Machine Learning Methods Research Articles

An Overview of Machine-Learning Methods for Soil Moisture Estimation

Soil moisture (SM) is crucial for sustainable applications in agriculture, meteorology, and hydrology. While direct measurement provides superior accuracy, it is unfeasible when applied over extensive geographical areas because of its costly and time-intensive nature. On the other hand, parameterization, complexity, and assumptions used in empirical and physical models lead to challenging SM estimations using these models. By handling extensive datasets and identifying complex connections within the data, the machine-learning (ML) approach has become an attractive solution to address the aforementioned limitations. This approach can estimate SM by effectively capturing the complex relationships among environmental variables and soil moisture data. Although the ML approach is a powerful tool for estimating SM, it has several limitations, such as data dependency, scalability, and high dimensionality. This paper aims to present an overview of ML methods used for modeling SM while also discussing their challenges and notable achievements within this field. These models vary in suitability depending on data availability and context. DL models excel in capturing spatiotemporal complexity but require abundant data. SVMs are robust in noisy or sparse datasets, and hybrid models offer improved flexibility and predictive accuracy. Incorporating remote sensing, satellite data, and hybrid physical-AI frameworks can further enhance performance. However, the opaque “black-box” nature of ML remains a barrier to trust and operational use, emphasizing the need for explainable AI (XAI) to improve transparency. The findings underscored the importance of prioritizing the transferability of AI-based models across varied environmental conditions to ensure scalable and dependable soil moisture monitoring.

Machine Learning In Production Engineering: A Comprehensive Review

The study examines how machine learning (ML) methods can be incorporated into production engineering practices. The paper highlights data preprocessing and cleaning as essential steps to maintain data quality and reliability for ML applications. The review shows the production environment challenges that include missing data values and the presence of outliers along with data inconsistencies. The text explains how advanced automation techniques decrease human involvement while improving feature extraction methods, which produce uniform features across different manufacturing systems. The paper emphasizes that effective model deployment relies on rigorous data engineering pipelines that perform comprehensive data ingestion, transformation, and feature engineering. The review intends to explore the existing ML applications within production engineering while identifying key practices that enable model readiness and reliability.

Multifunctional Hydrogen-Bonded Organic Frameworks for Intelligent Anti-Counterfeiting and Food Safety Monitoring.

In an era of increasing digital threats and product counterfeiting, this study introduces MA-IPA@NPA, a groundbreaking hydrogen-bonded organic framework (HOF) material designed for advanced anticounterfeiting applications. This innovative material showcases distinctive optical properties, including dual fluorescence-phosphorescence emission and an ultralong phosphorescence lifetime, making it exceptionally difficult to replicate. Additionally, MA-IPA@NPA demonstrates efficacy as a fluorescence sensor for detecting tryptamine and gallic acid in food products, addressing both security and food safety concerns. Through electrospinning technology, we successfully developed a multifunctional composite nanofiber membrane by integrating MA-IPA@NPA with poly(vinyl alcohol) nanofibers, thereby combining the superior optical properties of the HOF with the flexibility and durability of polymer nanofibers. This advanced composite forms the foundation of our Multiple-Responsive Intelligent Anticounterfeiting label, which exhibits dynamic responses to diverse stimuli and incorporates multilevel verification through sophisticated machine learning methods, including binary image recognition and a Back-Propagation Neural Network. Our comprehensive research not only presents a novel strategy for developing advanced, multifunctional anticounterfeiting systems but also offers a timely solution to the escalating demand for enhanced security and authenticity verification in our increasingly digital world, paving the way for more robust and reliable anticounterfeiting measures across various industries.

Native language identification from text using a fine-tuned GPT-2 model

Native language identification (NLI) is a critical task in computational linguistics, supporting applications such as personalized language learning, forensic analysis, and machine translation. This study investigates the use of a fine-tuned GPT-2 model to enhance NLI accuracy. Using the NLI-PT dataset, we preprocess and fine-tune GPT-2 to classify the native language of learners based on their Portuguese-written texts. Our approach leverages deep learning techniques, including tokenization, embedding extraction, and multi-layer transformer-based classification. Experimental results show that our fine-tuned GPT-2 model significantly outperforms traditional machine learning methods (e.g., SVM, Random Forest) and other pre-trained language models (e.g., BERT, RoBERTa, BioBERT), achieving a weighted F1 score of 0.9419 and an accuracy of 94.65%. These results show that large transformer models work well for native language identification and can help guide future research in personalized language tools and artificial intelligence (AI)-based education.

Exploring the use of satellite imagery and computer vision‐based machine learning method to improve the spatial granularity of poverty statistics

AbstractSpatially granular poverty statistics can enhance the efficiency of targeting resources to improve the living conditions of the poor. Previous studies suggest that the use of high‐resolution satellite imagery may be an alternative approach in generating granular poverty maps. This study outlines the methods in improving the spatial granularity of government‐published poverty estimates using convolutional neural networks and ridge regression applied on publicly available satellite imagery, household surveys, and census data from the Philippines and Thailand. A convolutional neural network (CNN) was used to extract features of satellite images that are correlated with the intensity of nightlights. These features were then aggregated at the same level for which government‐published estimates were available to estimate a prediction model for poverty rates. Results suggest that the adopted methodology performed satisfactorily in predicting lower levels of nightlight intensity for the specific years considered in this study. Additional preliminary numerical assessment also reveals that prediction accuracy may be enhanced by using random forest as an alternative to ridge regression. The use of proprietary satellite images with higher resolution may also improve prediction accuracy.

Medical Federated Learning with Improved Representation and Personalized Aggregation

Federated learning is a promising bridge that connects machine learning methods and multi-central medical data. It trains models using the local data, and protects the privacy of data. There are many methods for federated learning to aggregate models, especially personalized methods, which show relatively excellent performance. However, most of them excessively pay attention to global and local information while ignoring the random components during aggregating. That limits their performance in metrics like accuracy, specificity and sensitivity. We propose a method (denoted by FedDiv) to make a balance between these metrics. The basic idea is to extract centralized features meanwhile filtering random components, and conduct personalized aggregation. These centralized features draw encoders’ attention, which enhances the performance of personalized models in specificity and sensitivity. Besides, they contain more global and local information, which is advantageous for personalized aggregation. Meanwhile, our personalized method preserves the local information as far as possible during aggregating models. These local information are the critical factor for the personalized models to perform better in accuracy. Finally, we validate this method in 3 public and 1 private medical datasets. Comparing with 14 federated methods, our method achieves the best performance in metrics including accuracy, specificity, sensitivity and F1 score.

Estimation of postmortem interval under different ambient temperatures based on multi-organ metabolomics and machine learning algorithm.

In forensic practice, the estimation of postmortem interval has been a persistent challenge. Recently, there has been an increasing utilization of metabolomics techniques combined with machine learning methods for postmortem interval estimation. When examining metabolite changes from a global perspective, rather than relying on specific substance changes, estimating postmortem interval through machine learning methods is more precise and entails fewer errors. Prior studies have investigated the use of metabolomics to estimate postmortem interval. Nevertheless, most of them focused on analyzing the metabolomic properties of a single organ or biofluid concerning a specific temperature. In this study, we employ the GC-MS platform to identify metabolites in the liver, kidney, and quadriceps femoris muscle of mechanically suffocated Sprague Dawley rats at various temperatures. Multivariable statistical analysis was used to determine differential compounds from the original data. The machine learning method was used to establish models for the estimation of postmortem interval under various ambient temperatures. As indicated by the results, liver, kidney, and quadriceps femoris muscle samples were screened for 24, 18, and 19 differential metabolites respectively, associated with postmortem interval under various ambient temperatures. Based on the metabolites listed above, the support vector regression models were established by utilizing single-organ and multi-organ metabolomics data for postmortem interval estimation. The multi-organ model showed a higher estimation accuracy. Also, a comprehensive generalization postmortem interval estimation model was established with multi-organ metabolomics data and temperature variables, which can be used for the postmortem interval estimation within the temperature range of 5-35℃. These results demonstrate that a multi-organ model utilizing metabolomics techniques can accurately estimate the postmortem interval under various ambient temperatures. Meanwhile, this research establishes a strong foundation for the practical application of metabolomics in postmortem interval estimation.

A Clinically Annotated Transcriptomic Atlas of Nervous System Tumors.

While DNA methylation signatures are distinct across nervous system neoplasms, it has not been comprehensively demonstrated whether transcriptomic signatures exhibit similar uniqueness. Additionally, no large-scale dataset for comparative gene expression analyses exists. This study addresses these knowledge and resource gaps. We compiled and harmonized raw transcriptomic and clinical data for neoplastic (n=5,402) and non-neoplastic (n=1,973) nervous system samples from publicly available sources, all profiled on the same microarray platform. After adjusting for surrogate variable effects ('batch effects'), machine learning methods were used to visualize, cluster, and reclassify samples with uncertain diagnoses (n=2,225). We generated the largest clinically annotated transcriptomic atlas of nervous system tumors to date. Sample clustering was primarily driven by diagnosis. We show the utility of the atlas by refining the transcriptional subtypes of pheochromocytoma and paraganglioma (PH/PG), revealing six robust subtypes (Neuronal, Vascular, Metabolic, Steroidal, Developmental, Indeterminate), which were independently validated using TCGA RNA-seq data and that correlated with specific mutational signatures and clinical behaviors of these tumors. Like bulk DNA methylation, we demonstrate that bulk transcriptomic signatures are distinct across the diagnostic spectrum of nervous system neoplasms. Our atlas' broad coverage of diagnoses, including rarely studied entities, spans all ages and includes individuals from diverse geographical regions, enhancing its utility for comprehensive and robust comparative gene expression analyses, as exemplified by our PH/PG analyses. For access visit http://kdph.shinyapps.io/atlas/ or https://github.com/axitamm/BrainTumorAtlas.

A comprehensive analysis of landslide susceptibility in Iyidere Basin (NE, Turkey) using machine learning techniques and statistical bivariate methods

Abstract Natural events are called disasters when they cause great damage, human suffering, or loss of life. Landslides, one of these disasters, cause significant damage to property and infrastructure and pose risks to people's lives. In this research, landslide susceptibility was studied in Iyidere Basin, located in northeastern Turkey. This basin, which is among the cities where the most landslide events occur in Turkey, is a very important representative area in terms of a comprehensive analysis of landslides in the region. Bivariate (frequency ratio, weight of evidence, statistical index) and machine learning methods (artificial neural network, logistic regression) were used to evaluate landslide susceptibility with fifteen environmental parameters and 588 landslide inventory data. Landslide inventory data was generated using different sources, and environmental parameters databases were created using various sources and software. A receiver operating characteristic curve and Kappa statistic value were generated to test the performance and reliability of the susceptibility maps. It was determined that landslide susceptibility is higher in the downstream part of the basin. Although it varies between methods, it has been determined that approximately one-quarter of the basin has high and very high landslide susceptibility. The most effective parameters (drainage density, slope, curvature, lithology, land cover, distance to stream, and roads) for susceptibility and their classes were revealed.

Machine learning decision support model construction for craniotomy approach of pineal region tumors based on MRI images

BackgroundPineal region tumors (PRTs) are rare but deep-seated brain tumors, and complete surgical resection is crucial for effective tumor treatment. The choice of surgical approach is often challenging due to the low incidence and deep location. This study aims to combine machine learning and deep learning algorithms with pre-operative MRI images to build a model for PRTs surgical approaches recommendation, striving to model clinical experience for practical reference and education.MethodsThis study was a retrospective study which enrolled a total of 173 patients diagnosed with PRTs radiologically from our hospital. Three traditional surgical approaches of were recorded for prediction label. Clinical and VASARI related radiological information were selected for machine learning prediction model construction. And MRI images from axial, sagittal and coronal views of orientation were also used for deep learning craniotomy approach prediction model establishment and evaluation.Results5 machine learning methods were applied to construct the predictive classifiers with the clinical and VASARI features and all methods could achieve area under the ROC (Receiver operating characteristic) curve (AUC) values over than 0.7. And also, 3 deep learning algorithms (ResNet-50, EfficientNetV2-m and ViT) were applied based on MRI images from different orientations. EfficientNetV2-m achieved the highest AUC value of 0.89, demonstrating a significant high performance of prediction. And class activation mapping was used to reveal that the tumor itself and its surrounding relations are crucial areas for model decision-making.ConclusionIn our study, we used machine learning and deep learning to construct surgical approach recommendation models. Deep learning could achieve high performance of prediction and provide efficient and personalized decision support tools for PRTs surgical approach.Clinical trial numberNot applicable.

Novel machine learning models for the prediction of acute respiratory distress syndrome after liver transplantation

Early prediction of acute respiratory distress syndrome (ARDS) after liver transplantation (LT) facilitates timely intervention. We aimed to develop a predictor of post-LT ARDS using machine learning (ML) methods. Data from 755 patients in the internal validation set and 115 patients in the external validation set were retrospectively reviewed, covering demographics, etiology, medical history, laboratory results, and perioperative data. According to the area under the receiver operating characteristic curve (AUROC), accuracy, specificity, sensitivity, and F1-value, the prediction performance of seven ML models, including logistic regression (LR), decision tree, random forest (RF), gradient boosting decision tree (GBDT), naïve bayes (NB), light gradient boosting machine (LGBM) and extreme gradient boosting (XGB) were evaluated and compared with acute lung injury prediction scores (LIPS). 234 (30.99%) ARDS patients were diagnosed. The RF model had the best performance, with an AUROC of 0.766 (accuracy: 0.722, sensitivity: 0.617) in the internal validation set and a comparable AUROC of 0.844 (accuracy: 0.809, sensitivity: 0.750) in the external validation set. The performance of all ML models was better than LIPS (AUROC 0.692, 0.776). The predictor variables included the age of the recipient, BMI, MELD score, total bilirubin, prothrombin time, operation time, standard urine volume, total intake volume, and red blood cell infusion volume. We firstly developed a risk predictor of post-LT ARDS based on RF model to ameliorate clinical practice.

Prediction of coronary heart disease based on klotho levels using machine learning

The diagnostic accuracy for coronary heart disease (CHD) needs to be improved. Some studies have indicated that klotho protein levels upon admission comprise an independent risk factor for CHD and have clinical value for predicting CHD. This study aimed to construct a tool to predict CHD risk by analyzing klotho levels and clinically relevant indicators by using a machine learning (ML) method. We randomly assigned the dataset of the National Health and Nutrition Examination Survey (NHANES) 2007–2016 to training and test sets at a ratio of 70:30. We evaluated the ability of five models constructed using logistic regression, neural networks, random forest, support vector machine, and eXtreme Gradient Boosting to predict CHD. We determined their predictive performance using the following parameters: area under the receiver operating characteristic curve, accuracy, precision, recall, F1, and Brier scores. We analyzed data from 11,583 persons in US NHANES and entered 13 potential predictive variables, including klotho and other clinically relevant indicators, into the feature screening process. We established that the five ML models could predict the onset of CHD. The RF model showed the best predictive performance among the five ML models.

Identification of Prognostic Biomarkers in Gene Expression Profile of Neuroblastoma Via Machine Learning

ABSTRACTNeuroblastoma (NB) is a common pediatric solid malignancy characterized by heterogeneous clinical outcomes. The identification of predictive and interpretable prognostic biomarkers is critical for advancing precision medicine in NB. We proposed an integrative network‐based machine learning method for biomarker discovery, which employed a network smoothed t‐statistic support vector machine to select prognostic related biomarkers, and then we performed network analysis on these biomarkers to find hub genes. Later, we conducted a comprehensive analysis to integrate bulk and single‐cell RNA sequencing data to character the tumor microenvironment of prognostic state and correlated them to the discovered hub genes. This analysis identified 528 prognostic biomarkers associated with NB. Network‐based analysis further refined this set to 11 hub prognostic biomarkers for NB: AURKA, BLM, BRCA1, BRCA2, CCNA2, CHEK1, E2F1, MAD2L1, PLK1, RAD51, and RFC3. Among these genes, high RFC3 expression was significantly associated with poor prognosis, highlighting its potential as a novel prognostic biomarker in NB. Additionally, our findings revealed that these biomarkers are correlated to chemotherapy drugs, such as vincristine and cyclophosphamide. Furthermore, drug sensitivity analyses identified several candidate drugs, such as dactinomycin, bortezomib, docetaxel, and sepantronium bromide, that may hold therapeutic potential for NB treatment. This study offers novel insights to underlying NB prognosis and therapeutic targets and provides a foundation for developing personalized treatment strategies to improve clinical outcomes.

Machine Learning-based Method to Label Signals from People with Neurological Injuries

ABSTRACTInterfaces that use sEMG signals face the challenge of correctly identifyingthe signal while distinguishing it from noise or interference.Although classical techniques like visual inspection and machinelearning methods exist, most studies focus on signals from healthyindividuals. There is a lack of data and methods suitable for signalsfrom individuals with neurological conditions, such as cerebralpalsy and post-stroke. This study analyzes sEMG data from individualswith neurological injuries, using machine learning methods toidentify muscle contractions and rest without pre-processing. Thedata were acquired from people with neurological diseases, such ascerebral palsy and post-stroke. They were extracted using sEMGfrom triceps brachii and extensor carpi radialis muscles. The signalswere not preprocessed and were input as segmented time windowsto three proposed classifiers: Support Vector Machine, Random Forestand an Ensemble Voting classifier. All three classifiers reachedaround 99% accuracy and F1-Score on typical sEMG data, but theresults on abnormal data were inconclusive.

Broad Random Forest: A Lightweight Prediction Model for Short-Term Wind Power by Fusing Broad Learning and Random Forest

As an important component of sustainable development and energy transition, wind power is rapidly rising. This paper selects the time series of historical wind power as features and establishes a lightweight prediction model called a broad random forest model (BRF). The proposed model fully uses the feature representation ability of the broad learning system (BLS) and the fast computational speed of random forest (RF). To begin, the example sets are created with a sliding window for the wind power series. Then, the processed data are input into the BLS module. The feature-expansion function of BLS is fully utilized to generate mapped features and enhanced features. These two types of features are reconstructed to obtain a new sample set. Next, the RF model is established for the new sample set to make predictions. The prediction results of all decision trees are superimposed, and their average value is taken as the final prediction result. Finally, the predicted results of BRF are compared with other mainstream machine learning and deep learning methods. The experimental results show that the proposed model has the best predictive performance on the wind power datasets, with an improvement of 0.22% in R2 at least.

Martensite Start Temperature Modeling via Artificial Neural Network Model

The martensite start temperature (Ms) of steels plays an important role in the formulation of heat‐treatment processes. Therefore, it is of great practical importance to predict Ms accurately and rapidly. In the present work, machine learning (ML) methods are used to model Ms based on the Ms data of 1177 steels. Moreover, its generalization performance is verified using fivefold cross validation. Three different back‐propagation (BP) neural network algorithms (genetic algorithm [GA], particle swarm optimization, mind evolutionary algorithm) are used for optimal model selection. The results indicate that, among the three BP neural network algorithms, the GA–BP model has the highest prediction accuracy on the test set. The performances of GA–BP, Thermal–Calc, and JMatPro in predicting the Ms of medium‐ and low‐carbon steels and high‐carbon steels are analyzed using an unknown dataset. The results show that the GA–BP model has strong generalization ability and can predict Ms relatively accurately. The influence of alloying elements on Ms is analyzed using the GA–BP model and the shapley additive explanation method, which provides strategies for studying the microstructure evolution of steel or optimizing the heat‐treatment process.

Clinical, radiological, and radiomics feature-based explainable machine learning models for prediction of neurological deterioration and 90-day outcomes in mild intracerebral hemorrhage

BackgroundThe risks and prognosis of mild intracerebral hemorrhage (ICH) patients were easily overlooked by clinicians. Our goal was to use machine learning (ML) methods to predict mild ICH patients’ neurological deterioration (ND) and 90-day prognosis.MethodsThis prospective study recruited 257 patients with mild ICH for this study. After exclusions, 148 patients were included in the ND study and 144 patients in the 90-day prognosis study. We trained five ML models using filtered data, including clinical, traditional imaging, and radiomics indicators based on non-contrast computed tomography (NCCT). Additionally, we incorporated the Shapley Additive Explanation (SHAP) method to display key features and visualize the decision-making process of the model for each individual.ResultsA total of 21 (14.2%) mild ICH patients developed ND, and 35 (24.3%) mild ICH patients had a 90-day poor prognosis. In the validation set, the support vector machine (SVM) models achieved an AUC of 0.846 (95% confidence intervals (CI), 0.627-1.000) and an F1-score of 0.667 for predicting ND, and an AUC of 0.970 (95% CI, 0.928-1.000), and an F1-score of 0.846 for predicting 90-day prognosis. The SHAP analysis results indicated that several clinical features, the island sign, and the radiomics features of the hematoma were of significant value in predicting ND and 90-day prognosis.ConclusionThe ML models, constructed using clinical, traditional imaging, and radiomics indicators, demonstrated good classification performance in predicting ND and 90-day prognosis in patients with mild ICH, and have the potential to serve as an effective tool in clinical practice.Clinical trial numberNot applicable.

An analysis of alternative machine learning and deep learningalgorithms for categorization and detection of various active ‎network assaults

Attacks on networks have grown increasingly widespread because of the exponential growth in internet traffic and the rapid progress of ‎network technology. A network attack occurs when a person gains illegal entry into a network. This includes any attempt to destroy the network, which might have disastrous consequences. Organizations depend significantly on tried-and-true network infrastructure security fea-‎tures like firewalls, encryption, and antivirus software. However, these strategies provide some defence against increasingly sophisti-‎cated attacks and viruses. Machine learning (ML) and deep learning (DL) are two important key concepts of artificial intelligence that gained ‎popularity around the turn of the century. The focus on statistical methodologies and data in these techniques may considerably improve ‎computing power by training computers to think like people. So, to address the inadequacies of non-intelligent solutions, computer ‎scientists started to use intelligent approaches in network security. This article provides a thorough examination of numerous deep learning ‎and machine learning methods for attack detection and classification.

Deep learning meets tree phenology modelling: PhenoFormer versus process‐based models

Abstract Predicting phenology, that is the timing of seasonal events of plant life such as leaf emergence and colouration in relation to climate fluctuations, is essential for anticipating future changes in carbon sequestration and tree vitality in temperate forest ecosystems. Existing approaches typically rely on either hypothesis‐driven process models or data‐driven statistical methods. Several studies have shown that process models outperform statistical methods when predicting under climatic conditions that differ from those of the training data, such as for climate change scenarios. However, in terms of statistical methods, deep learning approaches remain underexplored for species‐level phenology modelling. We present a deep neural architecture, PhenoFormer, for species‐level phenology prediction using meteorological time series. Our experiments utilise a country‐scale data set comprising 70 years of climate data and approximately 70,000 phenological observations of nine woody plant species, focussing on leaf emergence and colouration in Switzerland. We extensively compare PhenoFormer to 18 different process‐based models and traditional machine learning methods, including Random Forest (RF) and Gradient Boosted Machine (GBM). Our results demonstrate that PhenoFormer outperforms traditional statistical methods in phenology prediction while achieving significant improvements or comparable performance to the best process‐based models. When predicting under climatic conditions similar to the training data, our model improved over the best process‐based models by 6% normalised root‐mean‐squared error (nRMSE) for spring phenology and 7% nRMSE for autumn phenology. Under conditions involving substantial climatic shifts between training and testing (+1.21°C), PhenoFormer reduced the nRMSE by an average of 8% across species compared to RF and GBM, and performed on par with the best process models. These findings highlight the potential of deep learning for phenology modelling and call for further research in this direction, particularly for future climate projections. Meanwhile, the advancements achieved by PhenoFormer can provide valuable insights for anticipating species‐specific phenological responses to climate change.

Effect of Elevated Temperature on Physical Activity and Falls in Low-Income Older Adults Using Zero-Inflated Poisson and Graphical Models

High ambient temperature poses a significant public health challenge, particularly for low-income older adults (LOAs) with preexisting health and social issues and disproportionate living conditions, placing them at a vulnerable condition of heat-related illnesses and associated public health risks. This study aims to utilize advanced statistical regression and machine learning methods to analyze complex relationships between elevated temperature, physical activity (PA), sociodemographic factors and fall incidents among LOAs. We collected data from a cohort of 304 LOAs aged 60 and above, living in free-living conditions in low-income communities in Central Florida, USA. Zero-inflated Poisson regression was employed to examine the linear relationships, which reflect the zero-abundant nature of fall incidents. Then, an advanced machine learning approach—the mixed undirected graphical model (MUGM)—was employed to further explore the intricate, nonlinear relationships among daily PA, daily temperature, and fall incidents. The findings suggest that more moderate-to-vigorous PA is significantly associated with fewer fall incidents (RR = 0.90, 95% CI: (0.816, 0.993), p=0.037), after adjusting for other variables. In contrast, elevated temperature is strongly linked to a greater risk of falls (RR = 1.733, 95% CI: (1.581, 1.901), p < 0.0001), potentially reflecting seasonal influences. Although higher temperature increases fall events, this effect is mitigated among LOAs with increased sedentary behavior (p<0.0001). Additionally, findings from the MUGM reinforce the intricate nature of falls. Fall counts were highly correlated with race and positively associated with temperature, highlighting the importance of tailoring fall prevention strategies to account for seasonal variations and health disparities, and promoting PA.