Search

The design of a Dielectric Resonator Antenna (DRA) utilizing machine learning approaches is presented in this study. Antennas are an essential part of a wireless network. An antenna with a decent design will reduce system requirements and improve overall system performance. Full-wave electromagnetic simulation is exact and necessary in antenna design. Still, it takes more time to perform, resulting in enormous challenges in designing, optimizing, and performing sensitivity analysis. The data in this study is subjected to several Machine Learning (ML) algorithms for optimizing antenna efficiency and S-parameter value. To expedite antenna design, machine learning-assisted optimization (MLAO) has proven to be the most effective method. A wide range of regression techniques, including as Support Vector Machine (SVM), Decision Tree Regression (DTR), and Random Forest Regression (RFR), have been used in machine learning (ML) techniques to develop antenna models, enabling quick response prediction and optimum S11 value. Multiple MLAO algorithms have been implemented using these machine-learning techniques for various applications out of which Decision Tree Regression and Random Forest Regression outperforms among all the above-mentioned algorithms with 99.98% and 99.99% of accuracy. First, a broad overview of recent advancements in ML approaches for antenna modelling is presented.

International audience; The present study assessed the visible and short wave infrared (VNIR-SWIR) laboratory spectroscopy coupled random forest regression (RF) technique for predicting soil properties in the southern Karnataka Plateau, India. The spectral data acquired for about 228 profile samples were used to predict key soil properties. The RF model fits well for the spectral prediction of clay (R-2 = 0.65), sand (R-2 = 0.60), cation exchange capacity (R-2 = 0.74), field capacity (R-2 = 0.65) and permanent wilting point (R-2 = 0.72). Wherein soil organic carbon was poorly predicted with an R-2 of 0.22 and RPD of 1.2 due to its lower content and narrow range (0.8 to 20 g kg(-1)). The spectral assessment by PCA showed that the first (50%) and third (34%) components had high spectral variation and significantly correlated with soil properties such as pH, CEC, clay, FC, and PWP related to wavelengths indicating clay minerals and iron oxides. However, the second component had less spectral variation (13%) that is related to wavelengths indicating various organic components and correlated well with SOC. Thus, the VNIR-SWIR spectroscopy could be a suitable supplementary method for rapidly predicting soil properties related to clay minerals and iron oxides.

Dissolved gas analysis is an important method for diagnosing the operating condition of power transformers. Traditional methods such as IEC Ratios and Duval Triangles and Pentagon methods are not applicable in the case of abnormal or missing values of DGA data. A novel transformer fault diagnosis method based on an extreme gradient boosting algorithm is proposed in this paper. First, the traditional statistical method is replaced by the random forest regression algorithm for filling in missing values of dissolved gas data. Normalization and feature derivation of the outlier data is adopted based on the gas content. Then, hyperparameter optimization of the transformer fault diagnosis model based on an extreme gradient boosting algorithm is carried out using the tree-structured probability density estimator algorithm. Finally, the influence of missing data and optimization algorithms on transformer fault diagnosis models is analyzed. The effects of different algorithms based on incomplete datasets are also discussed. The results show that the performance of the random forest regression algorithm on missing data filling is better than classification and regression trees and traditional statistical methods. The average accuracy of the fault diagnosis method proposed in the paper is 89.5%, even when the missing data rate reaches 20%. The accuracy and robustness of the TPE-XGBoost model are superior to other machine learning algorithms described in this paper, such as k-nearest neighbor, deep neural networks, random forest, etc.

Study region: The natural river basins of Chile. Study focus: Drought effects on terrestrial ecosystems produce hydroclimatic stress with variable extensions. Particularly, hydrological drought duration can provide a better understanding of recovery together with catchment characteristics and climatology. This study focuses on the impacts of the multi-year drought experienced in Chile for more than a decade. The recovery of relevant catchment variables to quantify the drought termination (DT) and drought termination duration (DTD) after the hydrological drought is presented. A composite analysis of natural catchments using the CAMELS-CL data set discharge (1988–2020), k-NDVI (2000–2020), and soil moisture (1991–2020) provides the average response of the recovery after severe droughts. New hydrological insights for the region: This study demonstrates that local catchment properties can explain the recovery of studied variables after a hydrological drought. Explanatory variables from CAMELS-CL to derive the DT using random forest regression (RFR) were used with a strong correlation of 0.92, 0.84, and 0.89 for discharge, vegetation productivity, and soil moisture, respectively. The discharge patterns show longer recovery over environments dominated by shrublands with less precipitation and higher temperatures, in central Chile, while higher latitudes with higher vegetation cover, increasing precipitation, and lower temperatures present shorter recovery times. The vegetation productivity shows longer recovery over highly vegetated mountains in central Chile. The soil moisture recovery spatial distribution presented patterns that connect them with the discharge recovery. This work enables the identification of drought vulnerability, which is valuable for managing water resources and ecosystems and is helping to predict drought recovery periods in regions with a lack of observations.

Karst springs are important water sources for both human needs and environmental flows. The responses of karst springs to hydrometeorological factors vary depending on local conditions. In this study, we investigated Martandnag spring in the Liddar catchment in the Kashmir valley of northern India. We used statistical time series (autocorrelation and cross-correlation) and machine-learning (ML) techniques (random forest regression (RFR) and support vector regression (SVR)) to characterize how rainfall, temperature, and snow cover affect the karst spring flow and predict the future responses of the spring stage based on climate scenarios, in the Intergovernmental Panel on Climate Change Assessment Report 6. The statistical time series showed that the memory effect of Martandnag spring varies from 43 to 61 days, indicating moderate karstification and a relatively high storage capacity of the karst aquifer in the Liddar catchment. The delay between recharge and discharge varies from 13 to 44 days, and it is more strongly correlated to snow/ice melt than to rainfall. The ML analysis shows that SVR outperformed RFR in predicting spring flow. Under all climate scenarios, a trained SVR model showed that spring flow increased during the late winter to early spring, and decreased during the summer (except in August) and in autumn. Scenarios with increased greenhouse gas emissions further reduced flow in the summer and autumn. These predictions can be helpful for water-resource planning in similar watersheds in the Western Himalayas.

— The purpose of this paper is to predict the price of houses. House Price Index (HPI) is commonly used to estimate the changes in housing price. It requires additional information because house price is significantly connected with other features like area, location, and population. A comparative study of some Machine Learning algorithm. I tested a regression models such Random Forest Regression, Linear Regression, Lasso Regression and Decision Tree Algorithm are done in this paper. Linear Regression and Decision Tree is often used for classification and predictive analytics. Random Forest Regression is a model used for both classification and regression. The accuracy of the three algorithms in predicting house prices are calculated and the highest accuracy obtained in Linear Regression and Lasso Regression was around 62 % for the given dataset. The accuracy of Random Forest Regression model is 55 %. The accuracy of Decision Tree model is 38 %. Thus, by developing this model, it can predict the price of house in bases of given dataset and person get an idea about the house price.

— This research aims to investigate the use of predictive analysis in accurate fare prediction, which has become an important aspect for businesses such as Ola and Uber. Machine learning and artificial intelligence techniques are being employed to improve fare prediction accuracy. To achieve the most precise results, the study will compare various algorithms, including Random forest regression and classification, which are widely used for prediction modelling. Unlike in the past where fare estimation was solely based on distance, the current fare is influenced by multiple variables such as time of day, location, traffic conditions, duration of the ride, and base fare. This study will therefore explore the use of these variables to improve the accuracy of fare prediction.

The erratic distribution of rainfall greatly affects people's daily activities, especially in Semarang City, so it is necessary to predict rainfall. Correct prediction of rainfall can improve community preparedness in dealing with natural disasters. Algorithms for machine learning and data mining have been extensively utilized in research involving rainfall data from various regions. The primary objectives of this study are to find the best regression algorithm and use machine learning algorithms to predict rainfall in Semarang. The dataset used is daily rainfall data for the City of Semarang from the meteorological, climatological, and geophysical agency (BMKG). Machine learning algorithms such as multiple linear regression, random forest regression, and replicated neural networks will be used to conduct regression analysis on this dataset. The mean absolute error and Root mean squared error techniques are utilized to evaluate the performance of machine learning algorithms. With an error rate of 13.055 for root mean squared error (RMSE) and 6.621 for mean absolute error (MAE), the results of the research indicate that the performance of the neural network algorithm is superior to that of other algorithms.

Age estimation from developmental traits is typically assessed in isolation, where an age range is derived from known individuals that exhibit that degree of fusion. There are no objective means for incorporating developmental evidence from multiple areas of the skeleton into one cohesive age estimate. This limitation is obvious in the casework at the Defense POW/MIA Accounting Agency (DPAA), where subjectivity is introduced into age estimates based on multiple age indictors. This holds true even when age is derived from one source, The 1957 study by McKern and Stewart). This study uses 388 individuals from the McKern and Stewart study and 41 individuals from the Battle of Tarawa and uses Random Forest Regression (RFR) to estimate an age interval using multiple age indicators. These RFR estimates are compared to age estimates from the Forensic Anthropology Reports (FARs). Overall, FAR age estimates are more accurate (92.7%) than those from the two RFR models (80.5% and 76.6%). This increase in accuracy comes at the cost of some precision (FARs average age interval of 8.1 years and RFR average age intervals of 6.3 and 6.4 years). The RFR models prefer age indicators with late fusion, such as the medial clavicle, and the pubic symphysis, which exhibit a combination of developmental and degenerative ages in morphology. Some avenues for further research are discussed.

Monitoring forest conditions is an essential task in the context of global climate change to preserve biodiversity, protect carbon sinks and foster future forest resilience. Severe impacts of heatwaves and droughts triggering cascading effects such as insect infestation are challenging the semi-natural forests in Germany. As a consequence of repeated drought years since 2018, large-scale canopy cover loss has occurred calling for an improved disturbance monitoring and assessment of forest structure conditions. The present study demonstrates the potential of complementary remote sensing sensors to generate wall-to-wall products of forest structure for Germany. The combination of high spatial and temporal resolution imagery from Sentinel-1 (Synthetic Aperture Radar, SAR) and Sentinel-2 (multispectral) with novel samples on forest structure from the Global Ecosystem Dynamics Investigation (GEDI, LiDAR, Light detection and ranging) enables the analysis of forest structure dynamics. Modeling the three-dimensional structure of forests from GEDI samples in machine learning models reveals the recent changes in German forests due to disturbances (e.g., canopy cover degradation, salvage logging). This first consistent data set on forest structure for Germany from 2017 to 2022 provides information of forest canopy height, forest canopy cover and forest biomass and allows estimating recent forest conditions at 10 m spatial resolution. The wall-to-wall maps of the forest structure support a better understanding of post-disturbance forest structure and forest resilience.

Rainfall forecasting is critical for the economy, but it has proven difficult due to the uncertainties, complexities, and interdependencies that exist in climatic systems. An efficient rainfall forecasting model will be beneficial in implementing suitable measures against natural disasters such as floods and landslides. In this paper, a novel hybrid model of empirical mode decomposition (EMD) and random forest (RF) was developed to enhance the accuracy of annual rainfall prediction. The EMD technique was utilized to decompose the rainfall signal into six intrinsic mode functions (IMFs) to extract underlying patterns, while the RF algorithm was employed to make predictions based on the IMFs. The hybrid RF–IMF model was trained and tested using a dataset of annual rainfall in Kerala from 1871 to 2020, and its performance was compared to traditional models such as RF regression and the autoregressive moving average (ARMA) model. Mean absolute error (MAE), mean absolute percentage error (MAPE), mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination or R-squared (R2) were used to compare the performances of these three models. Model evaluation metrics show that the RF–IMF model outperformed both the RF model and ARMA model.

The main research question addressed in the paper is related to the possibility of medium-term forecasting of the public debts of the EU member states. The analysis focuses on a broad range of indicators (macroeconomic, fiscal, monetary, global, and convergence) that influence the public debt levels of the EU member states. A machine learning prediction model using random forest regression was approbated with the empirical data. The algorithm was applied in two iterations—a primary iteration with 33 indicators and a secondary iteration with the 8 most significant indicators in terms of their influence and forecasting importance regarding the development of public debt across the EU. The research identifies a change in the medium term (2023–2024) in the group of the four most indebted EU member states, viz., that Spain will be replaced by France, which is an even more systemic economy, and will thus increase the group’s share of the EU’s GDP. The results indicate a logical scenario of rising interest rates with adverse effects for the fiscal imbalances, which will require serious reforms in the public sector of the most indebted EU member states.

This study applies the ‘Flexible-Acceptor’ variant of the General Solubility Equation, GSE(Φ,B), to the prediction of the aqueous intrinsic solubility, log10 S0, of FDA recently-approved (2016–2020) ‘small-molecule’ new molecular entities (NMEs). The novel equation had been shown to predict the solubility of drugs beyond Lipinski’s ‘Rule of 5’ chemical space (bRo5) to a precision nearly matching that of the Random Forest Regression (RFR) machine learning method. Since then, it was found that the GSE(Φ,B) appears to work well not only for bRo5 NMEs, but also for Ro5 drugs. To put context to GSE(Φ,B), Yalkowsky’s GSE(classic), Abraham’s ABSOLV, and Breiman’s RFR models were also applied to predict log10 S0 of 72 newly-approve NMEs, for which useable reported solubility values could be accessed (nearly 60% from FDA New Drug Application published reports). Except for GSE (classic), the prediction models were retrained with an enlarged version of the Wiki-pS0 database (nearly 400 added log10 S0 entries since our recent previous study). Thus, these four models were further validated by the additional independent solubility measurements which the newly-approved drugs introduced. The prediction methods ranked RFR ~ GSE (Φ,B) > ABSOLV > GSE (classic) in performance. It was further demonstrated that the biases generated in the four separate models could be nearly eliminated in a consensus model based on the average of just two of the methods: GSE (Φ,B) and ABSOLV. The resulting consensus prediction equation is simple in form and can be easily incorporated into spreadsheet calculations. Even more significant, it slightly outperformed the RFR method.

Turbid water is known to affect aquatic ecosystems. If the spread of turbid water can be predicted, it is expected to lead to the prediction of damage caused by turbid water in rich aquatic ecosystems and aquaculture farms, and to countermeasures against turbid water. In this study, we developed a method for predicting the area of high-turbidity water using machine learning with satellite-observed total suspended solids (TSS) product and relatively readily available meteorological and oceanographic data (rainfall, wind direction and speed, atmospheric pressure, and tide level) in the past and evaluated it for the Kuma River estuary of the Yatsushiro Sea in Japan. The results showed that the highest accuracy was obtained using random forest regression, with a coefficient of determination of 0.552, when the area of high-turbidity water based on the previous day’s TSS product and hourly meteorological and oceanographic data from the previous day were used as inputs. The most important factor for the prediction was the area of high-turbidity water, followed by wind, and tide level, but the effect of rainfall was small, which was probably due to the flood-control function of the river. Our future work will be to evaluate the applicability of the method to other areas, improve the accuracy, and predict the distribution area.

Background: Tuberculosis (TB) is a public health problem worldwide, and the influence of meteorological and air pollutants on the incidence of tuberculosis have been attracting interest from researchers. It is of great importance to use machine learning to build a prediction model of tuberculosis incidence influenced by meteorological and air pollutants for timely and applicable measures of both prevention and control. Methods: The data of daily TB notifications, meteorological factors and air pollutants in Changde City, Hunan Province ranging from 2010 to 2021 were collected. Spearman rank correlation analysis was conducted to analyze the correlation between the daily TB notifications and the meteorological factors or air pollutants. Based on the correlation analysis results, machine learning methods, including support vector regression, random forest regression and a BP neural network model, were utilized to construct the incidence prediction model of tuberculosis. RMSE, MAE and MAPE were performed to evaluate the constructed model for selecting the best prediction model. Results: (1) From the year 2010 to 2021, the overall incidence of tuberculosis in Changde City showed a downward trend. (2) The daily TB notifications was positively correlated with average temperature (r = 0.231), maximum temperature (r = 0.194), minimum temperature (r = 0.165), sunshine duration (r = 0.329), PM2.5 (r = 0.097), PM10 (r = 0.215) and O3 (r = 0.084) (p < 0.05). However, there was a significant negative correlation between the daily TB notifications and mean air pressure (r = −0.119), precipitation (r = −0.063), relative humidity (r = −0.084), CO (r = −0.038) and SO2 (r = −0.034) (p < 0.05). (3) The random forest regression model had the best fitting effect, while the BP neural network model exhibited the best prediction. (4) The validation set of the BP neural network model, including average daily temperature, sunshine hours and PM10, showed the lowest root mean square error, mean absolute error and mean absolute percentage error, followed by support vector regression. Conclusions: The prediction trend of the BP neural network model, including average daily temperature, sunshine hours and PM10, successfully mimics the actual incidence, and the peak incidence highly coincides with the actual aggregation time, with a high accuracy and a minimum error. Taken together, these data suggest that the BP neural network model can predict the incidence trend of tuberculosis in Changde City.

In this study, the device characteristics of silicon nanowire feedback field-effect transistors were predicted using technology computer-aided design (TCAD)-augmented machine learning (TCAD-ML). The full current–voltage (I-V) curves in forward and reverse voltage sweeps were predicted well, with high R-squared values of 0.9938 and 0.9953, respectively, by using random forest regression. Moreover, the TCAD-ML model provided high prediction accuracy not only for the full I-V curves but also for the important device features, such as the latch-up and latch-down voltages, saturation drain current, and memory window. Therefore, this study demonstrated that the TCAD-ML model can substantially reduce the computational time for device development compared with conventional simulation methods.

Effective water quality management and reliable environmental modeling depend on the availability, size, and quality of water quality (WQ) data. Observed stream water quality data are usually sparse in both time and space. Reconstruction of water quality time series using surrogate variables such as streamflow have been used to evaluate risk metrics such as reliability, resilience, vulnerability, and watershed health (WH) but only at gauged locations. Estimating these indices for ungauged watersheds has not been attempted because of the high-dimensional nature of the potential predictor space. In this study, machine learning (ML) models, namely random forest regression, AdaBoost, gradient boosting machines, and Bayesian ridge regression (along with an ensemble model), were evaluated to predict watershed health and other risk metrics at ungauged hydrologic unit code 10 (HUC-10) basins using watershed attributes, long-term climate data, soil data, land use and land cover data, fertilizer sales data, and geographic information as predictor variables. These ML models were tested over the Upper Mississippi River Basin, the Ohio River Basin, and the Maumee River Basin for water quality constituents such as suspended sediment concentration, nitrogen, and phosphorus. Random forest, AdaBoost, and gradient boosting regressors typically showed a coefficient of determination R2>0.8 for suspended sediment concentration and nitrogen during the testing stage, while the ensemble model exhibited R2>0.95. Watershed health values with respect to suspended sediments and nitrogen predicted by all ML models including the ensemble model were lower for areas with larger agricultural land use, moderate for areas with predominant urban land use, and higher for forested areas; the trained ML models adequately predicted WH in ungauged basins. However, low WH values (with respect to phosphorus) were predicted at some basins in the Upper Mississippi River Basin that had dominant forest land use. Results suggest that the proposed ML models provide robust estimates at ungauged locations when sufficient training data are available for a WQ constituent. ML models may be used as quick screening tools by decision makers and water quality monitoring agencies for identifying critical source areas or hotspots with respect to different water quality constituents, even for ungauged watersheds.

Tidal flats are among the ecologically richest areas of the world where sediment composition (e.g. median grain size and silt content) and the macrozoobenthic presence play an important role in the health of the ecosystem. Regular monitoring of environmental and ecological variables is essential for sustainable management of the area. While monitoring based on field sampling is very time-consuming, the predictive performance of these variables using satellite images is low due to the spectral homogeneity over these regions. We tested a novel approach that uses features from a variational autoencoder (VAE) model to enhance the predictive performance of remote sensing images for environmental and ecological variables of tidal flats. The model was trained using the Sentinel-2 spectral bands to reproduce the input images, and during this process, the VAE model represents important information on the tidal flats within its layer structure. The information in the layers of the trained model was extracted to form features with identical spatial coverage to the spectral bands. The features and the spectral bands together form the input to random forest models to predict field observations of the sediment characteristics such as median grain size and silt content, as well as the macrozoobenthic biomass and species richness. The maximum prediction accuracy of feature-based maps was close to 62% for the sediment characteristics and 37% for benthic fauna indices. The encoded features improved the prediction accuracy of the random forest regressor model by 15% points on average in comparison to using just the spectral bands. Our method enhances the predictive performance of remote sensing, in particular the spatiotemporal dynamics in median grain size and silt content of the sediment thereby contributing to better-informed management of coastal ecosystems.

В статье проанализирована статистическая информация с официального статистического сайта Венгрии, относящаяся к стоимости жилищного строительного производства в этой стране, а также количество разрешений, выданных на строительство жилья, количество жилых зданий, которые будут построены, базовая площадь возводимых жилых зданий и инвестиции в жилищное строительство национальной экономики. После проведения корреляционного анализа построены три регрессионные модели: классическая линейная регрессия, и две модели машинного обучения: дерево решений и случайный лес. Приведено сравнение числовых характеристик точности и адекватности построенных моделей. Все расчеты проводились с помощью языка программирования Python., The article analyses statistical information from the official statistical website of Hungary related to the value of housing construction production in this country, as well as the number of permits issued for housing construction, the number of residential buildings to be constructed, the base area of residential buildings to be constructed and the investment in housing construction of the national economy. Following a correlation analysis, three regression models are constructed: a classical linear regression, and two machine learning models: a decision tree and a random forest. A comparison of the numerical characteristics of accuracy and adequacy of the constructed models is given. All calculations were performed using the Python programming language., Экономика и предпринимательство, Выпуск 5 (154) 2023, Pages 636-641

The aim of this study was to investigate the potential of using structural analysis parameters for estimating the higher heating value (HHV) of biomass by obtaining information on the composition of cellulose, lignin, and hemicellulose. To achieve this goal, several nonlinear mathematical models were developed, including polynomials, support vector machines (SVMs), random forest regression (RFR) and artificial neural networks (ANN) for predicting HHV. The performed statistical analysis “goodness of fit” showed that the ANN model has the best performance in terms of coefficient of determination (R2 = 0.90) and the lowest level of model error for the parameters X2 (0.25), RMSE (0.50), and MPE (2.22). Thus, the ANN model was identified as the most appropriate model for determining the HHV of different biomasses based on the specified input parameters. In conclusion, the results of this study demonstrate the potential of using structural analysis parameters as input for HHV modeling, which is a promising approach for the field of biomass energy production. The development of the model ANN and the comparative analysis of the different models provide important insights for future research in this field.

This thesis explores the implementation of Optical Character Recognition (OCR) – based text extraction and random forest regression analysis for housing market valuation, specifically focusing on the impact of value factors, derived from OCR-extracted economic values from housing cooperatives’ annual reports. The objective is to perform price estimations using the Random Forest model to identify the key value factors that influence the estimation process and examine how the economic values from annual reports affect the sales price. The thesis aims to highlight the often-overlooked aspect that when purchasing an apartment, one also assumes the liabilities of the housing cooperative. The motivation for utilizing OCR techniques stems from the difficulties associated with manual data collection, as there is a lack of readily accessible structured data on the subject, emphasizing the importance of automation for effective data extraction. The findings indicate that OCR can effectively extract data from annual reports, but with limitations due to variation in report structures. The regression analysis reveals the Random Forest model’s effectiveness in estimating prices, with location and construction year emerging as the most influential factors. Furthermore, incorporating the economic values from the annual reports enhances the accuracy of price estimation compared to the model that excluded such factors. However, definitive conclusions regarding the precise impact of these economic factors could not be drawn due to limited geographical spread of data points and potential hidden value factors. The study concludes that the machine learning model can be used to make a credible price estimate on cooperative apartments and that OCR methods prove valuable in automating data extraction from annual reports, although standardising report format would enhance their efficiency. The thesis highlights the significance of considering the housing cooperatives’ economic values when making property purchases.

In this study, predicting ability of support vector machines (SVM), Gaussian process (GP), artificial neural network (ANN), and Random forests (RF) based regression approaches was tested on the infiltration data of soil samples having different compositions of sand, silt, clay, and fly ash. In addition to this, their performances were compared with the Kostiakov model (KM) and Philip’s model (PM). Dataset containing a total of 392 observations was collected from the experimental measurements of soil infiltration rate on different soil samples. Out of the total dataset, 272 recordings were randomly selected for training and the residual 120 observations were selected for validation of the developed models. Standard statistical parameters were used to measure the predicting ability of various developed models. The result suggests that the best performance could be achieved by Polynomial kernel function-based GP regression (GP_Poly) with coefficient of correlation values as 0.9824, 0.9863, Bias values as 0.0006, −2.3542, root-mean-square error values as 47.7336, 40.3026, and Nash Sutcliffe model efficiency values as 0.9655, 0.9727 using training and testing dataset, respectively. Furthermore, time is found as the most influencing input variable for predicting the infiltration rate when GP_Poly-based model is used to predict the infiltration rate.

Accurate above-ground biomass (AGB) estimation across multiple spatial and temporal scales is essential for mitigating climate change and optimizing forest management strategies. The aim of the present study was to investigate the potential of Sentinel optical and Synthetic Aperture Radar (SAR) data in reliably estimating the plot-level total stem biomass (TSB), which constitutes the dominant material among the different tree components of AGB (stem, branches, and leaves). The study area was located in a dense coniferous forest characterized by an uneven-aged structure and intense topography. A random forest (RF) regression analysis was performed to develop TSB predictive models using Sentinel-1 and -2 images in an individual and combined manner. Consequently, three RF models were produced and evaluated for their predictive performance through the k-fold cross-validation (CV) method. The results showcased that the individual use of Sentinel-1 contributed to the production of the most accurate plot-level TSB estimates (i.e., coefficient of determination-R2 = 0.74, relative mean square error (RMSE) = 1.76 Mg/1000 m2, mean absolute error (MAE) = 1.48 Mg/1000 m2), compared to the use of Sentinel-2 data individually and the Sentinel-1 and -2 combination. In fact, the synergistic use of optical and SAR data led to the generation of an RF model that only marginally underperformed the SAR model (R2 = 0.73 and R2 = 0.72, respectively).

Crop growth and yield monitoring are essential for food security and agricultural economic return prediction. Remote sensing is an efficient technique for measuring growing season crop canopies and providing information on the spatial variability of crop yields. In this study, ten vegetation indices (VIs) derived from time series PlanetScope and Sentinel-2 images were used to investigate the potential to estimate corn grain yield with different regression methods. A field-scale spatial crop yield prediction model was developed and used to produce yield maps depicting spatial variability in the field. Results from this study clearly showed that high-resolution PlanetScope satellite data could be used to detect the corn yield variability at field level, which could explain 15% more variability than Sentinel-2A data at the same spatial resolution of 10 m. Comparison of the model performance and variable importance measure between models illustrated satisfactory results for assessing corn productivity with VIs. The green chlorophyll vegetation index (GCVI) values consistently produced the highest correlations with corn yield, accounting for 72% of the observed spatial variation in corn yield. More reliable quantitative yield estimation could be made using a multi-linear stepwise regression (MSR) method with multiple VIs. Good agreement between observed and predicted yield was achieved with the coefficient of determination value being 0.81 at 86 days after seeding. The results would help farmers and decision-makers generate predicted yield maps, identify crop yield variability, and make further crop management practices timely.

Monitoring and management of grapevine water status (GWS) over the critical period between flowering and veraison plays a significant role in producing grapes of premium quality. Although unmanned aerial vehicles (UAVs) can provide efficient mapping across the entire vineyard, most commercial UAV-based multispectral sensors do not contain a shortwave infrared band, which makes the monitoring of GWS problematic. The goal of this study is to explore whether and which of the ancillary variables (vegetation characteristics, temporal trends, weather conditions, and soil/terrain data) may improve the accuracy of GWS estimation using multispectral UAV and provide insights into the contribution, in terms of direction and intensity, for each variable contributing to GWS variation. UAV-derived vegetation indices, slope, elevation, apparent electrical conductivity (ECa), weekly or daily weather parameters, and day of the year (DOY) were tested and regressed against stem water potential (Ψstem), measured by a pressure bomb, and used as a proxy for GWS using three machine learning algorithms (elastic net, random forest regression, and support vector regression). Shapley Additive exPlanations (SHAP) analysis was used to assess the relationship between selected variables and Ψstem. The results indicate that the root mean square error (RMSE) of the transformed chlorophyll absorption reflectance index-based model improved from 213 to 146 kPa when DOY and elevation were included as ancillary inputs. RMSE of the excess green index-based model improved from 221 to 138 kPa when DOY, elevation, slope, ECa, and daily average windspeed were included as ancillary inputs. The support vector regression best described the relationship between Ψstem and selected predictors. This study has provided proof of the concept for developing GWS estimation models that potentially enhance the monitoring capacities of UAVs for GWS, as well as providing individual GWS mapping at the vineyard scale. This may enable growers to improve irrigation management, leading to controlled vegetative growth and optimized berry quality.

To predict the variability of dam water levels, parametric Multivariate Linear Regression (MLR), stochastic Vector AutoRegressive (VAR), Random Forest Regression (RFR) and Multilayer Perceptron (MLP) Artificial Neural Network (ANN) models were compared based on the influences of climate factors (rainfall and temperature), climate indices (DSLP, Aridity Index (AI), SOI and Niño 3.4) and land-use land-cover (LULC) as the predictor variables. For the case study of the Gaborone dam and the Bokaa dam in the semi-arid Botswana, from 2001 to 2019, the prediction results showed that the linear MLR is not robust for predicting the complex non-linear variabilities of the dam water levels with the predictor variables. The stochastic VAR detected the relationship between LULC and the dam water levels with R2 > 0.95; however, it was unable to sufficiently capture the influence of climate factors on the dam water levels. RFR and MLP-ANN showed significant correlations between the dam water levels and the climate factors and climate indices, with a higher R2 value between 0.890 and 0.926, for the Gaborone dam, compared to 0.704–0.865 for the Bokaa dam. Using LULC for dam water predictions, RFR performed better than MLP-ANN, with higher accuracy results for the Bokaa dam. Based on the climate factors and climate indices, MLP-ANN provided the best prediction results for the dam water levels for both dams. To improve the prediction results, a VAR-ANN hybrid model was found to be more suitable for integrating LULC and the climate conditions and in predicting the variability of the linear and non-linear time-series components of the dam water levels for both dams.

Classroom management is the process of using resources effectively to achieve goals. Planning the schedule is not easy because sometimes, after a schedule designed and when the schedule is published and used, there are problems where the class division of a course is not right on target. This study used the random forest regression method to predict the number of class participants. Data pattern affects the accuracy of calculating the predicted value. The best RMSE and MAE results in the Matematika Dasar Course are 6,51 for RMSE and 2,12 for MAE. At the same time, the prediction of course participant number is 73,18.&nbsp

Using a large database of U.S. seasoned equity offering (SEO) announcements from 2010 to 2015, we examine the effects of several explanatory variables—firm specific, macroeconomic, fixed income, and stock market variables—on the announcement period abnormal stock returns and on the longer-run post-issue abnormal returns. We use five different statistical methods—multivariate linear regression, regression on a reduced model using principal components analysis, year-by-year regression on a reduced model using principal components analysis, random forest regression on the whole sample, and year-by-year random forest regression. In general, across the methods, we find that firm’s profitability in the recent past is an important explanatory factor in both short-term and long-term abnormal stock returns, but several other significant explanatory factors change based on the statistical method used. Therefore, the statistical method used affects the results reported.

Exploiting Renewable energy to the maximum extent possible in an electric vehicle charging station (EVCS) is the key in supporting the anticipated carbon reduction from the electric vehicles (EVs). Knowing the expected load and the solar energy in advance at the EVCS can be crucial in framing a proper energy management strategy. Selection of suitable parameters associated with the participating EVs and EVCS are vital in utilizing them for predicting the probable EV load and expected solar energy for a given period under consideration. A prototype EVCS with smart communication infrastructure is developed considering solar pv as the energy source. Real time communication of the parameters between multiple agents has been established effectively using an interactive website, cloud server and an short message service (SMS) application programming interface (API). The data generated from the prototype models have been utilized in a random forest regression (RFR) classifier model in order to predict the probable solar energy and the expected EV load for every minute duration. The integrated communication frame work is found to be less complex to implement for an autonomous direct current (DC EVCS). The details provided at the graphical user interface (GUI) designed at the EVCS can be instrumental in developing a proper energy management strategy.

White paper: The aim of this work is to apply and analyze machine learning methods for uncertainty quantification of turbulence models. In this work we investigate the classical and data-driven variants of the eigenspace perturbation method. This methodology is designed to estimate the uncertainties related to the shape of the modeled Reynolds stress tensor in the Navier-Stokes equations for Computational Fluid Dynamics (CFD). The underlying methodology is extended by adding a data-driven, physics-constrained machine learning approach in order to predict local perturbations of the Reynolds stress tensor. Using separated two-dimensional flows, we investigate the generalization properties of the machine learning models and shed a light on impacts of applying a data-driven extension.

Objective To study the application of a machine learning algorithm for predicting gestational diabetes mellitus (GDM) in early pregnancy. Methods This study identified indicators related to GDM through a literature review and expert discussion. Pregnant women who had attended medical institutions for an antenatal examination from November 2017 to August 2018 were selected for analysis, and the collected indicators were retrospectively analyzed. Based on Python, the indicators were classified and modeled using a random forest regression algorithm, and the performance of the prediction model was analyzed. Results We obtained 4806 analyzable data from 1625 pregnant women. Among these, 3265 samples with all 67 indicators were used to establish data set F1; 4806 samples with 38 identical indicators were used to establish data set F2. Each of F1 and F2 was used for training the random forest algorithm. The overall predictive accuracy of the F1 model was 93.10%, area under the receiver operating characteristic curve (AUC) was 0.66, and the predictive accuracy of GDM-positive cases was 37.10%. The corresponding values for the F2 model were 88.70%, 0.87, and 79.44%. The results thus showed that the F2 prediction model performed better than the F1 model. To explore the impact of sacrificial indicators on GDM prediction, the F3 data set was established using 3265 samples (F1) with 38 indicators (F2). After training, the overall predictive accuracy of the F3 model was 91.60%, AUC was 0.58, and the predictive accuracy of positive cases was 15.85%. Conclusions In this study, a model for predicting GDM with several input variables (e.g., physical examination, past history, personal history, family history, and laboratory indicators) was established using a random forest regression algorithm. The trained prediction model exhibited a good performance and is valuable as a reference for predicting GDM in women at an early stage of pregnancy. In addition, there are certain requirements for the proportions of negative and positive cases in sample data sets when the random forest algorithm is applied to the early prediction of GDM.

In order to improve the prediction accuracy and efficiency of coal mine gas emission, a coal mine gas emission prediction method based on random forest regression is proposed. The bootstrap self-service resampling technology is used to collect training sample data and construct a random forest regression model. The mean value of the decision tree output value is taken as the prediction result of coal mine gas emission and the out-of-bag data is used to evaluate the prediction performance of the regression model. The optimal hyperparameters of the random forest regression model are determined by calculating the mean of squared residuals and goodness of fit of the out-of-bag data. The increase in the mean of squared residuals of the out-of-bag data is used to characterize the importance of the characteristic variables. All the characteristic variables of coal mine gas emission are replaced by some characteristic variables with cumulative influence weight of 90%. And eight characteristic variables with high importance are selected as input variables of the model, including coal mining height, coal thickness, coal seam gas content, recovery rate, burial depth, daily progress, mining intensity and adjacent layers spacing. The test results show that the random forest regression model with all characteristic variables and some characteristic variables has good prediction performance. After selecting characteristic variables, the average absolute error of the model decreases from 022 m3/min to 021 m3/min, and the average relative error decreases from 355% to 347%. The random forest regression model based on characteristic variable selection reduces the dimensionality of the characteristic variables of the prediction model, reduces the original data acquisition work, and improves the prediction efficiency under the premise of ensuring better prediction performance.

Marine aerosol is one of the most important natural aerosols. It has a significant impact on marine climate change, biochemical cycling and marine ecosystems. Previous studies on marine aerosols, especially in the South China Sea, were carried out by satellite and shipborne measurements. The above methods have drawbacks, such as low temporal–spatial resolution and signal interference. However, lidar has high accuracy and high temporal–spatial resolution, so it is suitable for high-precision long-term observations. In this work, we obtain marine aerosol data using Mie Lidar in Sansha, an island in the South Chain Sea. Firstly, by comparing boundary layer height (BLH) between Sansha and Hefei, we found that Sansha’s boundary layer height has significant differences with that of inland China. Secondly, we compare the aerosol extinction coefficients and their variation with height in Sansha and Hefei. Finally, we obtain hourly averaged aerosol optical depth at Sansha and explore its relation with weather. To analyze the AOD–weather relation, we select three meteorological factors (sea surface temperature, mean sea level pressure and 10 m u-component of wind) based on their feature importance, which is determined by random forest regression. We also analyze the relationship between AOD and the above meteorological factors in each season separately. The results show that there is a strong relation between the meteorological factors and AOD in spring and summer, while there is no clear correlation in fall and winter. These analyses can provide valid data for future researches on marine aerosols in the South China Sea.

To overcome limitations of currently used blood pressure measurement devices in accuracy, continuity and comfort, we propose an approach for blood pressure estimation from electrocardiogram (ECG) signals only. Thereby, statistical signal features are extracted from the ECG which, eventually, serve as input to a random forest regression. The method is trained and tested on MIMIC III waveform data with a large range of blood pressure values. It obtains a mean absolute error ± standard deviation of 3.73 ± 5.19 mmHg for diastolic blood pressure (DBP) and 5.92 ± 7.23 mmHg for systolic blood pressure (SBP), with Pearson coefficients ΥDBP=0.92 and ΥSBP=0.91 respectively.

A novel machine learning approach to circumvent the tedious work associated with solving PBPK models

The Mara River Basin of Africa has a world-famous ecosystem with vast vegetation, which is home to many wild animals. However, the basin is experiencing vegetation degradation and bad climate change, which has caused conflicts between people and wild animals, especially in dry seasons. This paper studied the vegetation greenness (VG), vegetation greenness trends (VGT), and their responses to climate change in dry seasons in the Mara River Basin, Africa. Firstly, based on Google Earth Engine (GEE) platform and Sentinel-2 images, the vegetation distribution map of the Mara River Basin was drawn. Then dry seasons MODIS NDVI data (January to February and June to September) were used to analyze the VGT. Finally, a random forest regression algorithm was used to evaluate the response of VG and VGT to temperature and precipitation derived from ERA5 from 2000 to 2019 at a resolution of 250 m. The results showed that the VGT was fluctuating in dry seasons, and the spatial differentiation was obvious. The greenness increasing trends both upstream and downstream were significantly larger than that of in the midstream. The responses of VG to precipitation were almost twice larger than temperature, and the responses of VGT to temperature were about 1.5 times larger than precipitation. The climate change trend of rising temperature and falling precipitation will lead to the degradation of vegetation and the reduction of crop production. There will be a vegetation degradation crisis in dry seasons in the Mara River Basin in the future. Identifying the spatiotemporal changes of VGT in dry seasons will be helpful to understand the response of VG and VGT to climate change and could also provide technical support to cope with climate-change-related issues for the basin.

En önemli ve hayati insan faaliyetlerden biri olarak tarım, küresel, yerel ve çevresel sorunlara karşı oldukça savunmasızdır. Bu kırılganlık COVID-19 pandemisinin ilk aşamalarında da görülmüştür. Bu bağlamda, söz konusu durumların tarımsal ürünlerin talep ve fiyatlama dinamikleri üzerinde önemli etkilerinin olduğu söylenebilmektedir. Yine de tarımsal faaliyetlerin temel amacı, mahsul verimi ve üretimini iyileştirmek olduğu ifade edilebilir. Türkiye'nin hızla değişen koşullarla başa çıkabilmesi için, 11. Kalkınma Planının da ana hedeflerinden biri olarak belirtilen veriye dayalı tarımsal bilgi sistemlerini geliştirmeye devam etmesi gerekmektedir. Dolayısıyla doğru üretim miktarı tahmini, kritik bir görev olarak öne çıkmaktadır. Bu doğrultuda, 1990-2019 dönemi için meteorolojik parametreler, tarım ilacı kullanımı ve rekolteye dayalı veri setlerini kullanarak, Türkiye'deki dokuz ana mahsulün üretim miktarı tahmininde makine öğrenmesi yöntemlerinin geçerliliğinin değerlendirilmesi, bu çalışmanın temel amacı olarak ifade edilebilir. Eğitim aşamasından sonra tüm modellerle üretim miktarı tahmini yapılmış, elde edilen sonuçlar gerçek değerlerle karşılaştırılmıştır. Sonuçlara göre Karar Ağacı Regresyon (KAR) ve Rastgele Orman Regresyon (ROR) yöntemleriyle, bilhassa buğday, arpa ve mısır için başarılı tahminler alınmış, Destek Vektör Regresyon (DVR) yönteminin ise tutarsız tahminler verdiği görülmüştür., Agriculture, as one of the most important and vital human activity, is highly vulnerable to global, local and environmental issues. This fragility also surfaced in the initial stages of the COVID-19 pandemic. Accordingly, such matters are considered to have dramatic impacts on demand and pricing dynamics of agricultural products. Nonetheless, improving crop yield and its estimation is the fundamental goal of agricultural activities. To cope with the rapidly changing circumstances, Turkey needs to keep developing data-based agricultural information systems which is also stated as one of the main objectives of the 11th development plan. Therefore, accurate crop yield prediction appears to be a critical task. In this context, using meteorological parameters, pesticides use and crop yield values during 1990-2019, evaluation of machine learning regression methods in the yield prediction of nine major crops in Turkey can be stated as the main aim of this research. After the training, all models are used to predict crop yields and acquired values were compared with actual figures. The results showed that successful predictions were obtained by using the Decision Tree Regression (DTR) and Random Forest Regression (RFR) especially for wheat, barley and maize yields; however, Support Vector Regression (SVR) showed inconsistent predictions.

Land surface temperature (LST) is a vital parameter in the surface energy budget and water cycle. One of the most important foundations for LST studies is a theory to understand how to model LST with various influencing factors, such as canopy structure, solar radiation, and atmospheric conditions. Both physical-based and empirical methods have been widely applied. However, few studies have compared these two categories of methods. In this paper, a physical-based method, soil canopy observation of photochemistry and energy fluxes (SCOPE), and two empirical methods, random forest (RF) and long short-term memory (LSTM), were selected as representatives for comparison. Based on a series of measurements from meteorological stations in the Heihe River Basin, these methods were evaluated in different dimensions, i.e., the difference within the same surface type, between different years, and between different climate types. The comparison results indicate a relatively stable performance of SCOPE with a root mean square error (RMSE) of approximately 2.0 K regardless of surface types and years but requires many inputs and a high computational cost. The empirical methods performed relatively well in dealing with cases either within the same surface type or changes in temporal scales individually, with an RMSE of approximately 1.50 K, yet became less compatible in regard to different climate types. Although the overall accuracy is not as stable as that of the physical method, it has the advantages of fast calculation speed and little consideration of the internal structure of the model.

Firefighters face numerous challenges when entering burning structures to rescue trapped victims, assess the conditions of a residential structure, and extinguish the fire as quickly as possible. These challenges include extreme temperatures, smoke, toxic gases, explosions, and falling objects, which can hinder their efficiency and pose risks to their safety. Accurate information and data about the burning site can help firefighters make informed decisions about their duties and determine when it is safe to enter and evacuate, reducing the likelihood of casualties. This research presents unsupervised deep learning (DL) to classify the danger levels at a burning site and an autoregressive integrated moving average (ARIMA) prediction model to forecast temperature changes using the extrapolation of a random forest regressor. The DL classifier algorithms provide the chief firefighter with an awareness of the danger levels in the burning compartment. The prediction models forecast the rise in temperature from a height ranging from 0.6 m to 2.6 m and the changes in temperature over time at an altitude of 2.6 m. Predicting the temperature at this altitude is critical as the temperature increases faster with height, and elevated temperatures can weaken the building’s structural material. We also investigated a new classification method using an unsupervised DL autoencoder artificial neural network (AE-ANN). The prediction data analytical approach included using the autoregressive integrated moving average (ARIMA) with random forest regression implementation. The proposed AE-ANN model, with an accuracy score of 0.869, did not perform as well compared to previous work, with an accuracy of 0.989, at achieving high accuracy scores for the classification task using the same dataset. However, the random forest regressor and our ARIMA models are analyzed and evaluated in this work, while other research has not utilized this dataset, even though it is open-sourced. However, the ARIMA model demonstrated remarkable predictions of the trends of temperature changes in a burning site. The proposed research aims to classify fire sites into dangerous levels and predict temperature progression using deep learning and predictive modeling techniques. This research’s main contribution is using a random forest regressor and autoregressive integrated moving average models to predict temperature trends in burning sites. This research demonstrates the potential of using deep learning and predictive modeling to enhance firefighter safety and decision-making processes.

Soil organic matter (SOM) is a critical indicator of soil nutrient levels, and the precise mapping of its spatial distribution through remote sensing is essential for soil regulation, precise fertilization, and scientific management and protection. This information can offer decision support to agricultural management departments and various agricultural producers. In this paper, two new soil indices, NLIrededge2 and GDVIrededge2, were proposed based on the sensitive spectral response characteristics of SOM in Northeast China. Nine parameters suitable for SOM mapping and modeling were determined using the competitive adaptive reweighted sampling (CARS) method, combined with spectrum reflectance, mathematical transformations of reflectance, vegetation indices, and so on. Then, utilizing unmanned aerial vehicle (UAV)-based multispectral images with centimeter-level resolution, a random forest machine learning algorithm was used to construct the inversion model of SOM and mapping SOM in the study area. The results showed that the random forest algorithm performed best for estimating SOM (R2 = 0.91, RMSE = 0.95, MBE = 0.49, and RPIQ = 3.25) when compared with other machine learning algorithms such as support vector regression (SVR), elastic net, Bayesian ridge, and linear regression. The findings indicated a negative correlation between SOM content and altitude. The study concluded that the SOM modeling and mapping results could meet the needs of farmers to obtain basic information and provide a reference for UAVs to monitor SOM.

In order to achieve a virtual certification process and robust designs for turbomachinery, the uncertainty bounds for Computational Fluid Dynamics have to be known. The formulation of turbulence closure models implies a major source of the overall uncertainty of Reynolds-averaged Navier-Stokes simulations. We discuss the common practice of applying a physics constrained eigenspace perturbation of the Reynolds stress tensor in order to account for the model form uncertainty of turbulence models. Since the basic methodology often leads to overly generous uncertainty estimates, we extend a recent approach of adding a machine learning strategy. The application of a data-driven method is motivated by striving for the detection of flow regions, which are prone to suffer from a lack of turbulence model prediction accuracy. In this way any user input related to choosing the degree of uncertainty is supposed to become obsolete. This work especially investigates an approach, which tries to determine an a priori estimation of prediction confidence, when there is no accurate data available to judge the prediction. The flow around the NACA 4412 airfoil at near-stall conditions demonstrates the successful application of the data-driven eigenspace perturbation framework. Furthermore, we especially highlight the objectives and limitations of the underlying methodology.

Dam behavior prediction is a classic problem in the monitoring of dam structure. To obtain accurate results, different researchers have established various models. However, the models of predecessors rarely studied the nonlinear characteristics of dam displacement data and the abnormal values of monitoring data. It means that abnormal values will contaminate data set, and consequently reduce the accuracy of model predictions. In this article, an improved Random Forest (RF) model was proposed for analyzing dam displacement prediction and was coupled with a sliding time window strategy. The proposed model is developed by the following steps. First, for the purpose of alleviating the time-lag effect of impact factor phenomenon, a sliding time window strategy was introduced into the RF model to improve the time sensitivity. Second, aiming to determine the hyperparameters, Grid Search (GS) was introduced into RF model to improve the global optimization ability. This article takes masonry arch dam in China as an example, and adopts the horizontal displacement recorded by Global Navigation Satellite Systems (GNSS) as the research object. The accuracy and validity of the proposed model are verified and evaluated based on the evaluation criteria. The simulation results demonstrate that the proposed model could capture the long-term characteristics and provide better prediction based on short-term monitoring data. It also has strong robustness on the abnormal data series, has simpler structures and less parameters, and requires less time for model training, so it can be a potential tool for actual monitoring tasks.

Harvest time is an important factor affecting grain yield and postharvest quality. The estimation of crop maturity greatly supports farmers in the optimization of the harvest time. This study proposed a method for predicting paddy rice maturity (J816 and 5Y4 varieties) using color features and the random forest (RF) regression algorithm. Paddy panicle images were obtained using a flatbed scanner during the maturation period. To estimate paddy rice maturity, 22 color features representing the greenness of crop leaves were extracted from the paddy panicle images. Stepwise regression was used to select superior features as inputs to the RF regression model. The coefficient of determination (R2) and root mean square error (RMSE) values of the model were 0.93 and 1.18% for J816 and 0.94 and 1.60% for 5Y4, respectively. The results indicate that the proposed method in this study is a promising technique for the estimation of paddy rice maturity.

To improve the navigation performance of the navigation system combining inertial navigation system (INS) and global positioning system (GPS) under complicated environments, especially GPS outages, a navigation method - wavelet neural network based on random forest regression (RFR-WNN) to assist adaptive Kalman filter (AKF) - is proposed. AKF is employed to correct INS errors, the Kalman filter is improved by introducing adaptive factor, to suppress the influence of the complex environment and random errors on the filtering accuracy; RFR-WNN is used to construct a high-precision prediction model when GPS works well, and to provide the required observations for AKF update when GPS outages. To solve the problem that the single neural network structure is easy to cause the overfitting, unstable and low prediction accuracy due to the lack of comprehensive training samples, RFR is introduced to optimize the single WNN, which can improve the generalization ability and prediction accuracy. In order to verify the effectiveness and advancement of the proposed method, vehicle navigation experiments were carried out, the results indicate that the proposed method has better navigation accuracy and performance than compared methods during GPS outages, and this advantage is more obvious in the case that fewer samples are collected.

As a key link between top-down regulators and bottom-up factors, zooplankton responds sensitively to environmental variations and provides information on the ecological state of freshwater systems. Although the response of zooplankton to anthropogenic pressures and fluctuating natural conditions, such as nutrient loading and climate change, has been extensively examined, findings have varied markedly. The mechanistic basis for the correlation between environmental variability and the zooplankton community is still debated, particularly for subtropical eutrophic lakes. We used two methods to analyze physicochemical and selected biological variables derived from long-term monitoring of Lake Taihu, a subtropical shallow lake in China. We first applied random forest regression to examine how changes in zooplankton were related to a set of environmental variables on interannual time scales. Then we used the results to guide the construction of a conceptual model for piecewise structural equation modeling (pSEM) to quantify more precisely the zooplankton–environment relationship. Zooplanktivorous fish and nutrient concentrations were the most important predictors of long-term trends in zooplankton in RF regression. Intensification of planktivorous fish predation led to a lower zooplankton biomass and smaller individuals through the removal of larger crustaceans. Moreover, suppression of zooplankton can in part be explained by increases in inedible algae, triggered by a combination of reduced nutrient concentrations and weakened grazer control. These results were also confirmed in the pSEM, which further indicated that top-down regulators might be more important than bottom-up factors for the zooplankton community in Lake Taihu. Our results suggest that stocking of filter-feeding fish in the lake did not meet the expectation that they would control algae, but that the use of biomanipulation measures considering both water quality and fishery management seems promising. This study offers insights into how indicator metrics of zooplankton can improve our understanding of the associations between plankton communities and ecosystem alterations.

Since the 21st century, large cities around the world have experienced the transition from economically destructive development to a harmonious eco-environment. Understanding the dynamic relationships between human activities and urban eco-environment in this transition is a challenging and essential topic. The normalized difference vegetation index (NDVI) can reflect the urban vegetation cover status well. Socio-economic indexes can present the intensity and spatiality of human activities quantitatively. This work aims to use traditional regression models and machine learning algorithms to analyze the impact of socio-economic factors on NDVI accurately. Random forest regression (RFR) was performed to initially assess the contributions of all factors on NDVI, which was the numerical basis for feature selection. Subsequently, detailed dynamic relationship simulations were implemented using geographically weighted regression. In the case of Wuhan in China, the results showed that the goodness-of-fit of NDVI with socio-economic factors generally exceeded 50%. The influence coefficients changed from negative to positive, and 2010 was the turning point, indicating that human activities gradually played a favorable role in protecting vegetation during this transition period. The urban–rural interface, which was located between urban centers and marginal urban suburbs, was the area where human activities contributed most to vegetation. Thus, policy makers should focus on planning and managing housing construction and vegetation planting in urban–rural interface to relieve the population burden of the central area and improve the environmental conditions of the urban eco-environment subconsciously.

Railway bridges are key assets of a countries’ infrastructure, enabling transport of goods and people through freight and passenger trains. The studied structure is a steel railway bridge subjected to cyclic loading, equipped with 98 Fiber Bragg Gratings. A previous study identified train passages as main drivers of damage, isolated and converted them to fatigue damage. This research aims at predicting this damage through machine learning with available operational data as input (train type, train speed, ...) and adding publicly available data (temperature, humidity, ...). The research uses 4 months’ data of train passages and focuses on passenger trains, as too few freight train passages were recorded. Random Forest regression was selected for its ease of implementation with categorical data and high R-squared score. A model was trained for every sensor point. Additionally, the model classifies sensors based on damage predictability. Finally, the models were used to determine long-term damage caused by different bridge loading scenarios. By fixing a parameter like train type and then randomly sampling from train passages, the remaining train passages until a damage threshold is reached are estimated. By repeating this simulation 1000 times for every scenario, remaining train passages distributions are reached, showing best and worst case estimates.

Phylogenetic analyses under the Maximum Likelihood model are time and resource intensive. To adequately capture the vastness of tree space, one needs to infer multiple independent trees. On some datasets, multiple tree inferences converge to similar tree topologies, on others to multiple, topologically highly distinct yet statistically indistinguishable topologies. At present, no method exists to quantify and predict this behavior. We introduce a method to quantify the degree of difficulty for analyzing a dataset and present Pythia, a Random Forest Regressor that accurately predicts this difficulty. Pythia predicts the degree of difficulty of analyzing a datasetpriorto initiating Maximum Likelihood based tree inferences. Pythia can be used to increase user awareness with respect to the amount of signal and uncertainty to be expected in phylogenetic analyses, and hence inform an appropriate (post-)analysis setup. Further, it can be used to select appropriate search algorithms for easy-, intermediate-, and hard-to-analyze datasets.

Rice is the primary staple food source for Indonesian people, with consumption increasing so that rice production needs to be increased. Rice drought is one of the problems that can hamper rice production. This research aims to determine the best extraction feature between the normalized difference vegetation index (NDVI) and the normalized difference water index (NDWI) in describing rice fields’ dryness. Moreover, using the random forest regression algorithm. This research compares NDVI with NDWI using data originating from Sentinel-2A and retrieved via the google earth engine. Regression algorithms are used in research to predict drought in paddy fields. This research shows that NDVI is better than NDWI in predicting drought using random forest regression algorithms and logistic regression algorithms. The random forest regression algorithm based on the results obtained shows that the average root mean square error (RMSE) on NDVI is 0.018, and NDWI is 0.012. Based on the logistic regression algorithm results, it was found that the average value of RMSE on NDVI was 0.346, and NDWI was 0.336. Based on the results of the RMSE, it shows that the forecasting ability of the random forest regression algorithm is better than the logistic regression.

Several dynamic projects and fault diagnosis of mechanical structures require the knowledge of the acting external forces. However, the measurement of such forces is often difficult or even impossible; in such cases, an inverse problem must be solved. This paper proposes a force identification method that uses the response surface methodology (RSM) based on central composite design (CCD) in conjunction with a random forest regression algorithm. The procedure initially required the finite element modal model of the forced structure. Harmonic analyses were then performed with varied parameters of forces, and RSM generated a dataset containing the values of amplitude, frequency, location of forces, and vibration acceleration at several points of the structure. The dataset was used for training and testing a random forest regression model for the prediction of any location, amplitude, and frequency of the force to be identified with information on only the vibration acquisition at certain points of the structure. Numerical results showed excellent accuracy in identifying the force applied to the structure.