Forest Model Research Articles

The coupling model of random forest and interpretable method quantifies the response relationship between PM2.5 and influencing factors

Ambient fine particulate matter (PM2.5) is affected by many factors, such as source emissions, meteorological conditions, and chemical reactions. Revealing the effects of these factors on PM2.5 is essential to understand the causes of PM2.5 pollution. The machine learning method can establish the non-linear relationship between influencing factors and PM2.5. Here, a coupling model of machine learning and interpretation method was constructed to comprehensively quantify the importance of influencing factors to PM2.5 from multiple dimensions and analyze the sensitivity of influencing factors. Among the primary indicators of influencing factors, the importance of emission, meteorological conditions, and atmospheric chemical reaction to PM2.5 is 49%, 29%, and 22%, respectively. In the secondary indicator of influencing factors, the transmission effect is the most important meteorological condition, with an important degree of 15%. The liquid phase reaction is the most important atmospheric chemical reaction, with an importance of 7%. Among the three levels of influencing factors, emission, transport distance, liquid phase reaction coefficient, aerosol acidity, and accumulation promotion coefficient are important factors. The sensitivity of a single factor is complex and changeable, and the interaction between emission and other important factors is the strongest among the two factors. Of which the interaction between transmission distance and emission during the observation period is the strongest, and the interaction coefficient is 1.82. Our study focuses on the effect of influencing factors on PM2.5, provides a basis for the analysis of the causes of PM2.5 pollution, and technical support for the treatment of PM2.5.

Prediction of moisture content ratio of emulsified asphalt chip seal based on machine learning and electrical parameters

The moisture content ratio (MCR) of the emulsified asphalt chip seal can determine its curing degree. However, the MCR of emulsified asphalt chip seal is difficult to measure on actual projects, and there is a lack of a method to assess its MCR. The objective of this study is to establish a prediction methodology for the MCR of emulsified asphalt chip seal based on machine learning and electrical parameters. Features such as electrical parameters and MCR of emulsified asphalt chip seal at different times were measured experimentally. The importance of the features was evaluated using a Random Forest (RF) model. A Back Propagation Neural Network (BPNN) prediction model was established using the important features. The weights and biases of the BPNN were optimized and initialized using the Improved Particle Swarm Optimization (IMPSO) algorithm. As a result, the RF-IMPSO-BPNN emulsified asphalt chip seal MCR prediction model was developed. This model was compared with five other models. The results show that compared to the RF-PSO-BPNN model, the improved RF-IMPSO-BPNN model can improve the ability of the neural network to find the global optimal solution. Compared to the other four machine learning models, the RF-IMPSO-BPNN model can achieve higher prediction accuracy while reducing the human and material resources of the various devices to collect part of the data. In addition, the emulsified asphalt chip seal cures at low MCR. The model predictions are more accurate at low MCR. Therefore, this study developed the RF-IMPSO-BPNN emulsified asphalt chip seal MCR prediction model, which can use fewer features to achieve higher accuracy and provide a rapid and non-destructive idea for judging its curing.

Factors affecting the different growth rates of PM2.5：Evidence from composition variation, formation mechanisms, and importance analysis of water-soluble inorganic ions with case study in northern China

PM2.5 affects air quality, therefore, understanding the mechanism of PM2.5 growth is essential to figure out mitigation measures. Hourly real-time concentrations of water-soluble inorganic ions (WSIIs), including anions and cations, in fine particulate matter (PM2.5) were measured in Baoji, northwest China. During the winter monitoring period, the concentrations of PM2.5 and most WSIIs exhibited similar trends. Mass proportions of SNA [i.e., sulfate (SO42-), nitrate (NO3-), ammonium (NH4+)] in PM2.5 gradually increased with air deterioration, while equivalent ratios of anions to cations also increased. The heterogeneous aqueous reactions and/or gas-phase homogeneous reactions promoted the formation of secondary inorganics, especially during the haze events. Rapid transformations of primary gaseous precursors to secondary pollutants could lead to the substantial formation of SO42- and NO3-. In terms of particle growth rate, the mass proportions of SNA in PM2.5 decreased from General Growth (GG) to Explosive Growth (EG) events. Furthermore, the particle growth rates did not coincide with the pollution levels, while it occurred most frequently during the Transition Period, instead of the Polluted Period. The diurnal variation of SNA at different PM2.5 growth rates has been discussed. The results of the Random Forest (RF) model showed that RH was an important factor for EG of PM2.5, while low RH was a reliable reason for the relatively low mass proportion of SNA. The results of this study could advance our understanding of particle growth and provide scientific evidence to support the establishment of unique air quality control measures under different pollution scenarios in Fenwei Plain, China.

Hyperspectral Inversion of Soil Cu Content in Agricultural Land Based on Continuous Wavelet Transform and Stacking Ensemble Learning

Heavy metal pollution in agricultural land poses significant threats to both the ecological environment and human health. Therefore, the rapid and accurate prediction of heavy metal content in agricultural soil is crucial for environmental protection and soil remediation. Acknowledging the limitations of traditional single linear or nonlinear machine learning models in terms of prediction accuracy, this study developed an ensemble learning model that integrates multiple linear or nonlinear learning models with a random forest (RF) model to improve both the prediction accuracy and reliability. In this study, we selected a typical copper (Cu) polluted area in the Pearl River Delta of Guangdong Province as the research site and collected Cu content data and indoor soil reflectance spectral data from 269 surface soil samples. First, the soil spectral data were preprocessed using Savitzky–Golay (SG) smoothing, multiplicative scattering correction (MSC), and continuous wavelet transform (CWT) to reduce noise interference. Next, principal components analysis (PCA) was employed to reduce the dimensionality of the preprocessed spectral data, eliminating redundant features and lowering the computational complexity. Finally, based on the dimensionality-reduced data and Cu content, we established a stacked ensemble learning model, where the base models included SVR, PLSR, BPNN, and XGBoost, with RF serving as the meta-model to estimate the soil heavy metal content. To evaluate the performance of the stacking model, we compared its prediction accuracy with that of individual models. The results indicate that, compared to the traditional machine learning models, the prediction accuracy of the stacking model was superior (R2 = 0.77; RMSE = 7.65 mg/kg; RPD = 2.29). This suggests that the integrated algorithm demonstrates a greater robustness and generalization capability. This study presents a method to improve soil heavy metal content estimation using hyperspectral technology, ensuring a robust model that supports policymakers in making informed decisions about land use, agriculture, and environmental protection.

Spatial patterns of hydroecological health in the semi-arid yellow river basin: Revelations from machine learning models

The ecosystem of semi-arid watersheds is influenced by a combination of natural climate factors, rainfall, and habitat destruction, resulting in complex mechanisms of spatial differentiation and evolution of water ecological health. Indicator selection in mainstream water ecological health assessment methods, such as the Index of Biotic Integrity (IBI), often relies on subjective reference point choices. This approach tends to overlook the comprehensive impacts and interactions among various environmental stressors. For watersheds significantly influenced by natural climatic factors, considerable uncertainties arise, leading to a lack of scientific justification for establishing water ecological health protection goals. In this study, the nonlinear capabilities of the random forest (RF) model were applied to reduce subjectivity in traditional water ecological health assessments and to more accurately reveal the emerging spatial differentiation patterns and underlying causes of water ecological health in the Wei River Basin (WRB), the largest typical semi-arid watershed of the Yellow River in China. Our findings indicate: (1) Traditional evaluation indices indicate that the overall water ecological health of the WRB is classified as sub-healthy (60 %). The core indicators include dominant species, total algal density, and the percentage of diatom density, with no significant spatial differentiation observed. (2) An improved water ecological health assessment method for semi-arid watersheds, based on the RF model, has been developed to replace traditional subjective judgment steps. This method establishes a complex multi-input–output response relationship (R2 > 0.85) between environmental stress indicators and the biological integrity index for the WRB. (3) The model results identify key driving factors affecting changes in water ecological health in semi-arid watersheds, with the sensitivity of the new model increasing nearly 11-fold compared to traditional IBI methods. (4) Following improvements, the water ecological health characteristics of the WRB exhibit significant spatial heterogeneity, with a higher dispersion coefficient (1.21), and demonstrate enhanced nonlinear response trends to climatic factors. The application of machine learning models indicates that traditional methods may underestimate the extent of ecological health degradation in watersheds and tend to oversimplify spatial heterogeneity characteristics.

Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.

PanNETs are a rare group of pancreatic tumors that display heterogeneous histopathological and clinical behavior. Nodal disease has been established as one of the strongest predictors of patient outcomes in PanNETs. Lack of accurate preoperative assessment of nodal disease is a major limitation in the management of these patients, in particular those with small (< 2cm) low-grade tumors. The aim of the study was to evaluate the ability of radiomic features (RF) to preoperatively predict the presence of nodal disease in pancreatic neuroendocrine tumors (PanNETs). An institutional database was used to identify patients with nonfunctional PanNETs undergoing resection. Pancreas protocol computed tomography was obtained, manually segmented, and RF were extracted. These were analyzed using the minimum redundancy maximum relevance analysis for hierarchical feature selection. Youden index was used to identify the optimal cutoff for predicting nodal disease. A random forest prediction model was trained using RF and clinicopathological characteristics and validated internally. Of the 320 patients included in the study, 92 (28.8%) had nodal disease based on histopathological assessment of the surgical specimen. A radiomic signature based on ten selected RF was developed. Clinicopathological characteristics predictive of nodal disease included tumor grade and size. Upon internal validation the combined radiomics and clinical feature model demonstrated adequate performance (AUC 0.80) in identifying nodal disease. The model accurately identified nodal disease in 85% of patients with small tumors (< 2cm). Non-invasive preoperative assessment of nodal disease using RF and clinicopathological characteristics is feasible.

Effects of model-overfit on model-assisted forest inventory in boreal forests with remote sensing data

Abstract While remote sensing can be an effective tool in building a forest inventory, field measurements and model fitting can be both expensive and challenging. One strategy to reduce forest inventory costs is to leverage forest inventory models fitted to a different population (external models), although the effectiveness of external models is poorly understood. One concern is that models may predict well to the sample data, but poorly to the population—which is termed ‘overfitting’. The effect of overfit may be especially problematic in attempts to predict for a different population (a forest area not covered by any sample plots). Assessing overfit is difficult and its consequence for estimation are not well understood, especially in the context of prediction using external models. This study assesses how overfitting affects model-assisted forest inventory estimation when using internal and external models. We used field and remotely sensed data (Sentinel-2 images and airborne laser scanning data) from two forest areas in Finland. We evaluated four modeling approaches: ordinary least square regression (OLS), random forest, k-nearest neighbors, and gaussian process regression. Both analytical and bootstrap variance estimators were used to evaluate model-assisted estimation performance. Internal models, especially OLS, were the most affected by model overfitting, leading to bias in the population means and underestimation of variance. Estimates using external models provided unbiased means and realistic intervals except in the case of deliberate excessive overfitting. The bootstrap variance estimator was found to be more robust to overfit than the analytical variance estimator for the internal model, but was not helpful for the external model. Internal models should be parsimonious to generalize well to the population and avoid bias. The bootstrap estimator of variance is recommended for internal models, especially if there is concern about model overfitting.

Machine Learning-Based Cow Milk Quality Classification using Recursive Feature Elimination Cross-Validation

&lt;p&gt;Milk quality is of paramount importance as it directly impacts consumer health and well-being. High-quality milk is rich in essential nutrients such as calcium, protein, and vitamins, contributing to overall nutrition. Moreover, ensuring milk quality is vital for preventing the transmission of diseases and contaminants through dairy products. Therefore, research in this field is essential to guaranteeing the safety and nutritional value of milk consumed by individuals of all ages. In this paper, the design of machine learning-based grade measuring devices with recursive feature elimination with cross-validation (RFECV) is carried out as a guide in the design of a milk grade detection system. The milk is rated as low, medium, or high based on these criteria. The sensors will gather this information from the milk with the aid of the microcontroller. The algorithms utilized in this study and the results obtained from K-Nearest Neighbors (KNN) combined with the RFECV algorithm have a higher accuracy value: 17,20% better than the support vector machine (SVM) model, 25.37% better than the single K-Nearest Neighbors (KNN), and 26.37% better than the random forest (RF) model trained without RFECV. Using seven input features (pH, temperature, taste, odor, fat, turbidity, and color), the proposed model produces 96.27% accuracy.&lt;/p&gt;

Combination of plasma-based lipidomics and machine learning provides a useful diagnostic tool for ovarian cancer

Ovarian cancer (OC), the second leading cause of death among gynecologic cancers, is often diagnosed at an advanced stage due to its asymptomatic nature at early stages. This study aimed to explore the diagnostic potential of plasma-based lipidomics combined with machine learning (ML) in OC. Non-targeted lipidomics analysis was conducted on plasma samples from participants with epithelial ovarian cancer (EOC), benign ovarian tumor (BOT), and healthy control (HC). The samples were randomly divided into a train set and a test set. Differential lipids between groups were selected using two-tailed Student’s t-test and partial least squares discriminant analysis (PLS-DA). Both single lipid-based receiver operating characteristic (ROC) model, and multiple lipid-based ML model, were constructed to investigate the diagnostic value of the differential lipids. The results showed several lipids with significant diagnostic potential. ST 27:2;O achieved the highest prediction accuracy of 0.92 in distinguishing EOC from HC. DG 42:2 had the highest prediction accuracy of 0.96 in diagnosing BOT from HC. Cer d18:1/18:0 had the highest prediction accuracy of 0.65 in differentiating EOC from BOT. Furthermore, multiple lipid-based ML models illustrated better diagnostic performance. K-nearest neighbors (k-NN), partial least squares (PLS), and random forest (RF) models achieved the highest prediction accuracy of 0.96 in discriminating EOC from HC. The support vector machine (SVM) model reached the highest prediction accuracy both in distinguishing BOT from HC, and in differentiating EOC from BOT, with accuracies of 1.00 and 0.74, respectively. In conclusion, this study revealed that the combination of plasma-based lipidomics and ML algorithms is an effective method for diagnosing OC.

Phosphorus removal performance of Sulfide-Based autotrophic denitrification process

Sulfide-based Autotrophic Denitrification (SAD) Process can simultaneous remove sulfurous and nitrogenous pollutants, showing a promising prospect. Beyond our expectation, it also has an efficient phosphorus (P) removal performance. The operation results demonstrated that when the influent concentration of nitrate, sulfide and phosphate was 80.55 ± 2.98 mg N/L, 380.15 ± 20.83 mg S/L and 47.70 ± 4.35 mg P/L respectively, their removal efficiency was 87.63 ± 3.12 %, 99.61 ± 1.02 % and 85.38 ± 4.07 % at the HRT of 8.8 h. However, the phosphorus removal performance disappeared once the effluent pH dropped below 8.0. The random forest regression model revealed that effluent pH had the most significant impact on phosphorus removal performance. This finding was corroborated by a mathematical model that related the phosphate removal load to effluent pHs. The combination of batch test, Standard Measurements and Testing (SMT) and X-Ray Diffraction (XRD) method revealed that the phosphorus removal performance of SAD process came from the synergies of biological phosphorus removal (29.71 ± 3.21 %) and bio-induced phosphate precipitation (70.29 ± 3.21 %). The analysis of key functional genes coding for nitrogen, sulfur and phosphorus metabolism offered an explanation for their metabolic pathways especially the phosphorus removal pathway. The study would provide some new information for the development of SAD process.

An Analysis of the Effect of Skew Rolling Parameters on the Surface Quality of C60 Steel Parts Using Classification Models

This paper presents the experimental and numerical results of a study on producing axisymmetric parts made of the C60-grade steel by skew rolling. The experimental part of this study involved conducting the skew rolling process with varying parameters, including the forming angle α, tool angle θ, chuck velocity Vu, and reduction ratio δ. Their effect on the quality of produced parts was examined and described by the roughness parameter Ra. Numerical calculations involved the use of machine learning models to predict the quality class of produced parts. The highest prediction accuracy of the results was obtained with the random forest and logistic regression models. Metrics such as precision, recall and accuracy were used to evaluate the performance of individual models. Confusion matrices and ROC curves were also employed to illustrate the performance of the classification models. The results of this study will make it possible to prevent the formation of spiral grooves on the circumference of steel parts during the rolling process.

Towards Resilient Communities: Evaluating the Nonlinear Impact of the Built Environment on COVID-19 Transmission Risk in Residential Areas

Reflections on urban epidemics often drive improvements in the resilience of the built environment. However, the assessment regarding the nonlinear influence of the community environment on the spread of Corona Virus Disease 2019 (COVID-19) is inadequate. This study analyzed the influential mechanism of built environment factors on the epidemic risk in residential areas, using Shanghai as a case study. During the lockdown in April 2022, Shanghai reported daily data on COVID-19 outbreaks in residential areas, amounting to a total of 90,323 entries. Based on a GIS-based grid analysis approach, we employed a Random Forest (RF) model and a Multiscale Geographically Weighted Regression (MGWR) model to investigate the marginal effects and spatial heterogeneity of environmental factors on the mean count of COVID-19 outbreak days (MC) in residential areas within each grid zone. The results show that the value of MC forms a ring-mountain distribution surrounding the city's outer ring road. The RF model (R² = 0.57) demonstrates that the house price, population density, family number, and the standard deviation of building height (BH_SD) significantly correlated with MC, with the relative importance of 25%, 13%, 11%, and 6%, respectively. The MGWR model (R² = 0.63) highlights the spatial heterogeneity of family number, house age, house price, property fee, and delivery density. We also found that property fee and green rate were negatively correlated with the MC. These findings help improve responses to public health emergencies and create more resilient communities to cope with pandemics.

An adaptable dead fuel moisture model for various fuel types and temporal scales tailored for wildfire danger assessment

Estimating the Dead Fuel Moisture Content (DFMC) is crucial in wildfire risk management, representing a key component in forest fire danger rating systems and wildfire simulation models. DFMC fluctuates sub-daily and spatially, influenced by local weather and fuel characteristics. This necessitates models that provide sub-daily fuel moisture conditions for improving wildfire risk management. Many forest fire danger rating systems typically rely on daily fuel moisture models that overlook local fuel characteristics, with consequent impact on wildfire management. The semi-empirical parametric DFMC model proposed addresses these issues by providing hourly dead fuel moisture dynamics, with specific parameters to consider local fuel characteristics. A calibration framework is proposed by adopting Particle Swarm Optimization-type algorithm. In the present study, the calibration framework has been tested by using hourly 10-hours fuel sticks measurements. Implementing this model in forest fire danger rating systems would enhance detail in forest fire danger conditions, advancing wildfire risk management.

Association between salivary microbiota and tacrolimus pharmacokinetic variability in kidney transplant

Kidney transplantation (KT) serves as a highly effective treatment for end-stage renal disease (ESRD). Nonetheless, the administration of tacrolimus, a commonly used immunosuppressant in KT, faces challenges due to the lack of dependable biomarkers for its efficacy and the considerable variability in tacrolimus pharmacokinetics (TacIPV). In this study, 183 saliva samples from 48 KT recipients under tacrolimus therapy, alongside 9 healthy control samples, were subjected to 16S rRNA sequencing. The analysis revealed significant differences in the composition of salivary microbiota among KT recipients, patients with ESRD, and healthy controls. Moreover, trough blood concentrations (C0) of tacrolimus were associated with alterations in microbiota composition. Notably, Capnocytophage consistently exhibited a negative correlation in both group-level and individual trends. Furthermore, distinct taxa were identified that effectively distinguished recipients with varying TacIPV, as demonstrated by a cross-validation random forest model (mean AUC = 0.7560), with Anaerolinea emerging as a prominent contributor to the classifier. These findings suggest that salivary microbiota is closely linked to tacrolimus C0 levels and could aid clinicians in differentiating KT recipients based on TacIPV.

Global patterns in vegetation accessible subsurface water storage emerge from spatially varying importance of individual drivers

Abstract Vegetation roots play an essential role in regulating the hydrological cycle by removing water from the subsurface and releasing it to the atmosphere. However, the present understanding of the drivers of ecosystem-scale root development and their spatial variability globally is limited. This study investigates the varying roles of climate, landscape, and vegetation on the magnitude of root zone storage capacity ( S r ) worldwide, which is defined as the maximum volume of subsurface moisture accessible to vegetation roots. To this aim, we quantified S r and evaluated 21 possible climate, landscape, and vegetation controls for 3612 river catchments worldwide using a random forest machine learning model. Our findings reveal climate as primary, but spatially varying, driver of ecosystem scale S r with landscape and vegetation characteristics playing a minor role. More specifically, we found the mean inter-storm duration as most dominant control of S r globally, followed by mean temperature, mean precipitation, and mean topographic slope. While the inter-storm duration, temperature, and slope exhibit a consistent relation with S r globally, the relation between precipitation and S r varies spatially. Based on this spatial variability, we classified two different regimes: precipitation driven and energy limited. The precipitation-driven regime exhibits a positive relation between precipitation and S r for precipitation of up to 3 mm d − 1 , above which the relation flattens and eventually becomes negative. The energy-limited regime exhibits a strictly negative relation between precipitation and S r . Using the random forest model based on these three dominant climate variables and the landscape variable slope, we generated a global gridded dataset of S r , which closely resembles other global datasets of root characteristics. This suggests that our parsimonious approach based on four globally available variables to estimate S r on a global scale has the potential to be readily and easily integrated into the parameterization of S r in global hydrological and land surface models. This may enhance the accuracy of global predictions of land–atmosphere exchange fluxes and hydrological extremes by providing a robust representation of both spatial and temporal variability in vegetation root characteristics.

Making data classification more effective: An automated deep forest model

Despite a small overfitting risk, the deep forest model and its variants cannot automatically match data features; they rely on manual experience and comparative experiments for forest learner selection. This study proposes an automated deep forest model (ATDF) to enhance deep forest automation by automatically determining forest learners’ types and numbers based on training data. The model introduces a forest learner variability measure based on normalized mutual information, serving as a theoretical foundation for the automated process in deep forests. Then, a novel hierarchical clustering algorithm based on normalized mutual information is proposed to group forest learners at different granularities, determining the optimal forest learner type. This advanced technical method enables the determination of the model structure for stacking models, including deep forests. Finally, with the goal of maximizing cross-validation scores, the tree parson estimator-based Bayesian optimization algorithm determines the ideal number of forest learners for each type. Additionally, a standardized method for identifying forest learners is developed to guarantee the consistency of model outcomes. Most importantly, a series of comparative experiments on seven datasets from the UCI Machine Learning Repository confirmed the effectiveness and superiority of the proposed model. The results demonstrate that the proposed model has superior adaptability to new data and tasks, besides having a high level of automation, and performs excellently in the classification task.

Tree species selection for optimizing soil carbon storage: Insights from litter decomposition and bacterial community analysis in coastal ecosystems

Coastal wetland ecosystems are critical sinks for atmospheric carbon dioxide, playing a vital role in global carbon cycling and climate regulation. The decomposition of leaf litter plays a crucial role in the formation and stability of soil organic carbon (SOC) in these environments. This study investigated the impact of leaf litter decomposition from five tree species (Populus deltoids, Ligustrum lucidum, Taxodium 'Zhongshanshan', Hibiscus hamabo, and Nerium oleander) on SOC dynamics, humus composition, and soil bacterial community structure in a tidal flat. Litterbags were used to monitor the mass loss and changes in litter chemical composition over 270 days. The results revealed significant differences in decomposition rates among the tree species, with Nerium oleander exhibiting the fastest decomposition and Populus deltoids the slowest. Surprisingly, initial litter chemistry did not correlate with decomposition rates; however, changes in lignin and hemicellulose content during decomposition were significantly related to mass loss. Despite its rapid decomposition, Nerium oleander litter resulted in the highest accumulation of SOC, total humus, and humin compared to the other species, challenging the conventional view that slower decomposition leads to greater SOC storage. The soil microbial community structure was significantly influenced by SOC, humus, and litter components, with distinct microbial assemblages associated with each tree species. A random forest model identified key bacterial taxa, predominantly Proteobacteria, as important predictors of SOC content, highlighting the role of bacterial diversity in regulating SOC dynamics. These findings underscore the importance of considering litter quality, decomposition dynamics, and bacterial community composition in strategies aimed at enhancing soil carbon sequestration. This study suggests that selecting tree species with rapidly decomposing litter, such as Nerium oleander, in coastal plantations can be an effective management tool for optimizing soil carbon storage, offering valuable insights for mitigating climate change impacts.

Factors influencing housing prices: A comparative study using multiple linear regression and random forest

Abstract. The method is to construct a multiple linear regression model to examine the variables that significantly affect US home prices. The dataset has 13 variables and 545 observations, and it was obtained via Kaggle. This paper also considers comparing the multiple linear regression models and random forest model for predicting house prices and thus concludes which model can most accurately predict house prices. The result indicates that the factors including area, quantity of bedrooms and bathrooms, the existence of a basement, and state of the furnishings, etc. significantly impact housing prices. By comparing Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE), the conclusion suggests that the multiple linear regression model marginally surpasses the random forest regarding the accuracy of the predictions, despite the fact that both models function similarly. This research offers practical applications for enhancing real estate market strategies and provides valuable insights into the factors influencing housing prices.

Uncovering the features of industrial odors-derived environmental complaints and proactive countermeasures by using machine-learning

Industrial odor-derived environmental complaints pose an emerging and far-reaching challenge in cities worldwide with intensive industries. Developing effective odor complaint management strategies is essential for mitigating the public impact of industrial odors. Based on a typical case of persistent tire manufacturing odors affecting local communities, we proposed an environmental complaint risks (ECR) prediction model using machine-learning (ML) approaches, which combined complaints with temporal-resolution manufacturing-meteorology-environment data. Through intensive match-making between ML algorithms and multi-source parameters, Random Forest models can achieve a reliable ECR-prediction model performance with an average ROC-AUC of 0.79at a monthly timescale, indicating the effectiveness of ML-based ECR prediction models. The interpretable ML model quantitively depicted the underlying mechanisms of ECR prediction, driven by process emission behaviors, local wind direction, and historical high-risk period. Furthermore, to mitigate predictable ECR within a future period, we designed a model framework that integrated ECR prediction models with an adaptive optimization genetic algorithm. This enabled the proactive management by precisely and dynamically allocating limited resources of emission regulatory to high-ECR periods in advance. The strategy was proven effective, achieving a significant 24.7% average reduction in the overall ECR forecast during a period with intensive complaints. Overall, this study proposed a data-driven model framework that efficiently helps the multi-stakeholders shift from passive response to proactive ECR management, thereby enhancing the environmental and social sustainability.

Machine learning-based optimization for D-shaped PCF SPR refractive index sensor

In this research, we investigated common machine learning algorithms to estimate the highest sensitivity of a D-shaped PCF SPR sensor by optimizing the performance parameters. Extreme gradient boosting (XGBoost), random forest model, and PyTorch neural network machine learning algorithms were compared to build a model and accurately predict the results, and sensor parameters were optimized through Non-dominated Sorting Genetic Algorithm (NSGA-II). The XGBoost technique demonstrated exceptional prediction capability, achieving an impressive R2 value of 99.64% and the trained model served as the objective function. The maximum sensitivity of 4529.75 nm/RIU was achieved in the standard optimization approach, However, with the guidance of NSGA-II, this sensitivity increased to 4814.14 nm/RIU, representing an improvement of 6.28%. The developed model enables rapid, reliable, and computationally cost-effective parameter predictions. Additionally, it provides a comprehensive understanding of the intricate relationships between input parameters and sensitivity, thus contributing significantly to the existing literature in the quest for optimal parameter identification through the application of machine learning algorithms.