Gradient Boosting Research Articles

The Application of Machine Learning Techniques to Predict Stock Market Crises in Africa

This study sought to ascertain a machine learning algorithm capable of predicting crises in the African stock market with the highest accuracy. Seven different machine-learning algorithms were employed on historical stock prices of the eight stock markets, three main sentiment indicators, and the exchange rate of the respective countries’ currencies against the US dollar, each spanning from 1 May 2007 to 1 April 2023. It was revealed that extreme gradient boosting (XGBoost) emerged as the most effective way of predicting crises. Historical stock prices and exchange rates were found to be the most important features, exerting strong influences on stock market crises. Regarding the sentiment front, investors’ perceptions of possible volatility on the S&P 500 (Chicago Board Options Exchange (CBOE) VIX) and the Daily News Sentiment Index were identified as influential predictors. The study advances an understanding of market sentiment and emphasizes the importance of employing advanced computational techniques for risk management and market stability.

Machine learning in predicting heart failure survival: a review of current models and future prospects.

Heart failure is a complex and prevalent condition with significant implications for patient management and survival prediction. Traditional predictive models often fall short in accuracy due to their reliance on pre-specified predictors and assumptions of variable independence. This review aims to assess the role of machine learning (ML) algorithms in predicting heart failure survival, comparing their performance with traditional statistical methods and identifying key predictive features. We conducted a review of studies utilizing ML algorithms for heart failure survival prediction. Data were sourced from PubMed/MEDLINE, Google Scholar, ScienceDirect, Embase, DOAJ, and the Cochrane Library, covering studies published until July 2024. A total of 10 studies were reviewed, encompassing 468,171 patients with heart failure. ML algorithms, particularly random forests and gradient boosting methods, demonstrated superior performance compared to traditional statistical models. These algorithms effectively identified key risk factors and stratified patients into risk categories with high accuracy. Notably, extreme learning machine (ELM) and CatBoost models showed exceptional predictive capabilities, as indicated by metrics such as Harrell's concordance index (C-index) and area under the curve (AUC). Key predictive features included ejection fraction (EF), serum creatinine (S Cr), and blood urea nitrogen (BUN). ML algorithms offer significant advantages in predicting heart failure survival by uncovering complex patterns and improving risk stratification. Their integration into clinical practice could lead to more personalized treatment strategies and enhanced patient outcomes. However, challenges such as data quality, model interpretability, and integration into clinical workflows need to be addressed.

Radiomics-based machine learning for automated detection of Pneumothorax in CT scans.

The increasing complexity of diagnostic imaging often leads to misinterpretations and diagnostic errors, particularly in critical conditions such as pneumothorax. This study addresses the pressing need for improved diagnostic accuracy in CT scans by developing an intelligent model that leverages radiomics features and machine learning techniques. By enhancing the detection of pneumothorax, this research aims to mitigate diagnostic errors and accelerate the process of image interpretation, ultimately improving patient outcomes. Data used in this study was extracted from the medical records of 175 patients with suspected pneumothorax. The collected images were preprocessed in Matlab software. Radiomics features were extracted from each image and finally, the machine learning models were implemented on these features. The used machine learning algorithms are Gradient Tree Boosting (GBM), eXtreme Gradient Boosting (XGBoost), and Light GBM. To evaluate the performance of models, various evaluation criteria such as precision, accuracy, specificity, sensitivity, F1 score, Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), and misclassification were calculated. According to the calculated evaluation criteria, in terms of accuracy, the Gradient Boosting Machine (GBM) model achieved the highest performance with an accuracy of 98.97%, followed closely by the XGBoost model at 98.29%. For precision, the GBM model outperformed the other models, recording a precision value of 99.55%. Regarding sensitivity, all three models-GBM, XGBoost, and LightGBM (LGBM)-demonstrated strong performance, with sensitivity values of 99%, 99%, and 100%, respectively, indicating minimal variation among them. The artificial intelligence models used in this study have significant potential to enhance patient care by supporting radiologists and other clinicians in the diagnosis of pneumothorax. These models can facilitate the prioritization of positive cases, expedite evaluations, and ultimately improve patient outcomes.

MACHINE LEARNING FOR COST ESTIMATION AND FORECASTING IN BANKING: A COMPARATIVE ANALYSIS OF ALGORITHMS

Accurate cost estimation and forecasting are critical for effective decision-making in the banking sector. This study evaluates the performance of machine learning algorithms, including Linear Regression, Ridge Regression, Random Forest, Gradient Boosting Machine (GBM), and Long Short-Term Memory (LSTM) networks, for cost prediction using a robust dataset comprising operational, transactional, and macroeconomic features. Our results demonstrate that while simpler models like Linear and Ridge Regression offer computational efficiency, their predictive accuracy is limited in handling complex data. Tree-based methods, particularly Random Forest and GBM, significantly enhance performance by capturing intricate patterns, albeit at a higher computational cost. The LSTM network outperformed all models, achieving the highest R² score and the lowest MAE and MSE values, highlighting its superiority in capturing temporal dependencies. This research provides actionable insights for banking institutions, emphasizing the trade-offs between accuracy, efficiency, and model complexity. The findings pave the way for optimized ML adoption in financial forecasting, enhancing operational resilience and strategic planning.

Short-Term Energy Generation Forecasts at a Wind Farm—A Multi-Variant Comparison of the Effectiveness and Performance of Various Gradient-Boosted Decision Tree Models

High-quality short-term forecasts of wind farm generation are crucial for the dynamically developing renewable energy generation sector. This article addresses the selection of appropriate gradient-boosted decision tree models (GBDT) for forecasting wind farm energy generation with a 10-min time horizon. In most forecasting studies, authors utilize a single gradient-boosted decision tree model and compare its performance with other machine learning (ML) techniques and sometimes with a naive baseline model. This paper proposes a comprehensive comparison of all gradient-boosted decision tree models (GBDTs, eXtreme Gradient Boosting (XGBoost), Light Gradient-Boosting Machine (LightGBM), and Categorical Boosting (CatBoost)) used for forecasting. The objective is to evaluate each model in terms of forecasting accuracy for wind farm energy generation (forecasting error) and computational time during model training. Computational time is a critical factor due to the necessity of testing numerous models with varying hyperparameters to identify the optimal settings that minimize forecasting error. Forecast quality using default hyperparameters is used here as a reference. The research also seeks to determine the most effective sets of input variables for the predictive models. The article concludes with findings and recommendations regarding the preferred GBDT models. Among the four tested models, the oldest GBDT model demonstrated a significantly longer training time, which should be considered a major drawback of this implementation of gradient-boosted decision trees. In terms of model quality testing, the lowest nRMSE error was achieved by the oldest model—GBDT in its tuned version (with the best hyperparameter values obtained from exploring 40,000 combinations).

Evaluating Binary Classifiers for Cardiovascular Disease Prediction: Enhancing Early Diagnostic Capabilities

Cardiovascular disease (CVD) is a significant global health concern and the leading cause of death in many countries. Early detection and diagnosis of CVD can significantly reduce the risk of complications and mortality. Machine learning methods, particularly classification algorithms, have demonstrated their potential to accurately predict the risk of cardiovascular disease (CVD) by analyzing patient data. This study evaluates seven binary classification algorithms, including Random Forests, Logistic Regression, Naive Bayes, K-Nearest Neighbors (kNN), Support Vector Machines, Gradient Boosting, and Artificial Neural Networks, to understand their effectiveness in predicting CVD. Advanced preprocessing techniques, such as SMOTE–ENN for addressing class imbalance and hyperparameter optimization through Grid Search Cross-Validation, were applied to enhance the reliability and performance of these models. Standard evaluation metrics, including accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (ROC-AUC), were used to assess predictive capabilities. The results show that kNN achieved the highest accuracy (99%) and AUC (0.99), surpassing traditional models like Logistic Regression and Gradient Boosting. The study examines the challenges encountered when working with datasets related to cardiovascular diseases, such as class imbalance and feature selection. It demonstrates how addressing these issues enhances the reliability and applicability of predictive models. These findings emphasize the potential of kNN as a reliable tool for early CVD prediction, offering significant improvements over previous studies. This research highlights the value of advanced machine learning techniques in healthcare, addressing key challenges and laying a foundation for future studies aimed at improving predictive models for CVD prevention.

Integrating microbial profiling and machine learning for inference of drowning sites: a forensic investigation in the Northwest River.

Drowning incidents present significant challenges for forensic investigators in determining the exact site of occurrence. Traditional forensic methods often rely on physical evidence and circumstantial clues, but the emerging field of forensic microbiology offers a promising avenue for enhancing precision and reliability in site inference. Our study investigates the application of microbiome analysis in inferring drowning sites, focusing on microbial diversity in water samples and lung tissues of drowned animals from different sites in the Northwest River. We utilized 16S rDNA sequencing to analyze microbial diversity in water samples and lung tissues, revealing distinct microbial signatures associated with drowning sites. Our findings highlight variations in species richness and diversity across different sampling points, indicating the influence of environmental factors on microbial community structure. Machine learning models trained on microbial data from lung tissues demonstrated high accuracy in predicting drowning sites, with cross-validation accuracy ranging from 83.53% ± 3.99% to 95.07% ± 3.17%. Notably, the Gradient Boosting Machine (GBM) method achieved a classification accuracy of 95.07% ± 3.17% for different sampling points at a submersion time of 1 day. Moreover, our cross-species site inference results revealed that utilizing data from drowned mice to predict the drowning sites of rabbits in location W5 achieved an accuracy of 72.22%. In conclusion, our study underscores the potential of microbiome analysis in forensic investigations of drowning incidents. By integrating microbial data with traditional forensic techniques, there is significant potential to enhance the reliability of scene inferences, thereby making substantial contributions to case investigations and judicial trials.IMPORTANCEBy employing advanced techniques like microbial profiling and machine learning, the study aims to enhance the accuracy of determining drowning sites, which is crucial for both legal proceedings. By analyzing microbial diversity in water samples and drowned animal lung tissues, the study sheds light on how environmental factors and victim-related variables influence microbial communities. The findings not only advance our understanding of forensic microbiology but also offer practical implications for improving investigative techniques in cases of drowning.

Impact of COVID-19 on Square Pharmaceuticals Stock Prices: A Comparative Analysis of Machine Learning Models

The aim of this paper is to compare the forecasting performance of different machine learning algorithms in case of the daily stock prices of Square Pharmaceuticals Limited. To ensure the impact of COVID-19 on the stock prices we separated the data into different segments such as pre-COVID period from January 2011 to March 2020, and the COVID period from March 2020 to September 2021 and the whole study period from January 2011 to December 2021. This study compares predicting performance of various machine learning algorithms such as K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting (GB), and Long Short-Term Memory (LSTM). To ensure a fair comparison of algorithm performance, we implemented the same combination of data splits and time steps consistently across all algorithms, which yielded optimal performance for each model. The empirical findings indicate that the Random Forest model consistently delivered the highest accuracy across all periods, the SVM model showed an unexpected increase in accuracy during COVID period whereas the LSTM model's performance declined. This comprehensive analysis highlights the adaptability and robustness of machine learning models in volatile market conditions, emphasizing their utility in financial forecasting during global disruptions like the COVID-19 pandemic. International Journal of Statistical Sciences, Vol. 24(2), November, 2024, pp 73-84

How the US Macroeconomic Factors Affect the Gold Price?

Nowadays, investing in gold as a hedge against macroeconomic factors risk has been brought into the spotlight. It is essential for investors to predict gold prices before making their hedging decisions. After a thorough study of past precursors, the machine learning method, especially the gradient boosting technique, has been proven to be a powerful method for predicting gold prices. This study tests macroeconomic factors as well as oil prices and uses them as independent variables to predict gold prices. By using advanced machine learning technique: gradient boosting, this study achieves finding the best four factors model. The research shows that oil prices, the U.S. dollar index, interest rate, and GDP growth are significant factors in predicting gold prices. Among all the significant factors, oil price is the most important one. The explicit reasons of this result is because that transportation cost and operation cost of gold mining is largely influenced by oil price. This study lays the foundations for investors to make insightful decisions.

Resource Optimization for Grid-Connected Smart Green Townhouses Using Deep Hybrid Machine Learning

This paper examines Connected Smart Green Townhouses (CSGTs) as a modern residential building model in Burnaby, British Columbia (BC). This model incorporates a wide range of sustainable materials and smart components such as recycled insulation, Photovoltaic (PV) solar panels, smart meters, and high-efficiency systems. The CSGTs operate in grid-connected mode to balance on-site renewables with grid resources to improve efficiency, cost-effectiveness, and sustainability. Real datasets are used to optimize resource consumption, including electricity, gas, and water. Renewable Energy Sources (RESs), such as PV systems, are integrated with smart grid technology. This creates an effective framework for managing energy consumption. The accuracy, efficiency, emissions, and cost are metrics used to evaluate CSGT performance. CSGTs with one to four bedrooms are investigated considering water systems and party walls. A deep Machine Learning (ML) model combining Long Short-Term Memory (LSTM) and a Convolutional Neural Network (CNN) is proposed to improve the performance. In particular, the Mean Absolute Percentage Error (MAPE) is below 5%, the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are within acceptable levels, and R2 is consistently above 0.85. The proposed model outperforms other models such as Linear Regression (LR), CNN, LSTM, Random Forest (RF), and Gradient Boosting (GB) for all bedroom configurations.

Water Level Forecasting Combining Machine Learning and Ensemble Kalman Filtering in the Danshui River System, Taiwan

Taiwan faces intense rainfall during typhoon seasons, leading to rapid increases in water level in rivers. Accurate flood forecasting in rivers is essential for protecting lives and property. The objective of this study is to develop a river flood forecasting model combining multiple additive regression trees (MART) and ensemble Kalman filtering (EnKF). MART, a machine learning technique, predicts water levels for internal boundary conditions, correcting a one-dimensional (1D) unsteady flow model. EnKF further refines these predictions, enabling precise real-time forecasts of water levels in the Danshui River system for up to three hours lead time. The model was calibrated and validated using observed data from four historical typhoons to evaluate its accuracy. For the present time at three water level stations in the Danshui River system, the root mean square error (RMSE) ranged from 0.088 to 0.343 m, while the coefficient of determination (R2) ranged from 0.954 to 0.999. The validated model (module 1) was divided into two additional modules: module 2, which combined the ensemble unsteady flow model with inner boundary correction and MART, and module 3, which featured an ensemble 1D unsteady flow model without inner boundary correction. These modules were employed to forecast water levels at three stations from the present time to 3 h lead time during Typhoon Muifa in 2022. The study revealed that the Tu-Ti-Kung-Pi station was less affected by inner boundaries due to significant tidal influences. Consequently, excluding the upstream and downstream boundaries, Tu-Ti-Kung-Pi station showed a superior RMSE trend from present time to 3 h lead time across all three modules. Conversely, the Taipei Bridge and Bailing Bridge stations began using inner boundary forecast values for correction from 1 h to 3 h lead times. This increased the uncertainty of the inner boundary, resulting in higher RMSE values for these locations in modules 1 and 2 compared to module 3.

Differential Study on Estimation Models for Indica Rice Leaf SPAD Value and Nitrogen Concentration Based on Hyperspectral Monitoring

Soil and plant analyzer development (SPAD) value and leaf nitrogen concentration (LNC) based on dry weight are important indicators affecting rice yield and quality. However, there are few reports on the use of machine learning algorithms based on hyperspectral monitoring to synchronously predict SPAD value and LNC of indica rice. Meixiangzhan No. 2, a high-quality indica rice, was grown at different nitrogen rates. A hyperspectral device with an integrated handheld leaf clip-on leaf spectrometer and an internal quartz-halogen light source was conducted to monitor the spectral reflectance of leaves at different growth stages. Linear regression (LR), random forest (RF), support vector regression (SVR), and gradient boosting regression tree (GBRT) were employed to construct models. Results indicated that the sensitive bands for SPAD value and LNC were displayed to be at 350–730 nm and 486–727 nm, respectively. Normalized difference spectral indices NDSI (R497, R654) and NDSI (R729, R730) had the strongest correlation with leaf SPAD value (R = 0.97) and LNC (R = −0.90). Models constructed via RF and GBRT were markedly superior to those built via LR and SVR. For prediction of leaf SPAD value and LNC, the model constructed with the RF algorithm based on whole growth periods of spectral reflectance performed the best, with R2 values of 0.99 and 0.98 and NRMSE values of 2.99% and 4.61%. The R2 values of 0.98 and 0.83 and the NRMSE values of 4.88% and 12.16% for the validation of leaf SPAD value and LNC were obtained, respectively. Results indicate that there are significant spectral differences associated with SPAD value and LNC. The model built with RF had the highest accuracy and stability. Findings can provide a scientific basis for non-destructive real-time monitoring of leaf color and precise fertilization management of indica rice.

Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models

Micro-textured surfaces show promise in improving tribological properties, but predicting their performance remains challenging due to complex relationships between surface features and frictional behavior. This study evaluates five algorithms—linear regression, decision tree, gradient boosting, support vector machine, and neural network—for their ability to predict load-carrying capacity and friction force based on texture parameters including depth, side length, surface ratio, and shape. The neural network model demonstrated superior performance, achieving the lowest MAE (24.01) and highest R-squared value (0.99) for friction force prediction. The results highlight the potential of machine learning techniques to enhance the understanding and prediction of friction-reducing micro-textures, contributing to the development of more efficient and durable tribological systems in industrial applications.

Quantitative MRI Assessment of Post-Surgical Spinal Cord Injury Through Radiomic Analysis

Purpose: This study investigates radiomic efficacy in post-surgical traumatic spinal cord injury (SCI), overcoming MRI limitations from metal artifacts to enhance diagnosis, severity assessment, and lesion characterization or prognosis and therapy guidance. Background: Traumatic spinal cord injury (SCI) causes severe neurological deficits. While MRI allows qualitative injury evaluation, standard imaging alone has limitations for precise SCI diagnosis, severity stratification, and pathology characterization, which are needed to guide prognosis and therapy. Radiomics enables quantitative tissue phenotyping by extracting a high-dimensional set of descriptive texture features from medical images. However, the efficacy of postoperative radiomic quantification in the presence of metal-induced MRI artifacts from spinal instrumentation has yet to be fully explored. Methods: A total of 50 healthy controls and 12 SCI patients post-stabilization surgery underwent 3D multi-spectral MRI. Automated spinal cord segmentation was followed by radiomic feature extraction. Supervised machine learning categorized SCI versus controls, injury severity, and lesion location relative to instrumentation. Results: Radiomics differentiated SCI patients (Matthews correlation coefficient (MCC) 0.97; accuracy 1.0), categorized injury severity (MCC: 0.95; ACC: 0.98), and localized lesions (MCC: 0.85; ACC: 0.90). Combined T1 and T2 features outperformed individual modalities across tasks with gradient boosting models showing the highest efficacy. Conclusions: The radiomic framework achieved excellent performance, differentiating SCI from controls and accurately categorizing injury severity. The ability to reliably quantify SCI severity and localization could potentially inform diagnosis, prognosis, and guide therapy. Further research is warranted to validate radiomic SCI biomarkers and explore clinical integration.

Optimising Venturi flume oxygen transfer efficiency using uncertainty-aware decision trees

ABSTRACT This study optimizes standard oxygen transfer efficiency (SOTE) in Venturi flumes investigating the impact of key parameters such as discharge per unit width (q), throat width (W), throat length (F), upstream entrance width (E), and gauge readings (Ha and Hb). To achieve this, a comprehensive experimental dataset was analyzed using multiple linear regression (MLR), multiple nonlinear regression (MNLR), gradient boosting machine (GBM), extreme gradient boosting (XRT), random forest (RF), M5 (Pruned and Unpruned), random tree (RT), and reduced error pruning (REP). Model performance was evaluated based on key metrics: correlation coefficient (CC), root mean square error (RMSE), and mean absolute error (MAE). Among the proposed models, M5_Unprun emerged as the top performer, exhibiting the highest CC (0.9455), the lowest RMSE (0.1918), and the lowest MAE (0.0030). GBM followed closely with a CC value of 0.9372, an RMSE value of 0.2067, and an MAE value of 0.0006. Uncertainty analysis further solidified the superior performance of M5_Unpruned (0.7522) and GBM (0.8055), with narrower prediction bands compared to other models, including MLR, which exhibited the widest band (1.4320). One-way analysis of variance confirmed the reliability and robustness of the proposed models. Sensitivity, correlation, and SHapley Additive exPlanations analyses identified W and Hb as the most influencing factors.

Erosion wear performance of titania filled ramie-epoxy composites: A data driven optimization study using supervised machine learning approach

This paper reports on a data driven machine learning (ML) approach to analyze and predict the erosion behavior of titanium oxide (titania) filled ramie-epoxy composites. ML models are extensively used in recent years to mimic human decisions in various industries. After fabrication and well-designed erosion trials following design of experiments, the experimental data is critically analyzed to examine the effect of each input factor (erodent temperature, striking angle, striking velocity and filler content) on the output that is erosion wear rate. It is found that the erosion wear rate increases with increase in striking velocity and striking angle and decreases with increase in filler content. The experimental data is further used to feed five different ML models. The performance and adequacy of ML models are compared using five different performance metrics. It is noticed that although all the machine learning techniques effectively predicted the erosion rate, the Gradient boosting machine (GBM) model exhibited superior performance with an R2 value of 0.9486. The feature importance plot confirms that the, filler content, striking velocity and the striking angle played a major role in predicting the erosion rate of the hybrid composites.

Development of a Machine Learning Tool to Predict Deep Inspiration Breath Hold Requirement for Locoregional Right-Sided Breast Radiation Therapy Patients.

&#xD;This study presents machine learning (ML) models that predict if deep inspiration breath hold (DIBH) is needed based on lung dose in right-sided breast cancer patients during the initial computed tomography (CT) appointment. &#xD;Materials and methods. &#xD;Anatomic distances were extracted from a single-institution dataset of free breathing (FB) CT scans from locoregional right-sided breast cancer patients. Models were developed using combinations of anatomic distances and ML classification algorithms (gradient boosting, k-nearest neighbors, logistic regression, random forest, and support vector machine) and optimized over 100 iterations using stratified 5-fold cross-validation. Models were grouped by the number of anatomic distances used during development; those with the highest validation accuracy were selected as final models. Final models were compared based on their predictive ability, measurement collection efficiency, and robustness to simulated user error during measurement collection. &#xD;Results. &#xD;This retrospective study included 238 patients treated between 2016 and 2021. Model development ended once eight anatomic distances were included, and the validation accuracy plateaued. The best performing model used logistic regression with four anatomic distances achieving 80.5% average testing accuracy, with minimal false negatives and positives (< 27%). The anatomic distances required for prediction were collected within 3 minutes and were robust to simulated user error during measurement collection, changing accuracy by < 5%. &#xD;Conclusion. &#xD;Our logistic regression model using four anatomic distances provided the best balance between efficiency, robustness, and ability to predict if DIBH was needed for locoregional right-sided breast cancer patients.&#xD.

Automated Cardiovascular Disease Detection with Hybrid Machine Approach

Cardiovascular ailment (CVD) is a main reason of death and disability globally, posing tremendous challenges for early detection and prevention. A heart condition or the accumulation of fatty deposits inside the arteries, is frequently linked to CVD and raises the risk of blood clots and other consequences. Predicting and diagnosing CVD is critical to mitigating its effect and enhancing patient results. With the appearance of massive data in healthcare, large volumes of patient records are available that may assist in identifying early warning symptoms of coronary heart disorder. This project aims to generate a hybrid machine learning technique which leverages deep learning and traditional machine learning algorithms to automatically locate cardiovascular illnesses. By integrating more than one dataset, we intend to upgrade the model's overall performance in diagnosing coronary heart situations. Numerous machine learning classification models, consisting of Random Forest and Gradient Boosting, might be employed and in comparison, to evaluate their effectiveness in detecting CVD. Each model can be evaluated using overall performance indicators like precision, accuracy, recall, and F1-Score. In previous research, the Random Forest model did 94% accuracy in coronary heart disorder detection, at the same time as the Gradient Boosting model established a balanced overall performance through accuracy, precision, recall, and F1-score with 73% each in detecting cardiovascular diseases via this hybrid technique. We aim to enhance prediction accuracy and offer a greater reliable tool for early CVD detection, in the long run enhancing affected person care and saving lives.

Ensemble Learning for Oat Yield Prediction Using Multi-Growth Stage UAV Images

Accurate crop yield prediction is crucial for optimizing cultivation practices and informing breeding decisions. Integrating UAV-acquired multispectral datasets with advanced machine learning methodologies has markedly refined the accuracy of crop yield forecasting. This study aimed to construct a robust and versatile yield prediction model for multi-genotyped oat varieties by investigating 14 modeling scenarios that combine multispectral data from four key growth stages. An ensemble learning framework, StackReg, was constructed by stacking four base algorithms—ridge regression (RR), support vector machines (SVM), Cubist, and extreme gradient boosting (XGBoost)—to predict oat yield. The results show that, for single growth stages, base models achieved R2 values within the interval of 0.02 to 0.60 and RMSEs ranging from 391.50 to 620.49 kg/ha. By comparison, the StackReg improved performance, with R2 values extending from 0.25 to 0.61 and RMSEs narrowing to 385.33 and 542.02 kg/ha. In dual-stage and multi-stage settings, the StackReg consistently surpassed the base models, reaching R2 values of up to 0.65 and RMSE values as low as 371.77 kg/ha. These findings underscored the potential of combining UAV-derived multispectral imagery with ensemble learning for high-throughput phenotyping and yield forecasting, advancing precision agriculture in oat cultivation.

Simulating flood risk in Tampa Bay using a machine learning driven approach

Machine learning (ML) models can simulate flood risk by identifying critical non-linear relationships between flood damage locations and flood risk factors (FRFs). To explore it, Tampa Bay, Florida, is selected as a test site. The study’s goal is to simulate flood risk and identify dominant FRFs using historical flood damage data as target variable, with 16 FRFs as predictor variables. Five different ML models such as decision tree (DT), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and random forest (RF) were adopted. RF classifies 2.42% of Tampa Bay as very high risk and 2.54% as high risk, while XGBoost classifies 3.85% as very high risk and 1.11% as high risk. Moreover, the communities reside at low altitudes and near the waterbodies, with dense man-made infrastructure, are at high flood risk. This study introduces a comprehensive framework for flood risk assessment and helps policymakers mitigate flood risk.