Random Regression Models Research Articles

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.

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

Invasive noxious weed species (INWS) are typical poisonous plants and forbs that are considered an increasing threat to the native alpine grassland ecosystems in the Qinghai–Tibetan Plateau (QTP). Accurate knowledge of the continuous cover of INWS across complex alpine grassland ecosystems over a large scale is required for their control and management. However, the cooccurrence of INWS and native grass species results in highly heterogeneous grass communities and generates mixed pixels detected by remote sensors, which causes uncertainty in classification. The continuous coverage of INWS at the pixel level has not yet been achieved. In this study, objective 1 was to test the capability of Senginel-2 imagery at estimating continuous INWS cover across complex alpine grasslands over a large scale and objective 2 was to assess the performance of the state-of-the-art convolutional neural network-based regression (CNNR) model in estimating continuous INWS cover. Therefore, a novel CNNR model and a random forest regression (RFR) model were evaluated for estimating INWS continuous cover using Sentinel-2 imagery. INWS continuous cover was estimated directly from Sentinel-2 imagery with an R2 ranging from 0.88 to 0.93 using the CNNR model. The RFR model combined with multiple features had a comparable accuracy, which was slightly lower than that of the CNNR model, with an R2 of approximately 0.85. Twelve green band-, red-edge band-, and near-infrared band-related features had important contributions to the RFR model. Our results demonstrate that the CNNR model performs well when estimating INWS continuous cover directly from Sentinel-2 imagery, and the RFR model combined with multiple features derived from the Sentinel-2 imager can also be used for INWS continuous cover mapping. Sentinel-2 imagery is suitable for mapping continuous INWS cover across complex alpine grasslands over a large scale. Our research provides information for the advanced mapping of the continuous cover of invasive species across complex grassland ecosystems or, more widely, terrestrial ecosystems over large spatial areas using remote sensors such as Sentinel-2.

Approximation of reliabilities for random-regression single-step genomic best linear unbiased predictor models

Random-regression models (RRM) are used in national genetic evaluations for longitudinal traits. The outputs of RRM are an index based on random regression coefficients and its reliability. The reliabilities are obtained from the inverse of the coefficient matrix of mixed model equations (MME). The reliabilities must be approximated for large data sets because it is impossible to invert the MME. There is no extensive literature on methods to approximate the reliabilities of RRM when genomic information is included by single-step GBLUP. We developed an algorithm to approximate such reliabilities. Our method combines the reliability of the index without genomic information with the reliability of a GBLUP model in terms of effective record contributions. We tested our algorithm in the 3-lactation model for milk yield from the Czech Republic. The data had 30 million test-day records, 2.5 million animals in the pedigree, and 54,000 genotyped animals. The correlation between our approximation and the reliabilities obtained from the inversion of the MME was 0.98, and the slope and intercept of the regression were 0.91 and 0.02, respectively. The elapsed time to approximate the reliabilities for the Czech data was 21 min.

Modeling the impact of driving aggression on lane change performance Measures: Steering compensatory Behavior, lane change execution duration and crash probability

The current study aimed to investigate the influence of driving aggression on lane change behavior. Drivers belonging to three levels of aggressive driving styles (aggressive, moderately aggressive, and non-aggressive) participated in lane change experiments, and 232 lane change maneuvers were recorded. Steering behavior during lane change maneuvers was investigated using three steering performance measures, including the standard deviations of steering angle, steering reversal rates, and maximum steering swerve. Three separate generalized estimating equation models were developed to analyze the effects of aggressive driving behavior on the standard deviation of steering angle, steering reversal rates, and maximum steering swerve. A Weibull accelerated failure time model with clustered heterogeneity was developed to analyze the effect of aggressive driving behavior on lane change execution duration. Additionally, to model the crash probability during lane change, a random effects logistic regression model was developed. The findings indicate that aggressive and moderately aggressive drivers completed lane changes 59% and 38% faster, respectively, compared to non-aggressive drivers. This implies a propensity for aggressive and moderately aggressive drivers to execute lane changes more swiftly than non-aggressive drivers. Aggressive drivers increased their standard deviation of steering angle, steering reversal rates, and maximum steering swerves by 180%, 60%, and 62%, respectively, compared to non-aggressive drivers. This implies that aggressive drivers engaged in extreme steering behavior as a compensatory measure for their reckless driving in order to avoid a collision during lane change maneuvering. However, despite their vigorous compensatory steering behavior, the crash rate (number of crashes observed) increased by 5.10 and 2.83 times for aggressive and moderately aggressive drivers, respectively, compared to non-aggressive drivers. The findings have implications for developing driving assistance systems and lane change simulation models.

Multi-sensor satellite imagery reveals spatiotemporal changes in peatland water table after restoration

Remote sensing (RS) has been suggested as a tool to spatially monitor the status of peatland ecosystem functioning after restoration. However, there have been only a few studies in which post-restoration hydrological changes have been quantified with RS-based modelling. To address this gap, we developed an approach to assess post-restoration spatiotemporal changes in the peatland water table (WT) with optical (Sentinel-2 and Landsat 7–9) and radar (Sentinel-1) imagery. We tested the approach in eleven northern boreal peatlands (six restored, and five control sites) impacted by forestry drainage in northern Finland using Google Earth Engine cloud computing capabilities. We constructed a random forest regression model with spatiotemporal field-measured WT data as a dependent variable and satellite imagery features as independent variables. To assess the spatiotemporal changes, we constructed representative maps for situations before and after restoration, separately for early summer high-water and midsummer low-water conditions. To further quantify temporal changes during 2015–2023 and to test their statistical significance, we conducted a bootstrap hypothesis test for the areas near the restoration measures and similar areas in the control sites. The regression model had a relatively good fit and explanatory capacity (overall R2 = 0.71, RMSE = 6.01 cm), while there were notable site-specific variations. The WT maps showed that the post-restoration changes were not uniform and concentrated near the restoration measures. The bootstrap test showed that the WT increased more in the restored areas (4.7–8.8 cm) than in the control areas (0.1–5.2 cm). Our results indicate that restoration impact on surface hydrology can be quantified with multi-sensor satellite imagery and a machine learning approach in treeless peatlands.

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.

Does corporate governance influence environmental, social and governance disclosure practices of state‐owned enterprises? An international study

AbstractThis paper provides fresh insights into the impact of corporate governance mechanisms on environmental, social and governance (ESG) disclosure practices of state‐owned enterprises (SOEs). To accomplish this study's research objective, we collected ESG and corporate governance data from Refinitiv Eikon's database on a balanced sample of 253 SOEs from 37 worldwide countries over 5 years (2018–2022), obtaining a total of 1265 observations. A battery of fixed and random effects panel regression models has been estimated to test the impact of board characteristics, like board size, board independence, board gender diversity, number of board meetings, Chief Executive Officer (CEO) duality and the presence of a corporate social responsibility (CSR) committee, on overall and individual ESG disclosure scores of sampled SOEs. Results show that while board size and CEO duality negatively affect SOE ESG disclosure, board independence and gender diversity, as well as the number of board meetings and the existence of a CSR committee, exert a positive influence.

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.

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.

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.

P132 Longitudinal changes in the Scleroderma Health Assessment Questionnaire visual analogue scales in patients with systemic sclerosis: a retrospective cohort study

Abstract Background/Aims The aim was to examine the course, impact of baseline predictors, and relationship with functional ability, of the six Scleroderma Health Assessment Questionnaire (SHAQ) visual analogue scales (VAS) over time in patients with SSc. Methods A retrospective analysis of patients attending annual review visits at a tertiary SSc center between 2005 and February 2020. Linear Mixed-effect models were used to assess longitudinal trajectories and effect of potential prognostic factors on the six different SHAQ VAS, except finger ulcers where the VAS scale was dichotomised (presence/absence) and analysed using a random intercept logistic regression model. To assess whether longitudinal changes in SHAQ VAS correlated with the HAQ-DI/11-point scleroderma functional index, we obtained the gradients of individual linear regression models, overall and by disease type. Results 537 patients (75% lcSSc) with at ≥ 2 available time-points were included. Mean follow-up time and number of review visits were 6.8 (SD = ±4.2) years 6.4 (SD = ±3.7) visits, respectively. The mean (SD) RP and disease duration (defined as the first non-RP symptom) were 7.6 (11.9) and 8.0 (8.2) years, respectively. Time-in-study (Table 1) was associated with increase in VAS intestinal (p = 0.004), overall disease (p = 0.001) and presence of ulcers (p = 0.013). There was a trend observed concerning RP VAS (p = 0.068) and VAS breathing (p = 0.074), and no difference with VAS pain (p = 0.183). Time since RP onset showed a significant negative association with VAS pain (b=-0.01, [95%CI= -0.01 to 0.00], p = 0.032). Age had a significant negative effect on intestinal VAS (b=-0.01 [95%CI= -0.01 to -0.00], p = 0.040). Presence of ulcers increased with disease duration (OR = 0.97 [95%Cl= 0.94 to 1.00], p = 0.026), and in those with diffuse disease (OR = 0.54 [95%CI= 0.31 to 0.95], p = 0.033). For patients who were anti-RNP positive (compared to negative), the overall disease score VAS was higher (b = 0.23, 95%Cl= 0.00 to 0.45, p = 0.048) higher. All correlations between SHAQ VAS scales and function (HAQ-DI and 11-point scleroderma functional index) were positive (Table 2), and were almost exclusively stronger in patients with diffuse disease. Conclusion Longitudinal assessment of the SHAQ VAS scales provides important insights into disease trajectory. We have identified baseline factors associated with VAS outcomes, and associations with function over time. Disclosure M. Hughes: None. Y. Sylvestre: None. J. Manning: None. M. Mandzuk: None. M. Samaranayaka: None. G. Dinsdale: None. A. Herrick: None.

Effect of Capital Structure on the Financial Performance of Ethiopian Commercial Banks

This study aimed to examine the effects of capital structure on the financial performance of Ethiopian commercial banks. The dependent variable, financial performance, is measured by Return on Assets (ROA), while factors such as loan-to-deposit ratio (LDR), asset-to-total equity ratio (ATER), total deposit-to-total asset ratio (TDTAR), capital adequacy ratio (CAD), and asset growth ratio (GA) were used as proxy independent variables to gauge capital structure. Using a quantitative approach and an explanatory research design, this study analyzes 6 years of audited financial reports from 14 commercial banks in Ethiopia. This investigation employs a random effect regression model and Stata 14 software package to explore the relationships among these variables. The result revealed that both the loan-to-deposit ratio and the total deposit-to-total asset ratio have a positive and significant impact on financial performance, while the asset growth ratio showed a negative effect. Based on these findings, this study recommends that bank authorities concentrate on bolstering their deposit base, managing asset growth efficiently, maintaining adequate capital levels, and optimizing leverage levels to improve financial performance and ensure long-term sustainability in the banking sector. Additionally, this research is anticipated to inform policymakers about regulatory frameworks for banks and assist banking managers in formulating effective capital financing strategies within the Ethiopian commercial banking sector, thus enriching the existing literature on the relationship between capital structure and financial performance.

Machine learning-based Nusselt number prediction for falling-film evaporators in absorption refrigeration systems

The evaporator serves as a pivotal component of an absorption refrigeration system (ARS), bolstered by improved wettability and mitigation of the irregular arrangement of the liquid film. The complexities of the evaporation heat transfer characteristics of falling films have led to numerous empirical correlations for falling-film Nusselt number (Nu) estimation, demanding substantial computational resources and experimental expenses and limiting their universal applicability. This study used machine learning to predict Nu of a falling-film evaporator. Artificial neural network (ANN) and random forest regression (RFR) models were used to predict heat transfer characteristics and establish a novel Nu correlation using an experimentally derived dataset. Correlations of falling-film Nu were established for six tube types using empirical data, ANN, and RFR predictions and then compared based on experimental falling-film Nu. The ANN and RFR provided high prediction performance within 10 % error and an R2 of 0.985 and 0.999, respectively. The Nu correlations derived from ANN and RFR demonstrated satisfactory agreement, typically within ±15 % error of experimental results lower than that of the empirical correlations. The optimized ANN and RFR demonstrates their promising ability to predict heat transfer characteristics and establish Nu correlations, thereby reducing the need for immense experimental efforts.

Strategic turnaround: unraveling the impact of CEO power on firm performance during retrenchment

Purpose This paper aims to investigate the impact of retrenchment strategy on firm performance in the context of Pakistani firms while considering the moderating role of chief executive officer (CEO) power. By examining the influence of CEO duality and CEO share ownership on the relationship, this study contributes to strategic management and corporate governance knowledge within the Pakistani business environment. Design/methodology/approach A quantitative approach was used to analyze the relationship using data from annual financial statements. The sample consisted of 76 companies from the KSE-100 index from the year 2015 to 2020. Random effects regression models were used, along with hierarchical regression to explore the moderating effect of CEO power. Findings The findings demonstrate that the implementation of a retrenchment strategy positively impacts firm performance in Pakistani firms. The study also reveals that CEO power plays a crucial role in strengthening the relationship between retrenchment strategy and firm performance. Moreover, the study highlights the importance of considering the temporal sequence, size and age of firms when examining the impact of CEO power and retrenchment strategy on firm performance. Research limitations/implications The study enhances the understanding of the contingent nature of retrenchment strategies and the influence of CEO power in the Pakistani business context. Practically, the research contributes to strategic management and corporate governance dynamics, facilitating the development of strategies that enhance firm performance and sustainability in Pakistan. Originality/value This research provides original insights by specifically focusing on the Pakistani context and analyzing the interplay between retrenchment strategy, CEO power and firm performance. The study adds to the limited literature on the relationship between retrenchment and performance in the Pakistani business environment. Additionally, it highlights the significance of CEO power as a critical factor in determining the success of retrenchment.

Optimizing Parameter Efficiency in Machine Learning Models: A Focus on Reducing Memory Overhead with L-BFGS-Optimized Algorithms

This research addresses the critical challenge of detecting cotton leaf diseases through an advanced image processing and machine learning approach. The study primarily focuses on the extraction of significant features from cotton leaf images to facilitate accurate disease identification. The novelty of this work lies in the application of the Limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) algorithm for optimizing Support Vector Machines (SVM), enhancing the precision of disease detection in cotton leaves. This research method involves a comprehensive process of acquiring high-resolution leaf images, followed by an effective feature extraction technique that isolates crucial characteristics indicative of various plant diseases. Subsequently, these features are employed to train an SVM model optimized by the L-BFGS algorithm, a decision process that marks a significant departure from traditional gradient descent methods in SVM training. A pivotal aspect of this study is the comparative analysis conducted between the proposed L-BFGS-optimized SVM model and prevalent machine learning models including Random Forest, Decision Tree, Regression Models, and K-Nearest Neighbors (KNN). This comparison is grounded on various performance metrics such as accuracy, precision, recall, and F1-score, offering a comprehensive evaluation of each model's effectiveness in disease detection. The results of this research are expected to demonstrate the superiority of the L-BFGS-optimized SVM in terms of accuracy and efficiency in detecting cotton leaf diseases. This advancement holds substantial promise for agricultural technology, potentially leading to more informed and timely decision-making in crop management and disease prevention. The findings of this study aim to contribute significantly to the field of agricultural informatics, particularly in the domain of plant disease detection and management, by providing a more robust, accurate, and efficient tool for farmers and agriculturalists.

Exploring Symbiosis: Innovatively Unveiling the Interplay between the Cold Chain Logistics of Fresh Agricultural Products and the Ecological Environment

Cold chain logistics are crucial for reducing agricultural product loss, yet the environmental impact of energy and packaging consumption, among others, demands attention, making the search for eco-friendly development modes essential. Based on data from 30 provinces in China from 2015 to 2021, this study analyzes the basic correlation between the development of cold chain logistics of fresh agricultural products (CCLFAP) and the ecological environment (EE) by using a random forest regression model in comparison with the XGBoost model. Correlation heatmaps were used to analyze the relationships between the cold chain logistics of fresh agricultural products and various factors of the ecological environment. The generalized additive model was then used to establish the connection between cold chain logistics and the ecological environment, identifying significant factors impacting EE. The results demonstrate that a higher development level of cold chain logistics corresponds to a better development trend of EE. The economic efficiency and technical aspects of cold chain logistics for fresh agricultural products are closely related to ecological pressures and responses. The number of employees in the logistics industry, the trading volume of fresh agricultural products, the number of refrigerated vehicles, and the capacity of the cold room have significant positive correlations with the ecological environment, while the per capita consumption of fresh agricultural products, the number of cold chain logistics patent applications, and the road density had significant negative correlations with the ecological environment. The effects of the number of cold chain logistics enterprises and the freight turnover of agricultural products transported by the cold chain on the ecological environment fluctuated. These findings contribute to reducing climate and environmental emergencies throughout the life cycle, offering sustainable development solutions for the fresh agricultural product cold chain logistics industry.

Early genetic selection of Spanish Trotter Horses by new precocity criteria

National trotting races held in Spain between 1990–2022 were used to estimate genetic para-meters for 5 precocity criteria: age at first ranked race (AFR), age when the animal reached 50% of ranked races (A50%), age when the animal reached the first 10 ranked races (A10), total number of races in which the animal has competed before the first ranked race (NRC) and percentage of first placings/year of participation (PFP), in order to evaluate their usefulness for genetic evaluation and their possible inclusion in the Spanish Trotter Horse official genetic program. A total of 176,137 records belonging to 4947 animals were used. A Bayesian multivariate BLUP animal model showed heritability values between 0.08 (NRC) and 0.44 (A10). Medium-high genetic co-rrelations were obtained between precocity traits, ranging between −0.78 (A10-PFP) and 0.96 (A50%-A10). NRC and PFP exhibited negative correlations, with the lowest range for NRC. Additionally, a Random Regression Model (RRM) was applied to PFP to evaluate changes in performance during the animals’ sporting life. Heritability values decreased slightly up to 4 years of age (0.26–0.17), with a slight increase after the age of 5 (0.22). Genetic and permanent environmental correlations between age groups were in the high range between the nearest age groups. Variations of the expected breeding values (EBV) over the trajectory of all the age groups allowed us to differentiate robust and plastic animals (animals capable of maintaining sporting potential throughout their lives or not). Correlations between the EBV estimated with both methodologies evidenced the benefits of PFP for the early selection of performance traits in STH. Therefore, the application of an RRM for the PFP trait is recommended as it has shown acceptable heritability and adequate correlations with the rest of the precocity criteria studied. The incorporation of this trait in the breed improvement program will allow breeders to have early genetic information on animal precocity potential and ensure the inclusion of more robust individuals in their mating design.

Soft computing to predict the porosity and permeability of pervious concrete based on mix design and ultrasonic pulse velocity

ABSTRACT The present study explores the potential of machine learning to predict the porosity and permeability of pervious concrete constructed on mix parameters (compaction energy, aggregate-to-cement ratio and aggregate size) and ultrasonic velocity. The prediction models use non-destructive measurements and mixed design variables, which can help the construction sector apply the models without any theoretical expertise. The study uses 225 data samples from an experimental study. This study used six machine learning algorithms, namely, linear regression, artificial neural networks, boosted decision tree regression, random forest regression, K-nearest neighbour and support vector regression, to determine the best predictive model. The results show that the ANN model is the best technique for predicting the porosity of pervious concrete (R2 = 0.9502 for training datasets and R2 = 0.8958 for testing datasets) and boosted decision tress for permeability of pervious concrete (R2 = 0.9323 for training datasets and R2 = 0.7574 for testing datasets). The sensitivity analysis of the random forest regression model reveals that ultrasonic pulse velocity is the most influential parameter for the prediction of porosity and permeability of pervious concrete. The proposed models provide a more accurate method for estimating the porosity and permeability of pervious concrete.

How Land Use Transitions Contribute to the Soil Organic Carbon Accumulation from 1990 to 2020

Soil organic carbon stock (SOCS) changes caused by land use changes are still unclear, and understanding this response is essential for many environmental policies and land management practices. In this study, we investigated the temporal–spatial and vertical distribution characteristics of the SOCS in the Western Sichuan Plateau (WSP) using the sparrow search algorithm–random forest regression (SSA-RFR) models with excellent model applicability and accuracy. The temporal–spatial variations in the SOCS were modeled using 1080 soil samples and a set of nine environmental covariates. We analyzed the effect of land use changes on the SOCS in the WSP. The total SOCS increased by 18.03 Tg C from 1990 to 2020. The results of this study confirmed a significant increase in the SOCS in the study area since 2010. There was a 27.88 Tg C increase in the SOCS in 2020 compared to the total SOCS in 2010. We found that the spatial distribution of the SOCS increased from southeast to northwest, and the vertical distribution of the SOCS in the study area decreased with increasing soil depth. Forests and grasslands are the main sources of SOCS the total SOCS in the forest and grassland accounted for 37.53 and 59.39% of the total soil organic carbon (SOC) pool in 2020, respectively. The expansion of the wetlands, forest, and grassland areas could increase the SOCS in the study area. A timely and accurate understanding of the dynamics of SOC is crucial for developing effective land management strategies to enhance carbon sequestration and mitigate land degradation.

Genetic investigations on backfat thickness and body condition score in German Holstein cattle.

Up to now, little has been known about backfat thickness (BFT) in dairy cattle. The objective of this study was to investigate the lactation curve and genetic parameters for BFT as well as its relationship with body condition score (BCS) and milk yield (MKG). For this purpose, a dataset was analysed including phenotypic observations of 1929 German Holstein cows for BFT, BCS and MKG recorded on a single research dairy farm between September 2005 and December 2022. Additionally, pedigree and genomic information was available. Lactation curves were predicted and genetic parameters were estimated for all traits in first to third lactation using univariate random regression models. For BCS, lactation curves had nadirs at 94 DIM, 101 DIM and 107 DIM in first, second and third lactation. By contrast, trajectories of BFT showed lowest values later in lactation at 129 DIM, 117 DIM and 120 DIM in lactation numbers 1 to 3, respectively. Although lactation curves of BCS and BFT had similar shapes, the traits showed distinct sequence of curves for lactation number 2 and 3. Cows in third lactation had highest BCS, whereas highest BFT values were found for second parity animals. Average heritabilities were 0.315 ± 0.052, 0.297 ± 0.048 and 0.332 ± 0.061 for BCS in lactation number 1 to 3, respectively. Compared to that, BFT had considerably higher heritability in all lactation numbers with estimates ranging between 0.357 ± 0.028 and 0.424 ± 0.034. Pearson correlation coefficients between estimated breeding values for the 3 traits were negative between MKG with both BCS (r = -0.245 to -0.322) and BFT (r = -0.163 to -0.301). Correlation between traits BCS and BFT was positive and consistently high (r = 0.719 to 0.738). Overall, the results of this study suggest that BFT and BCS show genetic differences in dairy cattle, which might be due to differences in depletion and accumulation of body reserves measured by BFT and BCS. Therefore, routine recording of BFT on practical dairy farms could provide valuable information beyond BCS measurements and might be useful, for example, to better assess the nutritional status of cows.