Random Forest Machine Learning Model Research Articles

Ecosystem health assessment of East Kolkata Wetlands, India: Implications for environmental sustainability

The East Kolkata Wetlands (EKW) in Kolkata, India, span 12,500 ha and are a vital ecological zone providing several benefits, including water purification, flood control, and biodiversity support. This study investigated land use and land cover (LULC) alterations in the EKW from 1991 to 2023, using a random forest (RF) machine learning model. Significant LULC changes were observed over the 32 years, with wetland areas decreasing from 91.2 km2 in 1991 to 33.4 km2 in 2023, reflecting substantial habitat loss and reduced ecosystem services. Conversely, agricultural land expanded from 27.8 km2 to 58.7 km2, driven by economic and food production needs, and built-up areas increased dramatically from 0.2 km2 to 10.5 km2, indicating rapid urbanization. This study evaluated the health, resilience, and ecosystem functionality of EKW by analysing human-induced land use changes and using ecological indicators and landscape metrics. Landscape and class level metrics such as PLAND, largest patch index (LPI), total edge (TE), edge density (ED), number of patches (NP), and patch density (PD) were used to analyse the spatiotemporal dynamics of the wetlands. This study revealed a significant increase in fragmentation, with the number of patches increasing from 2689 in 1991 to 4532 in 2023, despite a consistent decrease in core wetland areas. Ecosystem health indicators, such as the ecosystem structure index (ESI) and landscape deviation degree (LDD), were used to assess landscape metrics and fragmentation changes. The ESI and other metrics revealed significant temporal fluctuations, providing insights into landscape structure, connectivity, and heterogeneity. The ESI improved from 0.87 in 1991 to 1.03 in 2023, indicating enhanced connectivity and diversity. Conversely, the LDD increased from 20.6% to 56.85%, indicating a shift towards impervious surfaces. The vegetation productivity and ecosystem health index (EHI) decreased, indicating biodiversity loss and reduced carbon sequestration. The EHI also dropped from 0.67 to 0.55, signifying ongoing environmental stress. This study emphasizes the need for conservation efforts to maintain the ecological integrity of the EKW amidst urbanization and land use changes and recommends a balanced approach for sustainable urban development and enhanced wetland resilience.

Interpretable Machine Learning Models for Prediction of UHPC Creep Behavior

The creep behavior of Ultra-High-Performance Concrete (UHPC) was investigated by machine learning (ML) and SHapley Additive exPlanations (SHAP). Important features were selected by feature importance analysis, including water-to-binder ratio, aggregate-to-cement ratio, compressive strength at loading age, elastic modulus at loading age, loading duration, steel fiber volume content, and curing temperature. Four typical ML models—Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting Machine (XGBoost), and Light Gradient Boosting Machine (LGBM)—were studied to predict the creep behavior of UHPC. Via Bayesian optimization and 5-fold cross-validation, the ML models were tuned to achieve high accuracy (R2 = 0.9847, 0.9627, 0.9898, and 0.9933 for RF, ANN, XGBoost, and LGBM, respectively). The contribution of different features to the creep behavior was ranked. Additionally, SHAP was utilized to interpret the predictions by the ML models, and four parameters stood out as the most influential for the creep coefficient: loading duration, curing temperature, compressive strength at loading age, and water-to-binder ratio. The SHAP results were consistent with theoretical understanding. Finally, the UHPC creep curves for three different cases were plotted based on the ML model developed, and the prediction by the ML model was more accurate than that by fib Model Code 2010.

Serum metabolomic profile of myasthenia gravis and potential values as biomarkers in disease monitoring

ObjectiveSerum metabolites from 19 myasthenia gravis (MG) patients and 15 normal controls were analyzed via untargeted metabolomics, including 6 pre/post-treatment paired MG patients, to assess the value of serum metabolites as biomarkers in monitoring MG. MethodDifferential metabolites between MG patients and normal controls were identified through liquid and gas chromatography-mass spectrometry simultaneously. Principal component analysis and orthogonal partial least squares-discriminant analysis were conducted to identify the differential metabolites. Candidate metabolites and pathways associated with MG were selected through a random forest machine learning model. ResultA total of 310 differential metabolites were identified with a threshold of variable projected importance > 1 and P value < 0.05. Among these, 158 metabolites were upregulated and 152 were downregulated. The random forest machine learning model selected 5 metabolites as potential biomarkers associated with MG: lignoceric acid (AUC=0.944), uridine diphosphate-N-acetylglucosamine (AUC=0.951), arachidonic acid (AUC=0.951), beta-glycerophosphoric acid (AUC=0.933), and L-Asparagine (AUC=0.877). Further analysis using 6 paired MG patients pre- and post-immunosuppression treatment revealed 25 upregulated and 6 downregulated metabolites in post-treatment serum, which might be relevant to disease intervention. The significance remains elusive due to the limited number of patients. ConclusionA subset of differential metabolites was identified in the serum of MG patients, some of which changed with immunosuppressive therapy. Small molecule metabolites may serve as valuable biomarkers for disease monitoring in MG.

Floating Litter detection at the Estuary of Puducherry using Sentinel-2 data and Machine Learning model

Marine Floating Litter (MFL) comprises synthetic polymers or plastic that are purposefully tossed out or inadvertently mislaid along rivers, drains, beaches, or other coastal environments that connect the marine ecosystem. Given the adverse impact of the chemicals involved in plastic manufacturing on the marine environment, including marine biota, the need to locate, track, and remove the floating plastic has become demanding. Increasing focus has been placed on remote sensing for its multispectral imaging with high resolution and its capability to monitor large areas systematically. Compared to old-fashioned in-situ observation, satellite imaging products are pecuniary and non-chronophagous. Therefore, the current study exploited the full functionality of open-source Sentinel-2 satellite-retrieved data to detect MFL. The Union Territory of Puducherry (Southern region of India) is the study location. Field measurements were collected from the Ariyankuppam River and the Chunnambar River. A spectral signature profile was created to distinguish other floating debris from floating plastic. The Floating Debris Index (FDI) and Plastic Index (PI) were modeled to validate the performance. It has been proven that FDI performs better at detecting MFL than PI. A Random Forest machine learning model was applied to classify water, plastic debris, and slurry debris. The overall observation of the model details the distribution percentage and accuracy assessment of the proposed model. The accuracy of classifying water, slurry debris, and plastic debris are 64.91%, 61.6%, and 96.71%, respectively, indicating room for improvement in classifying water and slurry debris. The proposed model is used for the first time at the Union Territory of Puducherry and is significantly more efficient compared to in-situ observation in terms of time, cost, and workforce.

Toxic effects of trace metal(loid) mixtures on aquatic organisms

The co-occurrence of metal (loid)s in realistic aquatic environments necessitates the evaluation of their combined effects. However, the generality of the additive effect hypothesis is contentious, particularly due to metal(loid)-metal(loid) interactions. The absence of systematic evaluation approaches restricts our ability to draw overall conclusions and make reliable predictions. In this study, we reviewed 1473 effect sizes from 38 publications, and classified all responses into seven main categories (from molecular to individual levels) according to their toxicological significance. Our meta-analysis revealed that metal(loid) mixtures had significant effects on aquatic organisms (33 %, 95 % CI 28 %–39 %, P < 0.05), along with significant response heterogeneity (Qt = 690,319.62, P < 0.0001; I2 = 99.95 %). Concurrently, we developed a Random Forest machine learning model to predict adverse effects and identify key variables. These two methods demonstrated that the toxicity of metal(loid) mixtures is primarily linked to the choice of toxicity endpoints, and the characteristics of metal(loid) mixtures. Our findings underscore the potential of combining meta-analysis with machine learning, a more systematic approach, to enhance the understanding and prediction of the adverse effects of metal(loid) mixtures, and they offer guidance for risk assessment and policy-making in complex environmental scenarios.

Prediction of Histological Grade of Oral Squamous Cell Carcinoma Using Machine Learning Models Applied to 18F-FDG-PET Radiomics

The histological grade of oral squamous cell carcinoma affects the prognosis. In the present study, we performed a radiomics analysis to extract features from 18F-FDG PET image data, created machine learning models from the features, and verified the accuracy of the prediction of the histological grade of oral squamous cell carcinoma. The subjects were 191 patients in whom an 18F-FDG-PET examination was performed preoperatively and a histopathological grade was confirmed after surgery, and their tumor sizes were sufficient for a radiomics analysis. These patients were split in a 70%/30% ratio for use as training data and testing data, respectively. We extracted 2993 radiomics features from the PET images of each patient. Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) machine learning models were created. The areas under the curve obtained from receiver operating characteristic curves for the prediction of the histological grade of oral squamous cell carcinoma were 0.72, 0.71, 0.84, 0.74, and 0.73 for LR, SVM, RF, NB, and KNN, respectively. We confirmed that a PET radiomics analysis is useful for the preoperative prediction of the histological grade of oral squamous cell carcinoma.

Unmasking The Enigma:Exploring Personality Traits Using Social Media Text

In this paper personality is an important parameter as it differentiates various individuals from another. Predicting personality has many applications in real world. The main objective of this project is to take textual data as input from the user and then run the trained machine learning model on this data to predict his four personality traits which are Introversion vs Extroversion, Sensing vs Intuition, Thinking vs Feeling, Judging vs Perceiving.The main objective is to build an application where users can answer the questions which are processed and analyzed to output his personality traits. The output is a string of four characters where each character determines a personality trait, total of sixteen personality types are possible.The Machine learning model Random Forest Classifier is used to classify the text and output four personality traits. Processing of large textual data is to be done using Natural Language Processing (NLP) techniques with the help of NLTK libraries to process and categorize the data. In order to increase the performance of the model hyper parameter tuning along with cross fold validations is done. Keywords: Random Forest, Natural Language Processing, Text

A STUDY ON SUPPLIER EVALUATION PROCESS IN FOOTWEAR MANUFACTURING INDUSTRY

This study introduces an innovative supplier evaluation approach for footwear manufacturing by integrating the SCOR 4.0 model with machine learning techniques. The SCOR 4.0 model, combined with the Best Worst Method (BWM), provides a structured framework for evaluating suppliers across various dimensions. A Random Forest (RF) machine learning model is then used to classify and rank suppliers based on performance ratings. The results show that the RF algorithm effectively identifies suitable suppliers, with lower rejection scores indicating superior performance. This integration enhances supplier evaluation processes and offers valuable insights for supply chain management in the footwear industry. Key Words: Supplier evaluation, SCOR 4.0 model, Best-worst method (BWM), Random Forest (RF), Supplier Rejection score

Monitoring of Low Chl-a Concentration in Hulun Lake Based on Fusion of Remote Sensing Satellite and Ground Observation Data

China’s northern Hulun Lake is a significant body of water internationally. The issue of eutrophication has gained prominence in recent years. The achievement of precise chlorophyll-a (Chl-a) monitoring is crucial for safeguarding Hulun Lake’s ecosystem. The machine learning-based remote sensing inversion method has been shown to be effective in capturing the intricate relationship between independent and dependent variables; however, it lacks a priori knowledge and is limited by the quality of remote sensing data sources. The relationship between independent and dependent variables can be more accurately simulated with the use of suitable auxiliary variables. Therefore, three machine learning models—random forest (RF), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost)—were established in this study using meteorological observation parameters as auxiliary variables combined with Sentinel-2 satellite image remote sensing band combinations as independent variables and measured Chl-a data as dependent variables. The estimation effects before and after the fusion of meteorological ground observation data were compared, and the best model was used to estimate the spatial–temporal variation trend of Chl-a in the regional water body. The results show that (1) the addition of meteorological parameters as auxiliary variables improved the precision of the three machine models; the decision coefficient (R2) rose by 7.25%, 5.71%, and 7.20%, respectively, to 0.76, 0.66, and 0.73. (2) The concentration of Chl-a in the lake region was projected from June to October 2019 to October 2021 using the RF optimal estimating model of meteorological fusion. The northeast, southwest, and south of the lake were where the comparatively high concentration values of Chl-a were located, whereas the lake’s center had a generally low concentration of the substance. Chromatically, Chl-a typically peaked in August after initially increasing and then declining. (3) The three rivers that feed into the river have varying levels of water pollution, with chemical oxygen demand (COD) and total nitrogen (TN) pollution being the most severe. This is what primarily caused the higher levels of Chl-a in the northeast, southwest, and south. This study is crucial for the preservation and restoration of Hulun Lake’s natural ecosystem and offers some technical support for the monitoring of the lake’s concentration of Chl-a.

Quantitative microbiome profiling of honey bee (Apis mellifera) guts is predictive of winter colony loss in northern Virginia (USA)

For the past 15 years, the proportion of honey bee hives that fail to survive winter has averaged ~ 30% in the United States. Winter hive loss has significant negative impacts on agriculture, the economy, and ecosystems. Compared to other factors, the role of honey bee gut microbial communities in driving winter hive loss has received little attention. We investigate the relationship between winter survival and honey bee gut microbiome composition of 168 honey bees from 23 hives, nine of which failed to survive through winter 2022. We found that there was a substantial difference in the abundance and community composition of honey bee gut microbiomes based on hive condition, i.e., winter survival or failure. The overall microbial abundance, as assessed using Quantitative Microbiome Profiling (QMP), was significantly greater in hives that survived winter 2022 than in those that failed, and the average overall abundance of each of ten bacterial genera was also greater in surviving hives. There were no significant differences in alpha diversity based on hive condition, but there was a highly significant difference in beta diversity. The bacterial genera Commensalibacter and Snodgrassella were positively associated with winter hive survival. Logistic regression and random forest machine learning models on pooled ASV counts for the genus data were highly predictive of winter outcome, although model performance decreased when samples from the location with no hive failures were excluded from analysis. As a whole, our results show that the abundance and community composition of honey bee gut microbiota is associated with winter hive loss, and can potentially be used as a diagnostic tool in evaluating hive health prior to the onset of winter. Future work on the functional characterization of the honey bee gut microbiome’s role in winter survival is warranted.

Preoperative prediction model for risk of readmission after total joint replacement surgery: a random forest approach leveraging NLP and unfairness mitigation for improved patient care and cost-effectiveness

BackgroundThe Center for Medicare and Medicaid Services (CMS) imposes payment penalties for readmissions following total joint replacement surgeries. This study focuses on total hip, knee, and shoulder arthroplasty procedures as they account for most joint replacement surgeries. Apart from being a burden to healthcare systems, readmissions are also troublesome for patients. There are several studies which only utilized structured data from Electronic Health Records (EHR) without considering any gender and payor bias adjustments.MethodsFor this study, dataset of 38,581 total knee, hip, and shoulder replacement surgeries performed from 2015 to 2021 at Novant Health was gathered. This data was used to train a random forest machine learning model to predict the combined endpoint of emergency department (ED) visit or unplanned readmissions within 30 days of discharge or discharge to Skilled Nursing Facility (SNF) following the surgery. 98 features of laboratory results, diagnoses, vitals, medications, and utilization history were extracted. A natural language processing (NLP) model finetuned from Clinical BERT was used to generate an NLP risk score feature for each patient based on their clinical notes. To address societal biases, a feature bias analysis was performed in conjunction with propensity score matching. A threshold optimization algorithm from the Fairlearn toolkit was used to mitigate gender and payor biases to promote fairness in predictions.ResultsThe model achieved an Area Under the Receiver Operating characteristic Curve (AUROC) of 0.738 (95% confidence interval, 0.724 to 0.754) and an Area Under the Precision-Recall Curve (AUPRC) of 0.406 (95% confidence interval, 0.384 to 0.433). Considering an outcome prevalence of 16%, these metrics indicate the model’s ability to accurately discriminate between readmission and non-readmission cases within the context of total arthroplasty surgeries while adjusting patient scores in the model to mitigate bias based on patient gender and payor.ConclusionThis work culminated in a model that identifies the most predictive and protective features associated with the combined endpoint. This model serves as a tool to empower healthcare providers to proactively intervene based on these influential factors without introducing bias towards protected patient classes, effectively mitigating the risk of negative outcomes and ultimately improving quality of care regardless of socioeconomic factors.

Determining target levels of power distribution system reliability indices using machine learning

Electrical distribution system (EDS) reliability has always been a critical subject due to the considerable share of distribution systems in power interruptions to end-users. Meeting regulatory service quality standards requires distribution companies to achieve defined reliability levels for performance improvement. Conventionally, specialists determine target reliability based on experience, experimental knowledge, and rules of thumb. However, these methods are error-prone and may result in suboptimal investments, economic inefficiency, and inadequate resource allocation in EDS operation and planning. Accordingly, this paper presents a machine learning-based method to determine the target level for EDS's reliability indices based on its historical performance. The approach involves comprehensive analysis of historical EDS reliability data, followed by a data envelopment analysis (DEA) to assess performance across subdivisions like substations or feeders, identifying the most effective units. Subsequently, machine learning models—Random Forest (RF), Support Vector Machine (SVM), and Radial Basis Function (RBF) network—are trained on optimal subdivisions from the DEA stage. These models accurately estimate target reliability for all subdivisions, contributing to the overall determination of the EDS target reliability level. A three-scenario case study validates the proposed method, suggesting its potential applicability as a valuable tool for regulatory agencies in setting EDS reliability targets. While admitting the potential challenges, notably the method's reliance on the quality and completeness of the historical data collected by distribution companies, the paper emphasizes the importance of collaborative efforts to ensure data accuracy and sufficiency. The proposed method leads to a fair mechanism to determine the target level for a real EDS's reliability indices in comparison with a business-as-usual scenario. Moreover, it provides a reliability performance ranking for the EDS's subdivisions.

Using machine learning models to estimate Escherichia coli concentration in an irrigation pond from water quality and drone-based RGB imagery data

The rapid and efficient quantification of Escherichia coli concentrations is crucial for monitoring water quality. Remote sensing techniques and machine learning algorithms have been used to detect E. coli in water and estimate its concentrations. The application of these approaches, however, is challenged by limited sample availability and unbalanced water quality datasets. In this study, we estimated the E. coli concentration in an irrigation pond in Maryland, USA, during the summer season using demosaiced natural color (red, green, and blue: RGB) imagery in the visible and infrared spectral ranges, and a set of 14 water quality parameters. We did this by deploying four machine learning models – Random Forest (RF), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGB), and K-nearest Neighbor (KNN) – under three data utilization scenarios: water quality parameters only, combined water quality and small unmanned aircraft system (sUAS)-based RGB data, and RGB data only. To select the training and test datasets, we applied two data-splitting methods: ordinary and quantile data splitting. These methods provided a constant splitting ratio in each decile of the E. coli concentration distribution. Quantile data splitting resulted in better model performance metrics and smaller differences between the metrics for both the training and testing datasets. When trained with quantile data splitting after hyperparameter optimization, models RF, GBM, and XGB had R2 values above 0.847 for the training dataset and above 0.689 for the test dataset. The combination of water quality and RGB imagery data resulted in a higher R2 value (>0.896) for the test dataset. Shapley additive explanations (SHAP) of the relative importance of variables revealed that the visible blue spectrum intensity and water temperature were the most influential parameters in the RF model. Demosaiced RGB imagery served as a useful predictor of E. coli concentration in the studied irrigation pond

Comparison and analysis of prediction accuracy between traditional machine learning algorithms and XGBoost algorithm in music emotion classification

Music emotion classification refers to determining the emotional types of music, such as happiness, sadness, anger, and passion, based on aspects like rhythm, melody, and tone. The development of artificial intelligence can be applied to music recommendation by employing machine learning algorithms to ascertain emotional attributes of music, enabling precise music suggestions for users to enhance their musical experience. This paper compares and analyzes the classification performance of traditional Random Forest machine learning algorithms and the XGBoost model on a Turkish music emotion dataset. We selected a comprehensive dataset from Kaggle, containing a vast array of music samples and their corresponding emotional labels, making it an extensive music emotion classification dataset. From the experimental results, it's evident that the traditional Random Forest machine learning model outperforms the XGBoost model in terms of accuracy, precision, and recall. The accuracy of the traditional Random Forest machine learning model stands at 80.8%, whereas the XGBoost model's accuracy is 75%. The recall rate for the traditional Random Forest machine learning model is 80.8%, while for XGBoost, it's 77.2%. The F1 score for the traditional Random Forest machine learning model is 80.5%, whereas for XGBoost, it's 75.3%. These parameters indicate that the traditional Random Forest machine learning model exhibits superior predictive performance in music emotion classification. However, the XGBoost model possesses its own advantages, such as faster learning and prediction speeds, high accuracy, and strong generalization capabilities. In summary, the traditional Random Forest machine learning model demonstrates better robustness and interpretability, effectively handling samples with noise and missing data, thus finding widespread practical application. On the other hand, the XGBoost model excels in rapid training and prediction, coupled with higher accuracy and versatility, making it advantageous in dealing with large datasets. The research outcomes of this paper hold significant importance for the study and application of music emotion classification. The experimental results presented herein offer valuable insights for researchers and practitioners, aiding them in selecting appropriate machine learning models, optimizing, and adjusting them to achieve the best classification results.

Relatedness and product complexity meet gravity models of international trade

Researchers have long used gravity models to analyze international trade patterns, identify export opportunities, and negotiate trade agreements. Recent research has emphasized the significance of relatedness and product complexity research in developing robust economic development strategies. This paper presents a novel approach, incorporating relatedness and product complexity as integral elements for interpreting export potential within gravity models powered by machine learning. Our approach stands out for its proficiency in accurately predicting bilateral trade values at a detailed product group level, providing valuable insights for policymakers and other stakeholders. The research leverages random forest machine learning models for predictions and incorporates relatedness and complexity to reveal new dimensions in international trade analysis.

Role of environmental and stand factors on forest dieback: An approach using structural equation modelling and machine learning

The Zagros forest region in western Iran is facing dieback processes, impacting both the environment and the local economy. Understanding the cause of forest dieback remains a challenge for forest experts due to the wide set of factors usually involved in the dieback phenomenon. To achieve this goal, we measured woody species dieback intensity (DI) using 124 plots distributed in oak forests across a wide range of environmental conditions. On these plots, we measured stand and vegetation factors (e.g. woody species richness, WSR), various soil properties and topographic indices (in particular the SAGA wetness index) and climatic factors. We then modeled dieback intensity using structural equation modeling (SEM) and machine learning (ML). We found a significant positive correlation between WSR and DI (r=0.48), and very low to low but still significant negative correlations with the SAGA wetness index (r=-0.10) and soil clay content (r=-0.16), respectively. Other soil properties and climate factors showed no significant influence on DI. After six rounds of respecification, the SEM fitting gave satisfactory results based on the validation map of DI indices (Goodness-of-fit Index = 0.948 and Comparative fit index =0.958). The DI map was generated using a random forest (RF) machine learning model to achieve an accuracy of 75% and a kappa index of 0.45, and then categorized into four classes. The map showed that the intensity of dieback was contrasting in our area: 41.1% of plots had no dieback, 58.4% had low DI, and less than 1% had moderate or high DI. We also found that soil clay content and woody species richness were crucial factors, explaining around 50% of the variance in DI. In conclusion, combining the methods from SEM and RF models provides an efficient approach to understand and identify key factors in the complex process of dieback.

Prediction of soil organic carbon using machine learning techniques and geospatial data for sustainable agriculture

Sustainable agriculture revolves around soil organic carbon (SOC), which is essential for numerous soil functions and ecological attributes. Farmers are interested in conserving and adding additional soil organic carbon to certain fields in order to improve soil health and productivity. The relationship between soil and environment that has been discovered and standardized throughout time has enhanced the progress of digital soil-mapping techniques; therefore, a variety of machine learning techniques are used to predict soil properties. Studies are thriving at how effectively each machine learning method maps and predicts SOC, especially at high spatial resolutions. To predict SOC of soil at a 30 m resolution, four machine learning models—Random Forest, Support Vector Machine, Adaptive Boosting, and k-Nearest Neighbour were used. For model evaluation, two error metrics, namely R2 and RMSE have been used. The findings demonstrated that the calibration and validation sets’ descriptive statistics sufficiently resembled the entire set of data. The range of the calculated SOC content was 0.06 to 1.76 %. According to the findings of the study, Random Forest showed good results for both cases, i.e. evaluation using cross validation and without cross validation. Using cross validation, RF confirmed highest R2 as 0.5278 and lowest RMSE as 0.1683 for calibration dataset while without cross validation it showed R2 as 0.8612 and lowest RMSE as 0.0912 for calibration dataset. The generated soil maps will help farmers adopt precise knowledge for decisions that will increase farm productivity and provide food security through the sustainable use of nutrients and the agricultural environment.

Characterizing land use/land cover change dynamics by an enhanced random forest machine learning model: a Google Earth Engine implementation

Land use and land cover (LULC) analysis is crucial for understanding societal development and assessing changes during the Anthropocene era. Conventional LULC mapping faces challenges in capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of the descriptions of LULC changes, this investigation employed a combination of advanced techniques. Specifically, multitemporal 30 m resolution Landsat-8 satellite imagery was utilized, in addition to the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, the study incorporated the random forest (RF) algorithm. This study aimed to generate continuous LULC maps for 2014 and 2020 for the Shrirampur area of Maharashtra, India. A novel multiple composite RF approach based on LULC classification was utilized to generate the final LULC classification maps utilizing the RF-50 and RF-100 tree models. Both RF models utilized seven input bands (B1 to B7) as the dataset for LULC classification. By incorporating these bands, the models were able to influence the spectral information captured by each band to classify the LULC categories accurately. The inclusion of multiple bands enhanced the discrimination capabilities of the classifiers, increasing the comprehensiveness of the assessment of the LULC classes. The analysis indicated that RF-100 exhibited higher training and validation/testing accuracy for 2014 and 2020 (0.99 and 0.79/0.80, respectively). The study further revealed that agricultural land, built-up land, and water bodies have changed adequately and have undergone substantial variation among the LULC classes in the study area. Overall, this research provides novel insights into the application of machine learning (ML) models for LULC mapping and emphasizes the importance of selecting the optimal tree combination for enhancing the accuracy and reliability of LULC maps based on the GEE and different RF tree models. The present investigation further enabled the interpretation of pixel-level LULC interactions while improving image classification accuracy and suggested the best models for the classification of LULC maps through the identification of changes in LULC classes.

Community coalescence and plant host filtering determine the spread of tetracycline resistance genes from pig manure into the microbiome continuum of the soil–plant system

The spread of livestock manure-borne antibiotic resistance genes (ARGs) into agroecosystems through manure application poses a potential threat to human health. However, there is still a knowledge gap concerning ARG dissemination in coalescing manure, soil and plant microbiomes. Here, we examined the fate of tetracycline resistance genes (TRGs) originating from pig manure microbiomes and spread in the soil-A thaliana system and explored the effects of microbial functions on TRGs spread at different interfaces. Our results indicate that the TRGs abundances in all microbiome continuum of the soil-A. thaliana system were significantly increased with the application of a living manure microbiome, although the addition of manure with both an active and inactive microbiome caused a shift in the microbial community composition. This was attributed to the increasing relative abundances of tetA, tetL, tetM, tetO, tetW and tolC in the system. The application of living manure with DOX residues resulted in the highest relative abundance of total TRGs (3.30×10−3 copies/16S rRNA gene copies) in the rhizosphere soil samples. Community coalescence of the manure and soil microbiomes increased the abundance of Firmicutes in the soil and root microbiome, which directly explains the increase in TRG abundance observed in these interfaces. In contrast, the leaf microbiome differed markedly from that of the remaining samples, indicating strong plant host filtering effects on Firmicutes and TRGs from pig manure. The random forest machine learning model revealed microbial functions and their significant positive correlation with TRG abundance in the microbiome continuum of the system. Our findings revealed that community coalescence is the main driver of TRG spread from manure to the soil and root microbiomes. Plant host filtering effects play a crucial role in allowing certain microbial groups to occupy ecological niches in the leaves, thereby limiting the establishment of manure-borne TRGs in aboveground plant tissues.

Predicting in-hospital mortality among patients admitted with a diagnosis of heart failure: a machine learning approach.

Existing risk prediction models for hospitalized heart failure patients are limited. We identified patients hospitalized with a diagnosis of heart failure between 7 May 2013 and 26 April 2022 from a large academic, quaternary care medical centre (training cohort). Demographics, medical comorbidities, vitals, and labs were collected and were used to construct random forest machine learning models to predict in-hospital mortality. Models were compared with logistic regression, and to commonly used heart failure risk scores. The models were subsequently validated in patients hospitalized with a diagnosis of heart failure from a second academic, community medical centre (validation cohort). The entire cohort comprised 21802 patients, of which 14539 were in the training cohort and 7263 were in the validation cohort. The median age (25th-75th percentile) was 70 (58-82) for the entire cohort, 43.2% were female, and 6.7% experienced inpatient mortality. In the overall cohort, 7621 (35.0%) patients had heart failure with reduced ejection fraction (EF≤40%), 1271 (5.8%) had heart failure with mildly reduced EF (EF 41-49%), and 12910 (59.2%) had heart failure with preserved EF (EF≥50%). Random forest models in the validation cohort demonstrated a c-statistic (95% confidence interval) of 0.96 (0.95-0.97), sensitivity (SN) of 87.3%, and specificity (SP) of 90.6% for the prediction of in-hospital mortality. Models for those with HFrEF demonstrated a c-statistic of 0.96 (0.94-0.98), SN 88.2%, and SP 91.0%, and those for patients with HFpEF showed a c-statistic of 0.95 (0.93-0.97), SN 87.4%, and SP 89.5% for predicting in-hospital mortality. The random forest model significantly outperformed logistic regression (c-statistic 0.87, SN 75.9%, and SP 86.9%), and current existing risk scores including the Acute Decompensated Heart Failure National Registry risk score (c-statistic of 0.70, SN 69%, and SP 62%), and the Get With the Guidelines-Heart Failure risk score (c-statistic 0.69, SN 67%, and SP 63%); P<0.001 for comparison. Machine learning models built from commonly recorded patient information can accurately predict in-hospital mortality among patients hospitalized with a diagnosis of heart failure.