Random Forest Regression Model Research Articles

The cortical neurophysiological signature of amyotrophic lateral sclerosis

Abstract The progressive loss of motor function characteristic of amyotrophic lateral sclerosis is associated with widespread cortical pathology extending beyond primary motor regions. Increasing muscle weakness reflects a dynamic, variably compensated brain network disorder. In the quest for biomarkers to accelerate therapeutic assessment, the high temporal resolution of magnetoencephalography is uniquely able to non-invasively capture micro-magnetic fields generated by neuronal activity across the entire cortex simultaneously. This study examined task-free magnetoencephalography to characterise the cortical oscillatory signature of amyotrophic lateral sclerosis for potential as a pharmacodynamic biomarker. Eight-ten minutes of magnetoencephalography in the task-free, eyes-open state was recorded in amyotrophic lateral sclerosis (n=36) and healthy age-matched controls (n=51), followed by a structural MRI scan for co-registration. Extracted magnetoencephalography metrics from the delta, theta, alpha, beta, low-gamma, high-gamma frequency bands included oscillatory power (regional activity), 1/f exponent (complexity) and amplitude envelope correlation (connectivity). Groups were compared using a permutations-based general linear model with correction for multiple comparisons and confounders. To test whether the extracted metrics could predict disease severity, a Random Forest Regression model was trained and evaluated using nested Leave-One-Out Cross-Validation. Amyotrophic lateral sclerosis was characterised by reduced sensorimotor beta band and increased high-gamma band power. Within the premotor cortex, increased disability was associated with a reduced 1/f exponent. Increased disability was more widely associated with increased global connectivity in the delta, theta, and high-gamma bands. Intra-hemispherically, increased disability scores were particularly associated with increases in temporal connectivity and inter-hemispherically with increases in frontal and occipital connectivity. The Random Forest model achieved a coefficient of determination (R2) of 0.24. The combined reduction in cortical sensorimotor beta and rise in gamma power is compatible with the established hypothesis of loss of inhibitory, GABAergic interneuronal circuits in pathogenesis. A lower 1/f exponent potentially reflects a more excitable cortex and a pathology unique to amyotrophic lateral sclerosis when considered with the findings published in other neurodegenerative disorders. Power and complexity changes corroborate with the results from paired-pulse transcranial magnetic stimulation. Increased magnetoencephalography connectivity in worsening disability is thought to represent compensatory responses to a failing motor system. Restoration of cortical beta and gamma band power has significant potential to be tested in an experimental medicine setting. Magnetoencephalography-based measures have potential as sensitive outcome measures of therapeutic benefit in drug trials and may have wider diagnostic value with further study, including as predictive markers in asymptomatic carriers of disease-causing genetic variants.

AeroSense: Sensing Aerosol Emissions from Indoor Human Activities

The types of human activities occupants are engaged in within indoor spaces significantly contribute to the spread of airborne diseases through emitting aerosol particles. Today, ubiquitous computing technologies can inform users of common atmosphere pollutants for indoor air quality. However, they remain uninformed of the rate of aerosol generated directly from human respiratory activities, a fundamental parameter impacting the risk of airborne transmission. In this paper, we present AeroSense, a novel privacy-preserving approach using audio sensing to accurately predict the rate of aerosol generated from detecting the kinds of human respiratory activities and determining the loudness of these activities. Our system adopts a privacy-first as a key design choice; thus, it only extracts audio features that cannot be reconstructed into human audible signals using two omnidirectional microphone arrays. We employ a combination of binary classifiers using the Random Forest algorithm to detect simultaneous occurrences of activities with an average recall of 85%. It determines the level of all detected activities by estimating the distance between the microphone and the activity source. This level estimation technique yields an average of 7.74% error. Additionally, we developed a lightweight mask detection classifier to detect mask-wearing, which yields a recall score of 75%. These intermediary outputs are critical predictors needed for AeroSense to estimate the amounts of aerosol generated from an active human source. Our model to predict aerosol is a Random Forest regression model, which yields 2.34 MSE and 0.73 r2 value. We demonstrate the accuracy of AeroSense by validating our results in a cleanroom setup and using advanced microbiological technology. We present results on the efficacy of AeroSense in natural settings through controlled and in-the-wild experiments. The ability to estimate aerosol emissions from detected human activities is part of a more extensive indoor air system integration, which can capture the rate of aerosol dissipation and inform users of airborne transmission risks in real time.

Feasibility of Remote Blood Pressure Estimation via Narrow-band Multi-wavelength Pulse Transit Time

Contact-free sensing gained much traction in the past decade. While remote monitoring of some parameters (heart rate) is approaching clinical levels of precision, others remain challenging (blood pressure). We investigated the feasibility of estimating blood pressure (BP) via pulse transit time (PTT) in a novel remote single-site manner, using a modified RGB camera. A narrow-band triple band-pass filter allowed us to measure the PTT between different skin layers, harvesting information from green and near-infrared wavelengths. The filter minimizes the inter-channel influence and band overlap, however, some overlap remains within the filter bands. We further resolve this using a color-channel model and a novel channel-separation method. Using the proposed setup and algorithm, we obtained multi-wavelength (MW) PTTs in an experiment inducing BP changes to 9 subjects. The results showed good absolute Pearson’s correlation coefficient between both MW PTT and systolic BP (R = 0.61, p = 0.08) as well as diastolic BP (R = 0.54, p = 0.05), pointing to feasibility of the proposed novel remote MW BP estimation via PTT. This was further confirmed in a leave-one-subject-out experiment, where a simple Random Forest regression model achieved mean absolute errors of 3.59 and 2.63 mmHg for systolic and diastolic BP respectively.

Interpretable Machine Learning for Geochemical Anomaly Delineation in the Yuanbo Nang District, Gansu Province, China

Machine learning (ML) has shown its effectiveness in handling multi-geoinformation. Yet, the black-box nature of ML algorithms has restricted their widespread adoption in the domain of mineral prospectivity mapping (MPM). In this paper, methods for interpreting ML model predictions are introduced to aid ML-based MPM, with the goal of extracting richer insights from the ML modeling of an exploration geochemical dataset. The partial dependence plot (PDP) and accumulated local effect (ALE) plot, along with the SHAP value analysis, were utilized to demonstrate the application of random forest (RF) modeling within both regression and classification frameworks. Initially, the random forest regression (RFR) model established the relationship between the concentrations of Au and those of elements such as As, Sb, and Hg in the study area, and from this model, the most important geochemical elements and their quantitative relationships with Au were revealed by their contributions in the modeling through PDP and ALE analyses. Secondly, the RF classification modeling established the relationships of mineralization occurrences (i.e., known mineral deposits) with geochemical elements (i.e., Au, As, Sb, Hg, Cu, Pb, Zn, and Ag), as did RFR modeling. The most important geochemical elements for indicating regional Au mineralization and the trajectories of PDP and ALE reached a consensus that As and Sb contributed the most, both in the regression and classification modeling, with regard to Au mineralization. Finally, the SHAP values illustrated the behavior of the training samples (i.e., known mineral deposits) in RF modeling, and the resulting prospectivity map was evaluated using receiver operating characteristics.

Prediction of Glass Chemical Composition and Type Identification Based on Machine Learning Algorithms

Ancient glass artifacts were susceptible to weathering from the environment, causing changes in their chemical composition, which pose significant obstacles to the identification of glass products. Analyzing the chemical composition of ancient glass has been beneficial for evaluating their weathering status and proposing measures to reduce glass weathering. The objective of this study was to explore the optimal machine learning algorithm for glass type classification based on chemical composition. A set of glass artifact data including color, emblazonry, weathering, and chemical composition was employed and various methods including logistic regression and machine learning techniques were used. The results indicated that a significant correlation (p < 0.05) could only observed between surface weathering and the glass types (high-potassium and lead–barium). Based on the random forest and logistic regression models, the primary chemical components that signify glass types and weathering status were determined using PbO, K2O, BaO, SiO2, Al2O3, and P2O5. The random forest model presented a superior ability to identify glass types and weathering status, with a global accuracy of 96.3%. This study demonstrates the great potential of machine learning for glass chemical component estimation and glass type and weathering status identification, providing technical guidance for the appraisal of ancient glass artifacts.

Mapping the Continuous Cover of Invasive Noxious Weed Species Using Sentinel-2 Imagery and a Novel Convolutional Neural Regression Network

Mapping the Continuous Cover of Invasive Noxious Weed Species Using Sentinel-2 Imagery and a Novel Convolutional Neural Regression Network

Optimization of process parameters of selective laser melted nickel-based superalloy for densification by random forest regression algorithm and response surface methodology

In this study, Random Forest Regression (RFR) and Response Surface Methodology (RSM) were employed to predict the optimized processing parameters to achieve the highest densification of a nickel-based superalloy Mar-M247LC fabricated by selective laser melting (SLM). The RFR model considered input processing parameters such as laser power, hatch distance, and scanning speed. A dataset of 223 samples, was used to train the RFR model. As a result, the RFR model exhibited accuracy of 99.57 %, R2 value of 0.976, Mean Square Error (MSE) of 0.402, and Mean Absolute Percentage Error (MAPE) of 0.426 % on testing set. In addition to the RFR model, this study also employed Central Composite Design (CCD) and RSM to optimize the processing parameter sets. Subsequently, this study conducted Box-Behnken Design (BBD) to experimentally validate the accuracy of this RFR model. In the end, a set of the optimal processing parameters was tested and resulted a sample densification of 99.959 %, outperformed that in the original database before building the RFR model, which was 99.734 %. In summary, the RFR models was able to predict densification with accuracy, and by coupling with RSM, the optimal processing parameter could be obtained, so better densification of the build could be achieved.

Enhancing Monthly Streamflow Prediction Using Meteorological Factors and Machine Learning Models in the Upper Colorado River Basin

Streamflow prediction is crucial for planning future developments and safety measures along river basins, especially in the face of changing climate patterns. In this study, we utilized monthly streamflow data from the United States Bureau of Reclamation and meteorological data (snow water equivalent, temperature, and precipitation) from the various weather monitoring stations of the Snow Telemetry Network within the Upper Colorado River Basin to forecast monthly streamflow at Lees Ferry, a specific location along the Colorado River in the basin. Four machine learning models—Random Forest Regression, Long short-term memory, Gated Recurrent Unit, and Seasonal AutoRegresive Integrated Moving Average—were trained using 30 years of monthly data (1991–2020), split into 80% for training (1991–2014) and 20% for testing (2015–2020). Initially, only historical streamflow data were used for predictions, followed by including meteorological factors to assess their impact on streamflow. Subsequently, sequence analysis was conducted to explore various input-output sequence window combinations. We then evaluated the influence of each factor on streamflow by testing all possible combinations to identify the optimal feature combination for prediction. Our results indicate that the Random Forest Regression model consistently outperformed others, especially after integrating all meteorological factors with historical streamflow data. The best performance was achieved with a 24-month look-back period to predict 12 months of streamflow, yielding a Root Mean Square Error of 2.25 and R-squared (R2) of 0.80. Finally, to assess model generalizability, we tested the best model at other locations—Greenwood Springs (Colorado River), Maybell (Yampa River), and Archuleta (San Juan) in the basin.

Biomass Higher Heating Value Estimation: A Comparative Analysis of Machine Learning Models

The research conducted focused on the capabilities of various non-linear and machine learning (ML) models in estimating the higher heating value (HHV) of biomass using proximate analysis data as inputs. The research was carried out to identify the most appropriate model for the estimation of HHV, which was determined by a statistical analysis of the modeling error. In this sense, artificial neural networks (ANNs), support vector machine (SVM), random forest regression (RFR), and higher-degree polynomial models were compared. After statistical analysis of the modeling error, the ANN model was found to be the most suitable for estimating the HHV biomass and showed the highest specific regression coefficient, with an R2 of 0.92. SVM (R2 = 0.81), RFR, and polynomial models (R2 = 0.84), on the other hand, also exhibit a high degree of estimation, albeit with somewhat larger modelling errors. The study conducted suggests that ANN models are best suited for the non-linear modeling of HHV of biomass, as they can generalize and search for links between input and output data that are more robust but also more complex in structure.

Factor analysis and countermeasures for global warming based on data science methods

In recent years, the frequent and intensifying occurrence of extreme weather events such as heatwaves, floods, and storms worldwide has led scientists and policymakers to be increasingly concerned about the phenomenon of global warming. The global average temperature has steadily risen over the past few decades, and 2015-2022 has been identified as the warmest years on record. Taking global warming as the research object, the main problem is to find out the factors affecting climate change. The article predicts the global average temperature of the future and builds a model to analyse the relationship between global average temperature, time, location and the factors affecting climate change. The prediction models of ARMIA and EEMD-LSTM were built, and the model with the best fit was obtained after several iterations of tuning and trial optimization. The results showed that Flood, Storm, and Extreme temperature, had a high correlation with the global average temperature. The data of greenhouse gas indicators such as CO2, NO, and CH4, and catastrophes such as earthquakes, Volcanic activity, and wildfires have objective effects on global warming. Random forest regression model pairs were developed, and analysis of the importance of each component to the model showed that CO2 concentration and CH4 concentration had significant effects on global average temperature. Propose measures that can curb or slow down global warming.

Optimising Plate Thickness in Interlocking Inter-Module Connections for Modular Steel Buildings: A Finite Element and Random Forest Approach

Interlocking Inter-Module Connections (IMCs) in Modular Steel Buildings (MSBs) have garnered significant interest from researchers. Despite this, the optimisation of plate thicknesses in such structures has yet to be extensively explored in the existing literature. Therefore, this paper focuses on optimising the thickness of interlocking IMCs in MSBs by leveraging established experimental and numerical simulation methodologies. The study developed various numerical models for IMCs with plate thicknesses of 4 mm, 6 mm, 10 mm, and 12 mm, all subjected to compression loading conditions. The novelty of this study lies in its comprehensive parametric analysis, which evaluates the slip prediction model. A random forest regression model, trained using the ‘TreeBagger’ function, was also implemented to predict slip values based on applied force. Sensitivity analysis and comparisons with alternative methods underscored the reliability and applicability of the findings. The results indicate that a plate thickness of 11.03 mm is optimal for interlocking IMCs in MSBs, achieving up to 8.08% in material cost reductions while increasing deformation resistance by up to 50.75%. The ‘TreeBagger’ random forest regression significantly enhanced slip prediction accuracy by up to 7% at higher force levels.

Construction and evaluation of a metabolic correlation diagnostic model for diabetes based on machine learning algorithms.

Diabetes mellitus (DM) is a prevalent chronic disease marked by significant metabolic dysfunctions. Understanding its molecular mechanisms is vital for early diagnosis and treatment strategies. We used datasets GSE7014, GSE25724, and GSE156248 from the GEO database to build a diagnostic model for DM using Random Forest (RF) and LASSO regression models. GSE20966 served as a validation cohort. DM patients were classified into two subtypes for functional enrichment analysis. Expression levels of key diagnostic genes were validated using quantitative real-time PCR (qRT-PCR) on Peripheral Blood Mononuclear Cells (PBMCs) from DM patients and healthy controls, focusing on CXCL12 and PPP1R12B with GAPDH as the internal control. After de-batching the datasets, we identified 131 differentially expressed genes (DEGs) between DM and control groups, with 70 up-regulated and 61 down-regulated. Enrichment analysis revealed significant down-regulation in the IL-12 signaling pathway, JAK signaling post-IL-12 stimulation, and the ferroptosis pathway in DM. Five genes (CXCL12, MXRA5, UCHL1, PPP1R12B, and C7) were identified as having diagnostic value. The diagnostic model showed high accuracy in both the training and validation cohorts. The gene set also enabled the subclassification of DM patients into groups with distinct functional traits. qRT-PCR results confirmed the bioinformatics findings, particularly the up-regulation of CXCL12 and PPP1R12B in DM patients. Our study pinpointed seven energy metabolism-related genes differentially expressed in DM and controls, with five holding diagnostic value. Our model accurately diagnosed DM and facilitated patient subclassification, offering new insights into DM pathogenesis.

Remote Quantification of Soil Organic Carbon: Role of Topography in the Intra-Field Distribution

Soil organic carbon (SOC) measurements are an indicator of soil health and an important parameter for the study of land-atmosphere carbon fluxes. Field sampling provides precise measurements at the sample location but entails high costs and cannot provide detailed maps unless the sampling density is very high. Remote sensing offers the possibility to quantify SOC over large areas in a cost-effective way. As a result, numerous studies have sought to quantify SOC using Earth observation data with a focus on inter-field or regional distributions. This study took a different angle and aimed to map the spatial distribution of SOC at the intra-field scale, since this distribution provides important insights into the biophysiochemical processes involved in the retention of SOC. Instead of solely using spectral measurements to quantify SOC, topographic and spectral features act as predictor variables. The necessary data on study fields in South-East England was acquired through a detailed SOC sampling campaign, including a LiDAR survey flight. Multi-spectral Sentinel-2 data of the study fields were acquired for the exact day of the sampling campaign, and for an interval of 18 months before and after this date. Random Forest (RF) and Support Vector Regression (SVR) models were trained and tested on the spectral and topographical data of the fields to predict the observed SOC values. Five different sets of model predictors were assessed, by using independently and in combination, single and multidate spectral data, and topographical features for the SOC sampling points. Both, RF and SVR models performed best when trained on multi-temporal Sentinel-2 data together with topographic features, achieving validation root-mean-square errors (RMSEs) of 0.29% and 0.23% SOC, respectively. These RMSEs are competitive when compared with those found in the literature for similar models. The topographic wetness index (TWI) exhibited the highest permutation importance for virtually all models. Given that farming practices within each field are the same, this result suggests an important role of soil moisture in SOC retention. Contrary to findings in dryer climates or in studies encompassing larger areas, TWI was negatively related to SOC levels in the study fields, suggesting a different role of soil wetness in the SOC storage in climates characterized by excess rainfall and poorly drained soils.

Relationships among six urban air pollutants and identification of pollution types – A case study of Chinese cities above prefecture level

Urban air pollution is caused by the interplay of urban development and natural conditions, but it's unclear which factor has a greater impact. Studying the link between air pollutants and identifying the types of pollution causes is crucial for understanding the pollution mechanisms and formulating efficient management measures. During the research period from 2015 to 2020, this study analyzed the relationships between six air pollutants, calculated the city capacity (CC) and natural condition (NC) scores of 285 cities with the help of the index system and entropy weight TOPSIS model, and employed Gaussian Mixture Model (GMM) and random forest regression model to identify air pollution types. The results show: During the study period, the concentrations of most pollutants decreased, with SO2 experiencing the largest decline, reflecting the significant effectiveness of China's recent atmospheric pollution control efforts. In terms of spatial distribution, the North China Plain (NCP) and the Loess Plateau (LP) remain focal areas of pollution. The correlation analysis results indicate a significant positive correlation among all air pollutants except O3, underscoring the necessity of coordinated pollution control efforts, but the complexity of O3 pollution should not be overlooked. High-value agglomerations of CC scores calculated by the model are predominantly located in the eastern coastal region, while NC scores exhibit two high-value agglomerations in the north and south. Utilizing the GMM, the 285 cities were classified into three categories, and the random forest regression model was employed to identify them as CC dominate, NC dominate, and intermediate types. This paper proposes a novel approach for categorizing city air pollution types, aiming to tailor prevention measures and foster sustainable urban development.

Deciphering patterns in whole fish nitrogen isotopes on a continental scale

Nitrogen isotopes (δ15N) have been used as an indicator of anthropogenic nitrogen loading at local and regional scales. We examined δ15N in fish from estuaries across the continental United States. In the summer of 2015, the U.S. Environmental Protection Agency’s National Coastal Condition Assessment (NCCA) collected fish in 136 coastal waterbodies throughout the United States. Whole fish were analyzed by NCCA for metals, organic contaminants, and lipids. For this study, we also analyzed these fish for isotopes of nitrogen (N). NCCA collected water quality, nutrients, chlorophyll a, and sediment chemistry at each site. We used these data, along with fish life history and watershed land use, to examine how whole fish δ15N was related to these environmental variables using random forest regression models at national and ecoregional scales. At the national scale, fish δ15N were negatively related to total N:total phosphorous (P) ratios (TN:TP) in surface water and reflected differences between the P-limited, δ15N depleted sites in the Floridian ecoregion to sites in other regions. δ15N was lower on the Atlantic relative to the Pacific coast. When considered by region, TN:TP was an important predictor of fish δ15N in 4 of 9 ecoregions, with higher δ15N observed with increasing N limitation (lower TN:TP) Fish life history was also an important predictor of fish δ15N at both the national and ecoregional scale. Whole fish δ15N was positively associated with bioaccumulative contaminants such as PCBs and mercury. Although land use was related to δ15N in fish, it was location specific. This study showed that N stable isotopes reflected ecological conditions at both regional and continental scales.

Rice Yield Estimation Using Multi-Temporal Remote Sensing Data and Machine Learning: A Case Study of Jiangsu, China

Effective estimation of crop yields at a regional scale holds significant importance in facilitating decision-making within the agricultural sector, thereby ensuring grain security. However, traditional ground-based measurement techniques suffer from inefficiencies, and there exists a need for a reliable, precise, and effective method for estimating regional rice yields. In this study, we employed four machine-learning techniques: partial least squares regression (PLSR), support vector regression (SVR), random forest regression (RFR), and back propagation neural network (BPNN). We combined these methods with multi-temporal rice NDVI (normalized difference vegetation index) data for rice yield estimation. Following an accuracy evaluation and a spatial analysis, the key findings of our study are as follows. (1) The RFR model emerged as the most accurate for rice yield estimation, achieving an R2 of 0.65, an RMSE of 388.79 kg/ha, and an rRMSE of 4.48%. While PLSR and SVR demonstrated comparable accuracy, they were both inferior to RFR. (2) Using the top seven predictors with the highest importance rankings as inputs for the RFR model (NDVI values on the 6th, 17th, 33rd, 44th, 71st, 90th, and 106th days after the rice transplanting stage) achieved comparable accuracy while reducing information redundancy. (3) The proposed model demonstrated good spatial applicability (MI = −0.03) for rice yield estimation in Jiangsu, China. (4) A high spatial resolution yearly rice yield dataset (1 km) spanning from 2001 to 2020 was generated using the proposed model and is accessible on the Zenodo database. In conclusion, this study has demonstrated the efficacy of combining multi-temporal remote sensing data with machine-learning techniques for accurate rice yield estimation, thereby aiding agricultural authorities and production enterprises in the timely formulation and refinement of cropping strategies and management policies for the ongoing season.

Synergetic Use of Sentinel-1 and Sentinel-2 Data for Wheat-Crop Height Monitoring Using Machine Learning

Monitoring crop height during different growth stages provides farmers with valuable information important for managing and improving expected yields. The use of synthetic aperture radar Sentinel-1 (S-1) and Optical Sentinel-2 (S-2) satellites provides useful datasets that can assist in monitoring crop development. However, studies exploring synergetic use of SAR S-1 and optical S-2 satellite data for monitoring crop biophysical parameters are limited. We utilized a time-series of monthly S-1 satellite data independently and then used S-1 and S-2 satellite data synergistically to model wheat-crop height in this study. The polarization backscatter bands, S-1 polarization indices, and S-2 spectral indices were computed from the datasets. Optimized Random Forest Regression (RFR), Support Vector Machine Regression (SVMR), Decision Tree Regression (DTR), and Neural Network Regression (NNR) machine-learning algorithms were applied. The findings show that RFR (R2 = 0.56, RMSE = 21.01 cm) and SVM (R2 = 0.58, RMSE = 20.41 cm) produce a low modeling accuracy for crop height estimation with S-1 SAR data. The S-1 and S-2 satellite data fusion experiment had an improvement in accuracy with the RFR (R2 = 0.93 and RMSE = 8.53 cm) model outperforming the SVM (R2 = 0.91 and RMSE = 9.20 cm) and other models. Normalized polarization (Pol) and the radar vegetation index (RVI_S1) were important predictor variables for crop height retrieval compared to other variables with S-1 and S-2 data fusion as input features. The SAR ratio index (SAR RI 2) had a strong positive and significant correlation (r = 0.94; p < 0.05) with crop height amongst the predictor variables. The spatial distribution maps generated in this study show the viability of data fusion to produce accurate crop height variability maps with machine-learning algorithms. These results demonstrate that both RFR and SVM can be used to quantify crop height during the growing stages. Furthermore, findings show that data fusion improves model performance significantly. The framework from this study can be used as a tool to retrieve other wheat biophysical variables and support decision making for different crops.

Revisiting the potential value of vital signs in the real-time prediction of mortality risk in intensive care unit patients

BackgroundPredicting patient mortality risk facilitates early intervention in intensive care unit (ICU) patients at greater risk of disease progression. This study applies machine learning methods to multidimensional clinical data to dynamically predict mortality risk in ICU patients.MethodsA total of 33,798 patients in the MIMIC-III database were collected. An integrated model NIMRF (Network Integrating Memory Module and Random Forest) based on multidimensional variables such as vital sign variables and laboratory variables was developed to predict the risk of death for ICU patients in four non overlapping time windows of 0–1 h, 1–3 h, 3–6 h, and 6–12 h. Mortality risk in four nonoverlapping time windows of 12 h was externally validated on data from 889 patients in the respiratory critical care unit of the Chinese PLA General Hospital and compared with LSTM, random forest and time-dependent cox regression model (survival analysis) methods. We also interpret the developed model to obtain important factors for predicting mortality risk across time windows. The code can be found in https://github.com/wyuexiao/NIMRF.ResultsThe NIMRF model developed in this study could predict the risk of death in four nonoverlapping time windows (0–1 h, 1–3 h, 3–6 h, 6–12 h) after any time point in ICU patients, and in internal data validation, it is suggested that the model is more accurate than LSTM, random forest prediction and time-dependent cox regression model (area under receiver operating characteristic curve, or AUC, 0–1 h: 0.8015 [95% CI 0.7725–0.8304] vs. 0.7144 [95%] CI 0.6824–0.7464] vs. 0.7606 [95% CI 0.7300–0.7913] vs 0.3867 [95% CI 0.3573–0.4161]; 1–3 h: 0.7100 [95% CI 0.6777–0.7423] vs. 0.6389 [95% CI 0.6055–0.6723] vs. 0.6992 [95% CI 0.6667–0.7318] vs 0.3854 [95% CI 0.3559–0.4150]; 3–6 h: 0.6760 [95% CI 0.6425–0.7097] vs. 0.5964 [95% CI 0.5622–0.6306] vs. 0.6760 [95% CI 0.6427–0.7099] vs 0.3967 [95% CI 0.3662–0.4271]; 6–12 h: 0.6380 [0.6031–0.6729] vs. 0.6032 [0.5705–0.6406] vs. 0.6055 [0.5682–0.6383] vs 0.4023 [95% CI 0.3709–0.4337]). External validation was performed on the data of patients in the respiratory critical care unit of the Chinese PLA General Hospital. Compared with LSTM, random forest and time-dependent cox regression model, the NIMRF model was still the best, with an AUC of 0.9366 [95% CI 0.9157–0.9575 for predicting death risk in 0–1 h]. The corresponding AUCs of LSTM, random forest and time-dependent cox regression model were 0.9263 [95% CI 0.9039–0.9486], 0.7437 [95% CI 0.7083–0.7791] and 0.2447 [95% CI 0.2202–0.2692], respectively. Interpretation of the model revealed that vital signs (systolic blood pressure, heart rate, diastolic blood pressure, respiratory rate, and body temperature) were highly correlated with events of death.ConclusionUsing the NIMRF model can integrate ICU multidimensional variable data, especially vital sign variable data, to accurately predict the death events of ICU patients. These predictions can assist clinicians in choosing more timely and precise treatment methods and interventions and, more importantly, can reduce invasive procedures and save medical costs.

Estimating aboveground biomass of urban trees based on ICESat-2 LiDAR and Zhuhai-1 hyperspectral data

Accurately and quickly estimating the aboveground biomass (AGB) of urban trees is crucial for assessing their ecological benefits and providing a scientific basis for city managers. The spaceborne LiDAR (ICESat-2) data offers vital vertical structure information of trees for precise AGB estimation. However, its discrete footprints limit spatially continuous AGB estimation. This study pioneers the integration of ICESat-2 and hyperspectral (Zhuhai-1) images for the estimation of AGB of trees in Shenzhen city, south of China. The study comprises three main steps. First, land cover classification based on GaoFen-6 images was conducted to extract the tree areas. Second, an AGB estimation model based on ICESat-2 photon features yields AGB values for all ICESat-2 footprints. Finally, a Random Forest (RF) regression model linking the AGB of footprints with narrowband vegetation indices from the Zhuhai-1 data was built to produce a wall-to-wall AGB map of Shenzhen. The results indicated that the 70th percentile of vegetation photon height was the optimal feature for estimating AGB within ICESat-2 footprints (R2: 0.62, RMSE: 4.45 kg/m2). For wall-to-wall AGB estimation based on RF regression, narrowband vegetation indices like SIPI, PSI, MNDVI, ARI2, CI2, and ACI2 were crucial, achieving an R2 of 0.55 and an RMSE of 3.88 kg/m2. This suggests that the combination of ICESat-2 and Zhuhai-1 data has a good ability to estimate the AGB of urban trees on a large scale and provides a new approach for forest resource studies in urban areas.

Hybrid Random Forest Regression and Artificial Neural Networks for Modelling and Monitoring the State of Health of Li-Ion Battery

Lithium-ion batteries play a significant role in modern energy storage systems for a number of applications, including renewable energy installations, electric cars, and portable devices. In order to guarantee the long-term dependability and safety of these battery packs, comprehensive modelling and monitoring approaches are required for accurate State of Health (SoH) evaluation. This research suggests an innovative strategy that combines the strengths of Random Forest Regression (RFR) and Artificial Neural Networks (ANN) for reliable Li-ion battery SoH modelling and monitoring. The research starts with the collection of thorough Li-ion battery data, which includes voltage, current, temperature, and cycling characteristics. The battery dataset's nonlinear relationships are captured utilising RFR as the main modelling method. In terms of feature selection and prediction precision, RFR's ensemble of decision trees shines, making it a strong contender for modelling complex battery behaviour. The SoH prediction is then enhanced by the use of ANN, a deep learning framework renowned for its ability to extract detailed patterns from data. The characteristics of RFR are complemented by ANN's capacity to discover hidden features and nonlinear correlations, improving the overall prediction performance. The suggested hybrid approach, that combines RFR and ANN, is trained and verified utilising a diverse database acquired from Li-ion battery sources under operational circumstances. To assess the prediction accuracy of a suggested framework measures like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values are employed. The outcomes show that the hybrid RFR-ANN model works better than the individual RFR and ANN models, producing better SoH predictions. A viable solution for real-time Li-ion battery health monitoring is provided by this combination of conventional ML and deep learning approaches, which demonstrates the synergy among complexity and interpretability. This research advances battery SoH assessment and paves the way for the practical incorporation of precise monitoring systems into applications like electric vehicles, where timely and accurate SoH data is essential for maximising battery performance and extending operational lifespan.