cells (DACs) from introducing heterogeneity to the structure and physical properties of the regulated materials. Here, a pioneering route to fabricate lateral heterostructures is proposed via artificial pressure gradients intentionally designed in DACs. Under the tailored pressure gradients, different structural phases emerge in distinct parts of the material, resulting in the formation of heterostructures. Harnessing the polymorphic transition nature of violet phosphorus under high pressure, violet/blue and violet/black phosphorus lateral heterostructures with different electrical properties have been successfully prepared by the pressure gradient method. This achievement highlights the potential of artificial pressure gradients as a portable and universal strategy for the fabrication of lateral heterostructures, shedding new light on the preparation and regulation of lateral heterostructures across a wider range of materials.

Feature Selection Based on Artificial Bee Colony and Gradient Boosting Decision Tree for Hotel Reservation Cancellation Prediction Using Random Forest

This study focuses on predicting hotel booking cancellations using machine learning to improve accuracy and operational efficiency. The methods used include Random Forest, Artificial Bee Colony (ABC), and Gradient Boosting Decision Tree (GBDT). ABC, which excels in optimization but is prone to local optima, is combined with GBDT for feature selection. The dataset used is Hotel_Bookings from Kaggle, with 119,390 entries and 28 features. The data is processed through cleansing, normalization, and split into 75% for training and 25% for testing. Feature selection is performed using ABC and GBDT, and the prediction model is built using Random Forest. Model evaluation using confusion matrix and metrics like precision, recall, f1-score, and accuracy shows accuracies of 86.17% and 86.65% for ABC and GBDT, respectively. Increasing the number of trees and features generally improves model performance, with feature selection showing significant performance improvements compared to models without feature selection.

Crystalline phase control of ferroelectric HfO2 thin film via heterogeneous co-doping

Our study investigates heterogeneous co-doped HfO2 thin films integrated into metal-ferroelectric-metal stacks, achieved by incorporating multiple layers doped with various species during the atomic layer deposition process. This approach creates an artificial crystallization temperature gradient across the HfO2 film, influencing the preferred nucleation sites of HfO2 during rapid thermal processing. Our findings demonstrate that the phase composition of the annealed HfO2 film is primarily determined by heterogeneous or homogeneous crystallization processes. In cases of heterogeneous crystallization, where crystallization initiates from nuclei formed at electrode/HfO2 interfaces, grains predominantly crystallize in the orthorhombic phase. Conversely, grains are more likely to crystallize in the monoclinic phase if they originate from nuclei formed at the center of the HfO2 film. Additionally, we observe correlations between the texture of the HfO2 film and the texture of the electrodes.

Diagnosis of Lung Cancer Through Exhaled Breath: A Comprehensive Study.

Exhaled breath analysis is an attractive lung cancer diagnostic tool. However, various factors that are not related to the disease status, comorbidities, and other diseases must be considered to obtain a reliable diagnostic model. Exhaled breath samples from 646 individuals including 273 patients with lung cancer (LC), 90 patients with cancer of other localizations (OC), 150 patients with noncancer lung diseases (NLD), and 133 healthy controls (HC) were analyzed using gas chromatography-mass spectrometry (GC-MS). The samples were collected in Tedlar bags. Volatile organic compounds (VOCs) were preconcentrated on Tenax TA sorbent tubes with subsequent two-stage thermal desorption followed by GC-MS analysis. The influence of age, gender, smoking status, time since last food consumption, and comorbidities on exhaled breath were evaluated. Also, the effect of histology, TNM, tumor localization, treatment status, and the presence of a tumor on VOC profile of patients with lung cancer were assessed. Intergroup statistics were estimated, diagnostic models were created using artificial neural networks (ANNs) and gradient boosted decision trees (GBDTs). Smoking status and food consumption affect exhaled breath VOC profile: benzene, ethylbenzene, toluene, 1,3-pentadiene 1,4-pentadiene acetonitrile, and some ratios are significantly different in exhaled breath of smokers and nonsmokers; the ratios 2,3-butandione/2-pentanone, 2,3-butandione/dimethylsulfide, and 2-butanone/2-pentanone are affected by time since last food consumption. Exhaled breath of LC is affected by the form of the disease and comorbidities. One-pentanol and 2-butanone were different in exhaled breath of patients with various tumor localization; 2-butanone was different in exhaled breath of patients before and during treatment. Diabetes as a comorbidity affects the pentanal level in exhaled breath; obesity affects the ratios of 2,3-butanedione/dimethylsulfide and 2-butanone/isoprene. Sensitivity and specificity of diagnostic models aimed to discriminate LC and HC, OC, and NLD were 78.7% and 51.0%, 62.2% and 53.4%, and 60.4% and 58.0%, respectively. HC and patients, regardless of the disease, can be classified with sensitivity of 76.6% and specificity of 68.2%. The models created to diagnose lung cancer can also classify OC and NLD as patients with lung cancer. Additionally, the influence of comorbidities and factors not related to the disease status must be considered before the creation of diagnostic models to avoid false results.

A novel hybrid ANN-GB-LR model for predicting oil and gas production rate

The Oil and Gas Production Rate (OGPR) is one of the most significant processes that play an essential role in the oil industry. Predicting OGPR is critical for effective reservoir management and enhancing oil recovery. Traditional methods (TMs) and numerical simulations (NS) often struggle to process and analyze nonlinear, complex, and massive datasets. To avoid these challenges, artificial intelligence (AI) techniques and machine learning (ML) models have been proposed as an alternative solution due to their high efficiency and rapidity in handling complex data. In this study, a new hybrid model is developed by combining the strengths of Artificial Neural Networks (ANN) and Gradient Boosting (GB), using Linear Regression (LR) as a meta-model by stacking technique. It captures nonlinear relationships effectively and manages outliers, enhancing prediction accuracy. The novelty of this study lies in the hybrid ANN-GB-LR model's ability to integrate various machine learning techniques into a robust framework, leveraging the high learning capacity of ANN, the robust handling of outliers by GB, and the straightforward interpretability of LR. This creative combination handles the limitations of individual models and enhances the general predictive performance. The model was trained and tested using actual field data from the Halewah field in Yemen. Evaluation metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2), were utilized to evaluate and compare the hybrid model with other ML models: Random Forest (RF), XGBoost (XGB), LR, Light Gradient Boosting Machine (LGBM), GB, and K-nearest neighbors (KNN). The hybrid ANN-GB-LR model achieved superior results, with an R2 of 0.998, an RMSE of 11.06 for oil flow rate predictions, and an R2 of 0.98 and an RMSE of 172.15 for gas flow rate predictions. These results significantly surpass the other models, demonstrating the hybrid model's outstanding ability to capture complex data and provide accurate predictions. The ANN-GB-LR model surpasses Traditional Methods in predicting OGPRs. It shows a strong and reliable tool for optimizing reservoir management. This study establishes a new standard for predictive modeling in the oil industry, providing a framework for future research to apply hybrid models in handling complex datasets.

Use of interpretable machine learning approaches for quantificationally understanding the performance of steel fiber-reinforced recycled aggregate concrete: From the perspective of compressive strength and splitting tensile strength

In this study, four machine learning (ML) algorithms, namely Support Vector Machine (SVM), Back-propagation Artificial Neural Network (BP-ANN), Adaptive Boosting (AdaBoost), and Gradient Boosted Regression Tree (GBRT), were employed to conduct an in-depth analysis of the global estimation model of the compressive strength and splitting tensile strength of steel fiber recycled aggregate concrete (SFR-RAC). A database containing 465 compressive strength sets and 339 splitting tensile strength sets with different mix proportions was established, and the ML model was trained and tested in combination with Bayesian optimization. The effects of multiple components on the strength of SFR-RAC were studied using partial correlation analysis and SHapley Additive exPlanations (SHAP) analysis. The results showed that AdaBoost and GBRT performed well according to the evaluation indicators, and the deviation between the predicted data and the actual data remained within 20%. The developed models were quantitatively analyzed to study the relationship between characteristics and compressive/splitting tensile strengths, and recommendations were given for key parameters in the SFR-RAC mix proportion. This study suggests improving the modeling accuracy by further incorporating out-of-range data and features for future research.

Toward a Digital Twin of a Solid Oxide Fuel Cell Microcogenerator: Data-Driven Modelling

Solid oxide fuel cells (SOFC) could facilitate the green energy transition as they can produce high-temperature heat and electricity while emitting only water when supplied with hydrogen. Additionally, when operated with natural gas, these systems demonstrate higher thermoelectric efficiency compared to traditional microturbines or alternative engines. Within this context, although digitalisation has facilitated the acquisition of extensive data for precise modelling and optimal management of fuel cells, there remains a significant gap in developing digital twins that effectively achieve these objectives in real-world applications. Existing research predominantly focuses on the use of machine learning algorithms to predict the degradation of fuel cell components and to optimally design and theoretically operate these systems. In light of this, the presented study focuses on developing digital twin-oriented models that predict the efficiency of a commercial gas-fed solid oxide fuel cell under various operational conditions. This study uses data gathered from an experimental setup, which was employed to train various machine learning models, including artificial neural networks, random forests, and gradient boosting regressors. Preliminary findings demonstrate that the random forest model excels, achieving an R2 score exceeding 0.98 and a mean squared error of 0.14 in estimating electric efficiency. These outcomes could validate the potential of machine learning algorithms to support fuel cell integration into energy management systems capable of improving efficiency, pushing the transition towards sustainable energy solutions.

Alpine viper in changing climate: thermal ecology and prospects of a cold-adapted reptile in the warming Mediterranean

In a rapidly changing thermal environment, reptiles are primarily dependent on in situ adaptation because of their limited ability to disperse and the restricted opportunity to shift their ranges. However, the rapid pace of climate change may surpass these adaptation capabilities or elevate energy expenditures. Therefore, understanding the variability in thermal traits at both individual and population scales is crucial, offering insights into reptiles' vulnerability to climate change. We studied the thermal ecology of the endangered Greek meadow viper (Viperagraeca), an endemic venomous snake of fragmented alpine-subalpine meadows above 1600 m of the Pindos mountain range in Greece and Albania, to assess its susceptibility to anticipated changes in the alpine thermal environment. We measured preferred body temperature in artificial thermal gradient, field body temperatures of 74 individuals in five populations encompassing the entire geographic range of the species, and collected data on the available of temperatures for thermoregulation. We found that the preferred body temperature (Tp) differed only between the northernmost and the southernmost populations and increased with female body size but did not depend on sex or the gravidity status of females. Tp increased with latitude but was unaffected by the phylogenetic position of the populations. We also found high accuracy of thermoregulation in V.graeca populations and variation in the thermal quality of habitats throughout the range. The overall effectiveness of thermoregulation was high, indicating that V.graeca successfully achieves its target temperatures and exploits the thermal landscape. Current climatic conditions limit the activity period by an estimated 1278 h per year, which is expected to increase considerably under future climate scenarios. Restricted time available for thermoregulation, foraging and reproduction will represent a serious threat to the fitness of individuals and the persistence of populations in addition to habitat loss due to mining, tourism or skiing and habitat degradation due to overgrazing in the shrinking mountaintop habitats of V.graeca.

A protet-based model that can account for energy coupling in oxidative and photosynthetic phosphorylation

Two-stage (e.g. light-dark) phosphorylation experiments showed that there is a stored ‘high-energy’ intermediate linking electron transport and phosphorylation. Large, artificial electrochemical proton gradients (protonmotive forces or pmfs) can also drive phosphorylation, a fact seen as strongly supportive of the chemiosmotic coupling hypothesis that a pmf is the ‘high-energy’ intermediate. However, in such experiments there is an experimental threshold (pmf >170 mV, equivalent to ΔpH ∼2.8) below which no phosphorylation is in fact observed, and 220 mV are required to recreate in vivo rates. This leads to the correct question, which is then whether those values of the pmf generated by electron transport are large enough. Even the lower ones as required for any phosphorylation (leave alone those required to explain in vivo rates) are below the threshold [1, 2], whether measured directly with microelectrodes or via the use of membrane-permeant ions and/or acids/bases (which are always transporter substrates [3], so all such measurements are in fact artefactual). The single case that seemed large enough (220 mV) is now admitted to be a diffusion potential artefact [4]. Many other observables (inadequate bulk H+ in ‘O2-pulse’-type experiments, alkaliphilic bacteria, dual-inhibitor titrations, uncoupler-binding proteins, etc.) are consistent with the view that values of the pmf, and especially of Δψ, are actually very low. A protet-based charge separation model [2], a protonic version analogous to how energy may be stored in devices called electrets, provides a high-energy intermediate that can explain the entire literature, including the very striking demonstration [5] that close proximity is required between electron transport and ATP synthase complexes for energy coupling between them to allow phosphorylation to occur. A chief purpose of this article is thus to summarise the extensive and self-consistent literature, much of which is of some antiquity and rarely considered by modern researchers, despite its clear message of the inadequacy of chemiosmotic coupling to explain these phenomena.

Predicting the Risk of Severity and Readmission in Patients with Heart Failure in Indonesia: A Machine Learning Approach.

In Indonesia, the poor prognosis and high hospital readmission rates of patients with heart failure (HF) have yet to receive focused attention. However, machine learning (ML) approaches can help to mitigate these problems. We aimed to determine which ML models best predicted HF severity and hospital readmissions and could be used in a patient self-monitoring mobile application. In a retrospective cohort study, we collected the data of patients admitted with HF to the Siloam Diagram Heart Center in 2020, 2021, and 2022. Data was analyzed using the Orange data mining classification method. ML support algorithms, including artificial neural network (ANN), random forest, gradient boosting, Naïve Bayes, tree-based models, and logistic regression were used to predict HF severity and hospital readmissions. The performance of these models was evaluated using the area under the curve (AUC), accuracy, and F1-scores. Of the 543 patients with HF, 3 (0.56%) were excluded due to death on admission. Hospital readmission occurred in 138 patients (25.6%). Of the six algorithms tested, ANN showed the best performance in predicting both HF severity (AUC = 1.000, accuracy = 0.998, F1-score = 0.998) and readmission for HF (AUC = 0.998, accuracy = 0.975, F1-score = 0.972). Other studies have shown variable results for the best algorithm to predict hospital readmission in patients with HF. The ANN algorithm performed best in predicting HF severity and hospital readmissions and will be integrated into a mobile application for patient self-monitoring to prevent readmissions.

AI-Driven Prediction and Mapping of Soil Liquefaction Risks for Enhancing Earthquake Resilience in Smart Cities

In response to increasing urbanization and the need for infrastructure resilient to natural hazards, this study introduces an AI-driven predictive model designed to assess the risk of soil liquefaction. Utilizing advanced ensemble machine learning techniques, the model integrates geotechnical and geographical data to accurately predict the potential for soil liquefaction in urban areas, with a specific focus on Yokohama, Japan. This methodology leverages comprehensive datasets from geological surveys and seismic activity to enhance urban planning and infrastructure development in smart cities. The primary outputs include detailed soil liquefaction risk maps that are essential for effective urban risk management. These maps support urban planners and engineers in making informed decisions, prioritizing safety, and promoting sustainability. The model employs a robust combination of artificial neural networks and gradient boosting decision trees to analyze and predict data points, assessing soil susceptibility to liquefaction during seismic events. Notably, the model achieves high accuracy in predicting soil classifications and N-values, which are critical for evaluating soil liquefaction risk. Validation against an extensive dataset from geotechnical surveys confirms the model’s practical effectiveness. Moreover, the results highlight the transformative potential of AI in enhancing geotechnical risk assessments and improving the resilience of urban areas against natural hazards.

A Comparative Analysis of Machine Learning Approaches for Evaluating the Compressive Strength of Pozzolanic Concrete

This study leverages machine learning techniques to predict pozzolanic concrete's compressive strength accurately. Using artificial neural networks (ANN), random forest (RF), and gradient boosting regressor (GBR) models trained on a dataset of 482 samples, the study divides the data into 70% training and 30% testing subsets with seven input parameters. Model performance is assessed through metrics like coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The RF model excels, achieving R2 values of 0.976 in training and 0.964 in testing, along with the lowest RMSE (2.84 MPa) and MAE (2.05 MPa) during training and RMSE values of 7.81 MPa and MAE values of 5.89 MPa during testing, demonstrating superior predictive accuracy. Sensitivity analysis highlights the pivotal role of cement as an input parameter, contributing significantly to the model's accuracy. Employing K-fold cross-validation confirms the RF model's robustness with an average R2 value of 0.959. This research underscores the RF model's reliability and effectiveness in forecasting pozzolanic concrete compressive strength, with practical applications for concrete optimization and construction practices, establishing it as the preferred choice compared to other machine learning models. IUBAT Review—A Multidisciplinary Academic Journal, 7(1): 90-122

From Tweets to Energy Trends (TwEn): An exploratory framework for machine learning-based forecasting of urban-scale energy behavior leveraging social media data

Understanding energy behavior is crucial in addressing climate change, yet the accuracy of energy predictions is often limited by reliance on oversimplified occupancy data. This study develops an exploratory framework, from Tweets to Energy Trends (TwEn), leveraging machine learning and geo-tagged social media data to investigate the social dynamics of urban energy behavior. TwEn explores the relationship between social media interactions, specifically the frequency of tweets using data from the X Platform, and energy use patterns on an hourly basis. Employing various machine learning models, including artificial neural networks (ANN), decision tree (DTREE), random forest (RDF), and gradient boosting machine (GBM), the study evaluates their efficiency in both static and time-series forecasting of energy use trends and investigates the capability of social media data in predicting urban energy patterns. In addition, the study carries out a series of sensitivity analyses to provide an examination of the data and models. Furthermore, comprehensive data acquisition methods are developed and implemented. Tested on New York City using actual hourly electricity consumption data, the framework demonstrates significant predictive power of tweet frequency on urban electricity use. The framework also exhibits significant seasonality in X data, identifying patterns and trends that can inform time series urban building energy models (UBEM). The results offer new insights into the determinants of urban energy behavior and provide crucial perspectives for augmenting UBEMs, ensuring they are closely aligned with the complex social dynamics of contemporary urban environments. By integrating both digital and physical data, this study sheds light on urban energy behavior, supporting the formulation of effective and sustainable energy policies for urban futures.

Prediction of values of Borsa Istanbul Forest, Paper, and Printing Index using machine learning methods

It is difficult to predict index values or stock prices with a single financial formula. They are affected by many factors, such as political conditions, global economy, unexpected events, market anomalies, and the characteristics of the relevant companies, and many computer science techniques are being used to make more accurate predictions about them. This study aimed to predict the values of the XKAGT index by using the monthly closing values of the Borsa Istanbul (BIST) Forestry, Paper and Printing (XKAGT) index between 2002 and 2023, and the machine learning techniques artificial neural networks (ANN), random forest (RF), k-nearest neighbor (KNN), and gradient boosting machine (GBM). Furthermore, the performances of four machine learning techniques were compared. Factors affecting stock prices are generally classified as macroeconomic and microeconomic factors. As a result of examining the studies on determining the macroeconomic factors affecting the stock markets, 10 macroeconomic factors were determined as input. The macroeconomic variables used were crude oil price, exchange rate of USD/TRY, dollar index, BIST100 index, gold price, money supply (M2), S&P 500 index, US 10-year bond interest, export-import coverage rate in the forest products sector, and deposits interest rate. It was determined that all machine learning techniques used in the study performed successfully in predicting the index value, but the k-nearest neighbor algorithm showed the best performance with R2=0.996, RMSE=71.36, and a MAE of 40.8. Therefore, in line with the current variables, investors can make analyzes using any of the ANN, RF, KNN, and GBM techniques to predict the future index value, which will lead them to accurate results.