Random Forest Regression Research Articles

Establishing Optimal Machine Learning Models for Monitoring Water Quality in Vietnam’s Upper Ma River

This study aims to establish the optimal regression model for predicting total suspended solids (TSS) and Turbidity based on in situ data and spectral regions of Sentinel-2 images. Various machine learning models were evaluated, including Multilayer Perceptron Regression (MLPR), Random Forest Regression (RFR), AdaBoost Regression (ABR), Multiple Linear Regression (MLR), and K-Nearest Neighbors Regression (KNNR). These models were applied to different band combinations of spectral regions: visible (VIS), near-infrared (NIR), shortwave-infrared (SWIR), VIS+NIR (VNIR), and VIS+NIR+SWIR (VNIR+SWIR). The study results revealed that the MLR model, while not the best performer during training (R2 = 0.89 for TSS and R2 = 0.66 for turbidity), did not exhibit overfitting, with corresponding R² values in testing being 0.80 and 0.42, respectively. Variable selection for MLR models identified optimal spectral bands: B3, B5, B6, B8, B11, and B12 for TSS, and B4, B8, B11, and B12 for Turbidity. The final no-intercept multiple linear regression models achieved R2 = 0.88 for TSS and R2 = 0.62 for turbidity. Performance metrics for TSS were superior, with lower MAE, MSE, and RMSE compared to Turbidity. This study underscores the efficacy of using MLR models with selected spectral bands for accurate and generalizable predictions of TSS and turbidity.

Analyzing the Complexity of US Federal Debt

The United States federal debt has witnessed a significant surge over recent decades. This study delves into inquiries regarding the persistent patterns in federal debt, key factors driving this alarming trend, and the optimal timing for implementing corrective measures to mitigate its speeding flight. Utilizing modern machine learning techniques, notably Random Forest (RF) and Support Vector Regression (SVR), alongside conventional statistical forecasting techniques, the research aims to predict future trends. It emphasizes the critical role of business analytic thinking in deciphering fiscal system-based complexities. To address the mounting challenges, these research findings underscore the urgent necessity for efficacious policies to oversee them.

Enhancing Supply Chain Efficiency with Predictive Analytics: A Machine Learning Approach to Dynamic Lead Time Prediction in a Chemical Industry

We develop and employ a four-step methodological approach for predicting the lead time delays in all echelons of a supply chain (SC). The first step of the methodological approach involves a critical synthesis of academic research efforts for identifying the main sources of delays in all echelons of a supply chain. The second step involves the development of questionnaires for validating the findings of the research through workshops with industry stakeholders. The third step involves the development of a suite of machine learning (ML) models, namely, Random Forest Regression, Decision Tree Regression, and Linear Regression. These models were selected based on their prevalence in the recent literature and their ability to handle linear and nonlinear relationships between multiple variables. The final fourth step involves the implementation of the suite of machine learning models in the real case of a Hellenic chemical manufacturing supply chain. The implementation results reveal that Random Forest Regression exhibits the highest predictive accuracy throughout all stages of the supply chain, achieving the lowest Mean Absolute Percentage Errors (MAPE), ranging from 0.5 to 7% in the examined supply chain echelons.

Machine Learning-Based Software for Predicting Pseudomonas spp. Growth Dynamics in Culture Media

In predictive microbiology, both primary and secondary models are widely used to estimate microbial growth, often applied through two-step or one-step modelling approaches. This study focused on developing a tool to predict the growth of Pseudomonas spp., a prominent bacterial genus in food spoilage, by applying machine learning regression models, including Support Vector Regression (SVR), Random Forest Regression (RFR) and Gaussian Process Regression (GPR). The key environmental factors—temperature, water activity, and pH—served as predictor variables to model the growth of Pseudomonas spp. in culture media. To assess model performance, these machine learning approaches were compared with traditional models, namely the Gompertz, Logistic, Baranyi, and Huang models, using statistical indicators such as the adjusted coefficient of determination (R2adj) and root mean square error (RMSE). Machine learning models provided superior accuracy over traditional approaches, with R2adj values from 0.834 to 0.959 and RMSE values between 0.005 and 0.010, showcasing their ability to handle complex growth patterns more effectively. GPR emerged as the most accurate model for both training and testing datasets. In external validation, additional statistical indices (bias factor, Bf: 0.998 to 1.047; accuracy factor, Af: 1.100 to 1.167) further supported GPR as a reliable alternative for microbial growth prediction. This machine learning-driven approach bypasses the need for the secondary modelling step required in traditional methods, highlighting its potential as a robust tool in predictive microbiology.

Leakage prediction approach and influencing factor analysis from seal test

Purpose Leakage serves as a core indicator of sealing performance degradation, particularly under high-speed and heavy-duty operational where increased leakage is common. Within heavy-duty vehicle transmissions, the leakage can lead to excessive pressure loss and eventual transmission failure. This study aims to introduce a predictive method for assessing sealing ring leakage in vehicle transmissions based on operating conditions. Design/methodology/approach Seal test was carried out using a specialized seal test rig. Various data points were collected during this test, including leakage, friction torque, oil temperature, oil pressure and rotating speed. The collected data underwent noise separation and reconstruction using the complete ensemble empirical mode decomposition with adaptive noise method. Subsequently, a leakage prediction model is developed using the random forest regression with parameter optimization. A quantitative evaluation for influencing factors in leakage prediction process is investigated. Findings The results achieve a mean accuracy index exceeding 95%, demonstrating close alignment between predicted and actual leakage values. Feature contribution results highlight that the trends of the oil temperature, friction torque and oil pressure significantly affect the leakage prediction, with the oil temperature trend exerting the most substantial influence. Originality/value This work sheds light on the interplay between operating conditions and sealing performance degradation, offering valuable insights for understanding and addressing sealing issues effectively. Peer review The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-07-2024-0271/

Assessment of CCMP in Capturing High Winds with Respect to Individual Satellite Datasets

High-wind structures were identified in the Cross-Calibrated Multi-Platform (CCMP) ocean wind vector reanalysis for comparison with winds measured by satellite radiometers, scatterometers, and synthetic aperture radar (SAR) instruments from February to October 2023. The comparison aims to evaluate bias, uncertainty, and spatial correlations with the goal of enhancing the accuracy of ocean wind datasets during tropical cyclones (TCs). In 10° longitude × 10° latitude blocks, each containing a TC, Soil Moisture Active Passive (SMAP) and Advanced Microwave Scanning Radiometer 2 (AMSR2) winds are 6.5 and 4.8% higher than CCMP, while Advanced Scatterometer (ASCATB) is 0.8% lower. For extratropical cyclones, AMSR2 and SMAP also show stronger winds with a 5% difference, and ASCATB is about 0.3% weaker compared to CCMP. The comparison between SAR and CCMP for TC winds, sampled at the locations and time frames of SAR tiles, indicates that SAR winds around TCs are about 9% higher than CCMP winds. Using empirically defined TC structural indices, we find that the TCs observed by CCMP are shifted in locations and lack a compact core region. A Random Forest (RF) regressor was applied to TCs in CCMP with corresponding SAR observations, nearly correcting the full magnitude of low bias in CCMP statistically, with a 15 m/s correction in the core region. The hierarchy of importance among the predictors is as follows: CCMP wind speed (62%), distance of SAR pixels to the eye region (21%) and eye center (7%), and distance of CCMP pixels to the eye region (5%) and eye center (5%).

Predictive Urban Air Quality Monitoring for Healthier Cities

The research work proposal outlines an innovative and crucial project for addressing urban air quality issues using advanced technological solutions. Establishing a real-time air quality monitoring system with integrated big data and machine learning will enable precise tracking and analysis of pollution levels. The research paper begins with the key aspects of air quality. It further focuses upon the need for utilizing advanced techniques to curb the issues due to poor air quality. A system is proposed to determine the air quality utilizing machine learning techniques, predicting the quality of air index. Evaluation measures are then undertaken for predicting the same using Random forest, Support vector and Catboost regression techniques.

Machine-learning-aided biochar production from aquatic biomass

AbstractModeling hydrothermal carbonization (HTC) and pyrolysis carbonization (PLC) for the conversion of biomass into high-quality biochar for various applications shows promise. Unlike the extensive modeling studies on lignocellulosic biomass, research on aquatic biomass (AB) had not been reported until now. In this study, we compiled 586 data points from existing literature and trained five tree-based models to predict the yields of hydrochar and pyrochar and their properties, including nitrogen recovery degree, energy density, energy recovery degree, and residual sulfur degree, based on 10 feedstock and process parameters. The random forest regression (RFR) model demonstrated the highest predictive accuracy among these models. It achieved R2 values ranging from 0.89 to 0.98 for hydrochar yield, nitrogen recovery degree of hydrochar, energy recovery degree of hydrochar, and residual sulfur degree of hydrochar. The extreme gradient boosting (XGB) model also showed exemplary performance, with R2 values between 0.84 and 0.94 for energy density of hydrochar, pyrochar yield, and nitrogen recovery degree of pyrochar. Results on feature importance highlighted that, beyond the well-documented impact of process parameters, the properties of biochar were significantly influenced by the elemental compositions, such as nitrogen and sulfur contents of the feedstock. The relationship between these factors was further elucidated using partial dependence plots. Finally, we used RFR model for hydrochar yield and XGB model for pyrochar yield as examples, to test generalization ability of developed models with new data, further explaining their application methods. Overall, this study provided valuable insights into predicting and understanding the HTC and PLC processes of AB to produce high-quality biochar for various applications using low resources and time costs. Besides, we presented an iterative learning application method where the developed models demonstrated exceptionally high performance with new data. This method is highly versatile and can be adopted across various directions in the field of machine learning. Graphical Abstract

Combining Sentinel-2 and diverse environmental data largely improved aboveground biomass estimation in China's boreal forests.

Accurately mapping aboveground biomass (AGB) in China's boreal forests is crucial for assessing global carbon stock and formulating forest management strategies but remains challenging as the environmental heterogeneity complicates AGB estimation. Here, we investigated the relative gains of integrating Sentinel-2 and environmental data, as well as synthetic aperture radar (SAR) images to map AGB in China's boreal forests. We used two machine learning algorithms, random forest and gradient boosting regression (GBR), and four dataset combinations to develop the AGB models, then evaluated the AGB map by carrying on uncertainty analysis and comparing it with existing AGB products. Results showed that the GBR model based on Sentinel-2 and environmental data presented the best AGB estimation capability (R2: 0.75, RMSE: 23.60 Mg/ha), while further adding SAR images had negative effects on the model improvement. The Tasseled Cap Distance, short-wave infrared from Sentinel-2, Black dragon fire disturbance, Elevation, and Geographic locations were found to be significant contributors to AGB prediction. Our AGB estimates exhibited moderate to low uncertainty and outperformed other existing AGB maps in China's boreal forests based on independent validation assessment. The AGB distribution presented a noticeable south-north gradient difference, ranging from 3.23 to 346.37 Mg/ha. This study provides new insight into AGB estimation through the integration of Sentinel-2 imagery and multiple environmental data and offers a basis for sustainable management in China's boreal forests.

Machine learning algorithms for optimization of magnetocaloric effect in all-d-metal Heusler alloys

This study examines the application of machine learning algorithms, specifically the Random Forest regression model, to optimize the magnetocaloric effect in all-d-metal Heusler alloys. The model was trained using descriptors related to the mean properties of individual atoms, the properties of simple compounds in their ground state, and measures of chemical disorder. It demonstrated high accuracy in predicting structural properties, while exhibiting moderate accuracy in predicting magnetic properties. To identify optimal alloy compositions, a genetic algorithm was used to find those with the greatest differences in magnetization during martensitic transitions. Using this combined approach, the Ni–Co–Mn–Ti alloy system was thoroughly explored, resulting in the discovery of an alloy with a maximum magnetization difference. These results are consistent with previous research based on density functional theory and highlight the effectiveness of integrating machine learning with genetic algorithms for the discovery of new materials with outstanding magnetocaloric properties. The study emphasizes the need for further refinement of models capable of accurately predicting complex magnetic interactions, which is essential for fully leveraging the potential of all-d-metal Heusler alloys in practical applications.

Forecasting Electric Vehicle Adoption in the USA Using Machine Learning Models

Electric vehicles (Electric Vehicles) are at the vanguard of the global dispensation to sustainable transportation, depicting a pivotal step toward diminishing greenhouse gas emissions and reliance on fossil fuels. Notwithstanding, the adoption of Electric Vehicles has been growing in the USA, but their future remains at a crossroads. The objective of the research is to design and execute machine learning models capable of providing accurate predictions of future trends in electric vehicle adoption in the USA. The dataset gathered for analyzing EV adoption in the USA comprises data across three primary categories: environmental data, economic indicators, and policy-related data. The economic indicators include household income, fuel prices, electricity rates, and lithium battery costs that affect EV purchasing power obtained from the U.S. Census Bureau and the U.S. Energy Information Administration (EIA). Environmental data include greenhouse gas emissions and air quality indices from the EPA, providing information on regional environmental conditions that might affect EV attractiveness. Other policy data included federal and state incentives such as tax credits, rebates, and EV infrastructure data, collected from the U.S. Led by the U.S. Department of Energy's Alternative Fuels Data Center and the Energy Laboratory, additional EV sales trends were pulled from databases of the automotive industry. In this research project, credible and proven machine learning models were employed, most notably, Linear Regression, Random Forest, and XG-Boost. The performance of the models was tested for EV adoption prediction by considering a few important metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). From the model performance metrics presented, the Gradient Boosting Regressor and Random Forest models performed far better by a big margin than Linear Regression. The prediction models, particularly, the Random Forest regressors and Gradient Boosting regressors demonstrated incredible forecasting of electric vehicle adoption. The model works excellently on the premise that historical data with relevant features can be utilized to gain some valuable insight into future trends. Policy-makers interested in stimulating the wider use of electric vehicles can ensure that targeted policies address both current barriers and future demands. Results of this analysis suggest incentives, such as tax credits, rebates, and subsidies, are some of the most common actions to reduce the upfront cost of an EV, a key circumventing factor in the choice that many consumers face.

COMPARATIVE ANALYSIS OF RF, SVR WITH GAUSSIAN KERNEL AND LSTM FOR PREDICTING LOAN DEFAULTS

This investigation elucidates the paramount endeavour of predicting loan defaults, which is imperative for the efficacious management of financial risk and the overall stability of financial institutions. Conventional statistical methodologies frequently encounter challenges in effectively capturing the nonlinear and sequential dynamics inherent in financial data, thereby necessitating the examination of more sophisticated machine learning methodologies. This research reports an experimental-based comparative evaluation of three ML and DL models—Long Short-Term Memory (LSTM) networks, Random Forest (RF), and Support Vector Regression (SVR)—to assess their efficacy in forecasting loan defaults. The models are evaluated using metrics such as Mean Squared Error (MSE), F1 score, and Accuracy, and their proficiency in addressing imbalanced datasets and elucidating intricate data relationships is highlighted. The results indicate that while the Random Forest model surpasses its counterparts in terms of accuracy and MSE, the LSTM model exhibits considerable potential in managing imbalanced data, as evidenced by its stable F1 score. Although SVR reveals competitive precision, it exhibits deficiencies in addressing class imbalance. The ANOVA analyses substantiate that the disparities in model performance are statistically significant. The research acknowledges that both the LSTM and SVR models remain in the developmental stages, with ongoing initiatives aimed at refining these models through hyperparameter optimization and advanced architectural frameworks to enhance their predictive efficacy in practical applications.

The Integration of Internet of Things and Machine Learning for Energy Prediction of Wind Turbines

Wind power has emerged as a crucial substitute for conventional fossil fuels. The combination of advanced technologies such as the internet of things (IoT) and machine learning (ML) has given rise to a new generation of energy systems that are intelligent, reliable, and efficient. The wind energy sector utilizes IoT devices to gather vital data, subsequently converting them into practical insights. The aforementioned information aids among others in the enhancement of wind turbine efficiency, precise anticipation of energy production, optimization of maintenance approaches, and detection of potential risks. In this context, the main goal of this work is to combine the IoT with ML in the wind energy sector by processing weather data acquired from sensors to predict wind power generation. To this end, three different regression models are evaluated. The models under comparison include Linear Regression, Random Forest, and Lasso Regression, which were evaluated using metrics such as coefficient of determination (R²), adjusted R², mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). Moreover, the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) were taken into consideration as well. After examining a dataset from IoT devices that included weather data, the models provided substantial insights regarding their capabilities and responses to preprocessing, as well as each model’s reaction in terms of statistical performance deviation indicators. Ultimately, the data analysis and the results from metrics and criteria show that Random Forest regression is more suitable for weather condition datasets than the other two regression models. Both the advantages and shortcomings of the three regression models indicate that their integration with IoT devices will facilitate successful energy prediction.

Adaptive Remaining Capacity Estimator of Lithium-Ion Battery Using Genetic Algorithm-Tuned Random Forest Regressor Under Dynamic Thermal and Operational Environments

The increasing interests and recent advancements in artificial intelligence and machine learning have significantly accelerated the development of novel techniques for the state estimation of batteries in electrified vehicles’ battery management systems (BMSs). Determining the remaining capacity among the several BMS states is crucial for ensuring the safe and stable functioning of an electric vehicle. This paper proposes an adaptive estimator for the remaining capacity of lithium-ion batteries, leveraging a Genetic Algorithm (GA)-tuned random forest (RF) regressor. The estimator is designed to function effectively under varying thermal conditions. The optimization of critical parameters, namely, the number of estimators (n-estimators) and the minimum number of samples per leaf (min-samples-leaf), is a focal point of this study to enhance model accuracy and robustness. The model effectively captures the battery’s dynamic behavior and inherent non-linearity. The Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) achieved during testing demonstrate promising accuracy and superior prediction. The results demonstrated significant improvements in state of charge (SOC) estimation accuracy. The proposed GA-optimized RF model achieved an MAE of 0.0026 at 25 °C and 0.0102 at −20 °C, showing a 41.37% to 50% reduction in the MAE compared to traditional random forest models without GA optimization. The RMSE was also reduced by 18.57% to 31.01% across the tested temperature range. These improvements highlight the model’s ability to accurately estimate the SOC in varying thermal conditions.

A Machine Learning Approach to Early Detection and Malignancy Prediction in Breast Cancer

Breast cancer is the most common cancer among women, making early detection crucial for effective treatment. Traditional diagnostic methods often face limitations, leading to potential errors in diagnosis. This study explores the transformative potential of artificial intelligence (AI) and machine learning (ML) in breast cancer diagnosis, particularly through models like AdaBoost, SVM, Random Forest, and logistic regression. By analyzing key variables—such as age, tumor size, and menopausal status—this research aims to accurately differentiate between malignant and benign lesions. The findings reveal that the AdaBoost model significantly outperforms others, achieving an impressive AUC of 93.60% and a precision rate of 95.65%. This indicates its exceptional ability to accurately classify cases, minimizing false positives and ensuring reliable detection of true positives. With an F1 score of 86.27%, AdaBoost effectively balances precision and recall, positioning it as a valuable tool in clinical settings. Overall, this study underscores the importance of integrating AI-driven approaches in breast cancer diagnosis, enhancing accuracy and improving patient outcomes while reducing unnecessary invasive procedures. The promising results advocate for the adoption of these advanced techniques in healthcare, paving the way for more personalized and effective treatment strategies.

Artificial Intelligence (AI)-Driven Frailty Prediction Using Electronic Health Records in Hospitalized Patients With Cardiovascular Disease.

This study aimed to create a deep learning model for predicting phenotypic physical frailty from electronic medical record information in patients with cardiovascular disease. This single-center retrospective study enrolled patients who could be assessed for physical frailty according to cardiovascular health study criteria (25.5% [691/2,705] of the patients were frail). Patients were randomly separated for training (Train set: 80%) and validation (Test set: 20%) of the deep learning model. Multiple models were created using LightGBM, random forest, and logistic regression for deep learning, and their predictive abilities were compared. The LightGBM model had the highest accuracy (in a Test set: F1 score 0.561; accuracy 0.726; area under the curve of the receiver operating characteristics [AUC] 0.804). These results using only commonly used blood biochemistry test indices (in a Test set: F1 score 0.551; accuracy 0.721; AUC 0.793) were similar. The created models were consistently and strongly associated with physical functions at hospital discharge, all-cause death, and heart failure-related readmission. Deep learning models derived from large sample sizes of phenotypic physical frailty have shown good accuracy and consistent associations with prognosis and physical functions.

Plastic Injection Molding Process Analysis: Data Integration and Modeling for Improved Production Efficiency

This paper presents a comprehensive analysis of the plastic injection molding process through the integration of data acquisition technologies and classification models. In collaboration with a company specializing in plastic injection, data were extracted directly from the machine during a specific period at the beginning of a shift change. These data were subjected to exploratory analysis to identify correlations between important variables, such as injection time, cycle time, and mold pressures. Additionally, classification models, including Random Forest and Logistic Regression, were constructed to predict and classify the process state based on these variables. The model results demonstrated high predictive performance, with 99.5% accuracy for Random Forest and 97% for Logistic Regression. These results provide a strong foundation for the early identification of potential problems and informed decision making to improve the efficiency of the plastic injection molding process. This study contributes to the advancement of the integration of intelligent technologies in industrial process optimization, aligned with the principles of Industry 4.0.

Development of a recommendation engine for university study programme selection: A regression-based approach

This paper is the third in a series focused on bridging the gap between secondary and higher education. Our primary objective is to develop a robust theoretical framework for an innovative e-business model called the Undergraduate Study Programme Search System (USPSS). This system considers multiple criteria to reduce the likelihood of exam failure or the need for multiple retakes, while maximizing the chances of successful program completion. Testing of the proposed algorithm demonstrated that the Stochastic Gradient Boosted Regression Trees method outperforms the current method used in Lithuania for admitting applicants to 47 educational programs. Specifically, it is more accurate than the Probabilistic Neural Network for 25 programs, the Ensemble of Regression Trees for 24 programs, the Single Regression Tree for 18 programs, the Random Forest Regression for 16 programs, the Bayesian Additive Regression Trees for 13 programs, and the Regression by Discretization for 10 programs.

Estimating vegetation structure and aboveground carbon storage in Western Australia using GEDI LiDAR, Landsat and Sentinel data

Abstract Worsening climate change impacts are amplifying the need for accurate estimates of vegetation structure and aboveground biomass density (AGBD) to assess changes in biodiversity and carbon storage. In Australia, increasing wildfire frequency and interest in the role of forests in the carbon cycle necessitates biomass mapping across large geographic extents to monitor forest change. The availability of spaceborne Light Detection and Ranging (LiDAR) optimised for vegetation structure mapping through the Global Ecosystem Dynamics Investigation (GEDI) provides an opportunity for large-scale forest AGBD estimates of higher accuracy. This study assessed the use of the GEDI canopy height product to predict woody AGBD across five vegetation types in Western Australia: tall eucalypt forests, eucalypt open‒woodlands, low-lying heathland, tropical eucalypt savannas, and tussock and hummock grasslands. Canopy height models were developed using random forest regressions trained on GEDI canopy height discrete point data. Predictor variables included spectral bands and vegetation indices derived from synthetic aperture radar (SAR) Sentinel‒1 data, and multispectral Landsat and Sentinel‒2 data. AGBD was subsequently estimated using power-law models derived by relating the predicted canopy heights to field AGBD plots. Mapping was conducted for 2020 and 2021. The accuracy of canopy height predictions varied with height quantiles; models underestimated the height of taller trees and overestimated the height of smaller trees. A similar underestimation and overestimation trend was observed for the AGBD estimates. The mean carbon stock was estimated at 69.0 ±12.0 MgCha-1 in the tall eucalypt forests of the Warren region; 33.8 ± 5.0 MgCha-1 for the open eucalypt woodlands in the South Jarrah region; 7.1 ± 1.4 MgCha-1 for the heathland and shrublands in the Geraldton Sandplains region; 43.9 ± 4.9 MgCha-1 for the Kimberley eucalypt savanna; and 3.9 ± 1.0 MgCha-1 for the Kimberley savanna grasslands. This approach provides a useful framework for the future development of this process for fire management, and habitat health monitoring.

Downscaling MODIS evapotranspiration into finer resolution using machine learning approach on a small scale, Ribb watershed, Ethiopia.

By monitoring evapotranspiration (ET), the exchange of water and energy between the soil, plants, and the atmosphere can be controlled. Routine estimations of ET on a daily, monthly, and seasonal basis can give relevant information on small-scale agricultural practices, such as the Ribb watershed in Ethiopia. However, MODIS sensors have recently given high temporal resolution ET products across large areas, but their low spatial resolution limits its application on a local scale. The primary goal of the study was to downscale the MODIS ET (1km) product to a finer spatial resolution at the watershed level. The model's 12 predictor variables (NDVI, EVI, LAI, FVC, SAVI, NDMI, NDWI, Albedo, emissivity, LST, and DEM: slope and elevation) were produced using the random forest (RF) algorithm using Sentinel-2 (S-2) 20m and Landsat-8 (L-8) 30m. The RF regression model was used to assess the relationship between predicted variables and downscaled MODIS ET. The FAO-PM ET model, developed from meteorological stations, was validated by and RMSE for three seasons (rainy, post-rainy, and dry) in 2022. The results were in good agreement with MODIS ET, with an RMSE of 0.22 for S-2 and 0.28 for L-8. In the FAO-PM ET model, the downscaled result showed greater spatial details and better agreement with gage station readings ( and ). Thus, considering the effectiveness and simplicity of machine learning techniques, our study demonstrated the potential for ET downscaling. Furthermore, the study suggests integrating spatiotemporal time series data to reach higher resolution.