Influence Of Factors Research Articles

Exploring the critical factors influencing the severity of maritime accidents via multinomial logit model with adaptive sparse group lasso penalty

Identifying the most influential factors affecting the severity of maritime accidents is crucial for developing effective strategies to reduce accident losses. However, this task is challenging due to the complex interactions between influencing factors and the presence of numerous irrelevant and redundant factors. As a new effort, this paper proposes a multinomial logit model with adaptive sparse group lasso penalty (MLASGL) to identify critical factors influencing the severity of maritime accidents. To fully illustrate the effect of complex interactions on severity, factor importance is initially evaluated using association rule mining and complex networks. Subsequently, adaptive weights are constructed based on the factor importance evaluation, followed by proposing an adaptive sparse group lasso that can impose a greater penalty on the noise factors. Additionally, considering that severity as a decision-making objective is often a multi-categorical variable, the multinomial logit is utilized to portray the relationship between the influencing factors and severity. Simultaneously, the negative log-likelihood function of the multinomial logit model is incorporated into the proposed adaptive sparse group lasso to eliminate irrelevant and redundant factors, thereby realizing the identification of critical factors. Finally, the feasibility and superiority of the proposed method are demonstrated by analyzing a real maritime accident dataset.

Experimental study of NiTi alloy cardiovascular stent formed via SLM

Selective laser melting (SLM) has garnered significant attention in the manufacturing of cardiovascular stents due to its potential for fabricating customized stents with intricate geometries that meet clinical requirements. This study aims to optimize the SLM parameters for NiTi stents to achieve minimal porosity and surface roughness, and investigate the biocompatibility and compression tests of SLMed stents. Firstly, the single-factor experiments of laser power, scanning speed and hatch spacing are conducted, respectively. Subsequently, a Box-Benhnken experimental was employed to establish regression prediction models for porosity and surface roughness using response surface methodology (RSM). The results show that scanning speed is the most influential factor on porosity, while laser power significantly affects surface roughness. The optimized parameter combination with minimum porosity of 0.165% and surface roughness of 6.17 μm as follows: laser power of 156W, scanning speed of 712mm/s, and hatch spacing of 0.9mm. The relative errors of them are 0.19% and 0.8%, respectively, indicating that the regression model possesses good prediction ability. Additionally, the corrosion rate and nickel ion release gradually increase with the immersion time, reaching the highest corrosion rate of 2.46g/m² and nickel ion release of 1.08μg after 42 days. Besides, the SLMed stent demonstrated good recovery ability in the compression test. The findings promote the utilization of SLM in the manufacturing of NiTi cardiovascular stents for medical implant applications.

Variation pattern, influential factors, and prediction models of PM2.5 concentrations in typical urban functional zones of northeast China

This study investigated the spatial and temporal variations of PM2.5 concentrations in Harbin, China, under the influence of meteorological parameters and gaseous pollutants. The complex relationship between meteorological parameters and pollutants was explored using Pearson correlation analysis and interaction effect analysis. Using the correlation analysis and interaction analysis methods, four mechanical learning models, PCC-Is-CNN, PCC-Is-LSTM, PCC-Is-CNN-LSTM and PCC-Is-BP neural network, were developed for predicting PM2.5 concentration in different time scales by combining the long-term and short-term data with the basic mechanical learning models. The results show that the PCC-Is-CNN-LSTM model has superior prediction performance, especially when integrating short-term and long-term historical data. Meanwhile, applying the model to cities in other climatic zones, the results show that the model performs well in the Dwa climatic zone, while the prediction performance is lower in the CWa climatic zone. This suggests that although the model is well adapted in regions with a similar climate to Harbin, model performance may be limited in areas with complex climatic conditions and diverse pollutant sources. This study emphasizes the importance of considering meteorological and pollutant interactions to improve the accuracy of PM2.5 predictions, providing valuable insights into air quality management in cold regions.

An energy-based criterion for defining slope failure considering the coupling effect of groundwater table and impact loading

Slope instability poses significant risks in tunnel construction, particularly under the influence of impact loading and fluctuations in groundwater table. This study addresses the complexity of energy transformation and distribution in slopes affected by these factors. The research aims to analyze the local dynamic Factor of Safety (FOS) from the perspective of energy-based criterion, considering groundwater table, impact loading, and load position. Key findings indicate that the groundwater table is the most influential factor on slope stability, followed by load position and impact loading. The overall dynamic FOS was observed to peak at 0.35 s and trough appears at 1.0 s during impact loading, stabilizing after 2 s. The evolution of the overall dynamic FOS is explained from the energy dissipation and transformation mechanisms. These insights provide a critical basis for risk assessment and prevention in complex slope scenarios, contributing to sustainable infrastructure development in line with UN SDG 11 (Sustainable Cities and Communities).

Development, Validity, and Reliability of Adolescent Motivation Inventory-Cerebral Palsy

Objectives: Motivation is the most influential factor in the drive and performance of adolescents with cerebral palsy (CP). As identification and analysis of volition in Iranian adolescents with CP seem to be essential, designing appropriate tools for assessing their motivation is crucial. To achieve this goal, we developed an adolescent motivation inventory-CP (AMI-CP) and evaluated its psychometric properties. Methods: In the first phase, item generation was conducted. Next, in the second phase, face and content validities of the items were assessed. Moreover, construct validity was assessed by exploratory factor analysis (EFA) and confirmatory factor analysis (CFA). A total of 304 adolescents with CP participated in the EFA, while 210 adolescents with CP participated in the CFA. Afterward, convergent and discriminant validities of the inventory were measured. Moreover, reliability was evaluated by calculating Cronbach α, McDonald’s omega, average inter-item correlation, composite, and test re-test reliability. Lastly, the standard error of measurement (SEM) and the minimum detectable change (MDC) were applied. Results: Five factors with 22 items were extracted by EFA, accounting for 50.42% of the variance. The results of model fit indexes confirmed the goodness-of-fit of the final model with 20 items. In addition, the AMI-CP had a Cronbach α value of 0.75 and an intra-class correlation coefficient of 0.94. Moreover, the SEM and MDC of the inventory were 2.63 and 7.31, respectively. Discussion: The AMI-CP is a helpful measure of motivation in adolescents with CP. This inventory can enhance the assessment of the CP adolescents’ motivation by evaluating values, interests, personal causation, and physical and social environments.

Spatio-temporal heterogeneity and influencing factors in the synergistic enhancement of urban ecological resilience: Evidence from the Yellow River Basin of China

Urban ecological resilience (UER) reflects the ability of cities to adapt to environmental changes and cope with natural disasters. Further, UER is an important perspective for understanding human–land relations in the Yellow River Basin (YRB). We constructed a novel system of UER evaluation indicators from the perspective of synergistic enhancement, with 99 cities in the YRB as objects for the research conducted from 2011 to 2021. The spatiotemporal heterogeneity and network pattern of UER were measured using the Theil index and modified gravity model. The factors influencing UER in the YRB were analysed using a multiscale geographically weighted regression model. The results show that (1) regarding time-series analysis, the UER in the YRB shows a fluctuating upward trend from 20.89 in 2011 to 26.23 in 2021, with the contribution of ecological image being the largest. The UER at different reaches, urban agglomerations, and cities varied considerably. (2) Regarding spatial analysis, the UER has a 'center-periphery' spatial distribution pattern dominated by provincial capital cities. The spatial network shows a '几'-shaped distribution pattern similar to the YRB mainstream distribution. Regarding UER connectivity, the ability for cross-regional joint development has improved. (3) The main influencing factors were urbanisation rate, education level, Normalized Difference Vegetation Index, and upgrading of the industrial structure, which represent urban development progress and geographical ecological characteristics. This study expands UER measurement and provides a basis and reference for synergistic enhancement of UER in the YRB.

Quality of life among physicians in Egypy and its influencing factors: a cross-sectional study

Doctors have an essential role in healthcare service, and their quality of life (QoL) is crucial for their professional satisfaction and overall well-being. This study assessed the QoL among physicians and explored the influencing factors that affect it. This cross-sectional study was carried out using a self-administered Internet survey. The survey was focused on physicians employed at various hospitals and clinics in Egypt. Data on participants' demographics, work-related factors, and QoL were collected using WHOQOL-BREF. WHOQOL-BREF questionnaire measures a participant's perception of their life quality across various domains, including general health, physical well-being, psychological health, social relationships, and the environment. The scores for each domain are calculated based on participants' responses to specific items, with higher scores indicating a better QoL. The QoL scores were 3.57±1.02 for the general health domain, 12.93±2.49 for physical domain, 12.29±2.67 for psychological domain, 12.87±3.20 for social domain, and 11.00±2.58 for environmental domain. The overall QoL score was 3.64±0.835. The findings indicate a moderate QoL among the participating physicians. The physicians' QoL domains were affected by age, sex, education level, marital status, chronic disease, smoking, speciality, working hours per week, extra working hours, and work experience.

Effects of co-pyrolysis interaction performance of cellulose and lignin on the gas products and hydrogen generation path

In this study, cellulose and lignin were subjected to co-pyrolysis for the production of syngas. For the pyrolysis experiments, three influencing factors were selected using a response surface method: pyrolysis temperature (400–800 °C), residence time (5–30 min), and lignin mass percentage (0–100 wt%). At a pyrolysis temperature of 477.4 °C, a residence time of 30 min, and a lignin mass percentage of 50 wt%, the actual syngas yield was 77.2 % higher than the theoretical value for the co-pyrolysis. In addition, the hydrogen volume fraction was improved by up to 24.87 % because of the interaction between cellulose and lignin during their co-pyrolysis (pyrolysis temperature of 800 °C, residence time of 17.5 min, lignin mass percentage of 80.65 wt%). Finally, the hydrogen formation process was simulated, using reactive force field molecular dynamics. The results showed that hydrogen molecules began to appear at a simulation time of 0.479 ns and then gradually increased in number with progressing simulation time. In addition, the hydrogen generation pathways were obtained by this simulation method. This study provides a data foundation for optimizing syngas and hydrogen production from biomass.

Modeling the spatially varying effects of biophysical factors on land surface temperature

A growing number of studies have investigated how land surface temperature (LST) is influenced by a variety of driving factors; however, little effort has been made to identify the dominant ones. The suggested method used the Upper Awash Basin (UAB), Ethiopia, as an example to explore the spatial heterogeneity and factors affecting LST, which is critical for selecting effective mitigation strategies to manage the thermal environment. The study employed two models: ordinary least squares (OLS) and geographically weighted regression (GWR). The OLS model was first used to capture the overall relationship between LST and some biophysical factors. The GWR was then utilized to investigate the spatial non-stationary relationships between LST and its influencing biophysical factors. Although the method was tested in UAB, Ethiopia, it can be applied in similar agroecosystems, to identify the dominant factors that influence LST and develop site-specific LST mitigation strategies.•The OLS and GWR models investigated the spatial heterogeneities of the influencing factors and LST.•Biophysical parameters such as enhanced vegetation index (EVI), modified normalized difference water index (MNDWI), normalized difference built-up index (NDBI), normalized difference bareness index (NDBaI), albedo and elevation were used as potential driving environmental factors of LST•The models performance was computed using the adjusted coefficient of determination (adj. R2), Akaike Information Criterion (AICc), and residual sum of squares (RSS).

Study on stress concentration and fatigue life of tubing with slip indentation

The indentation caused by slip on the outer wall of tubing is a significant contributor to stress concentration and, consequently, fatigue failure in the tubing string. Through an analysis of the interaction between slips and tubing, a mathematical model to predict slip-tubing interaction and slip crushing load is formulated, accounting for external pressure, internal pressure, and axial forces. On this basis, the influence factors and influence rules of slip crushing load are studied, and three-dimensional yield surface and tri-axial stress ellipse of tubing are investigated, considering different transverse load factors and design factors. To accurately forecast the fatigue life of tubing subjected to slip indentation, two models are established: one for fatigue life prediction and the other for tubing string vibration. In order to quantitatively assess the stress concentration arising from slip indentation, a finite element model of tubing featuring slip indentation is established. Finite element analysis reveals that stress concentration and non-uniformity are evident in the vicinity of slip indentation, with their severity intensifying as the indentation depth grows. The initial step in assessing fatigue life involves fatigue life tests on tubing material subjected to varying stress levels. Subsequently, a case study is conducted and the variations of wellhead pressure and axial stress are evaluated. Fatigue life analysis reveals that the fatigue life is notably sensitive to variations in stress amplitude and slip indentation depth. An increase in the magnitude of alternating stress and the depth of slip indentation will result in a significant reduction in the fatigue lifespan. The methodologies employed in this research, along with the resulting findings, offer a robust theoretical framework and a solid practical basis for forecasting and managing stress concentration and fatigue durability in tubing affected by slip indentation.

Heavy metals in roadside soil along an expressway connecting two megacities in China: Accumulation characteristics, sources and influencing factors

Transportation is widely recognized as a significant contributor to heavy metal (HM) pollution in roadside soils. A better understanding of HM pollution in soils near expressways is crucial, particularly given the rapid expansion of expressway transportation in China in recent years. In this study, 329 roadside topsoil samples were collected along the Beijing-Tianjin Expressway, which connects two megacities in China. Chemical analysis showed that HM concentrations in the soil samples were generally below national limits. The mean pollution index (Pi) values for As, Cr, Cu, Ni, Pb, and Zn ranged from 0.94 to 1.01, while Cd and Hg exhibited slightly higher mean Pi values of 1.19 and 1.13, respectively. The Nemerow integrated pollution index values for all samples ranged from 0.71 to 4.97, with a mean of 1.26. This suggests a slight enrichment of HM above natural background levels, especially for Cd and Hg. Source apportionment using positive matrix factorization revealed that natural sources contributed the most to soil HMs (64.51 %), followed by agricultural sources (19.15 %), traffic sources (9.77 %), and industrial sources (6.57 %). The Shapley additive explanation analysis, based on the random forest model, identified soil organic carbon, deep soil HM content, altitude, total soil K2O, urbanization composite impact index, and total soil P as primary influencing factors. This indicates that the impact of transportation on roadside soils along the Beijing-Tianjin Expressway is currently relatively limited. The prominent influence of soil properties and altitude underscored the importance of “transport” and “receptor” in the soil HMs accumulation process at the local scale. These findings provide critical data and a scientific basis for decision-makers to develop policies for expressway design and roadside soil protection.

Experimental investigation and simulation assessment on fluidity and hot tearing susceptibility of Al-Li-Cu-X alloy: The role of microalloying elements

The meticulous exploration of castability, especially the fluidity and hot tearing susceptibility (HTS), assumes paramount significance in the fabrication of high-quality Al-Li-Cu alloys. In this work, the effect of microalloying elements such as Ti, Mg, Si, Zr, and Sc on the fluidity and HTS of the alloys was systematically investigated, and the significant improvement in fluidity and the reduction in HTS by the addition of these microalloying elements were identified. Comparative analyses with the Al-3Li-1.5Cu alloy reveal a significant increase of up to 45 % in fluidity and a remarkable reduction of up to 83 % in HTS with the addition of these microalloying elements. To unveil the underlying mechanisms, the experimental results were compared with the predictions derived from the CSC criterion, Kou's criterion, and a numerical simulation performed using ProCAST software. The analysis reveals a discrepancy between these predictions and the experimental outcomes, highlighting their limitations in capturing the nuanced effects of minor microalloying elements on fluidity and HTS. Subsequently, a detailed exploration of other influencing factors, including microstructural features, solidification interval, and various thermophysical parameters, was conducted, illuminating the corresponding mechanisms. These findings are expected to provide valuable insights into the fluidity and HTS of Al-Li-Cu-X alloys, thereby contributing to the application and advancement of cast AlLi alloys.

Influence of nano-encapsulated Yucca schidigera extract on ruminal anaerobic gases of methane, carbon monoxide, and hydrogen sulfide production of different carbohydrate-based diets

Saponins, the primary component of Yucca schidigera extract (YSE), are known to influence microbial activity in the rumen, which can affect various fermentation parameters. Moreover, encapsulating YSE with Chitosan (CS) at varying carbohydrate levels (CHO) adds another layer of complexity that can provide valuable insights into the use of additives in mitigating greenhouse gases. This study investigated the impact of both crude and encapsulated forms of YSE on the production of ruminal anaerobic gases in cattle fed different levels of CHO-based diets. Ruminal contents were obtained from four slaughtered, crossbreed bulls (Charollais × Limousin) with a live weight of 400 ± 25 kg. The experimental design followed a completely randomized factorial arrangement, with factors including CHO level (25%, 45%, and 55% DM), YSE forms (without extract, CS, crude, and nano-capsules), and dose of extract (0, 0.25, 0.5 and 1.0 mL/g of DM). Results showed that the type of extract significantly affected asymptotic total gas production, methane (CH4), Hydrogen sulfide (H2S), Carbon monoxide (CO), and dry matter digestibility. Nano-chitosan increased gas production and exhibited greater efficiency in reducing CH4 production by up to 61.36%. While crude YSE reduced CH4 production by 38%, nano-capsules increased production by 17.7% to 42.8%. Furthermore, a significant interaction effect among CHO levels, type of extract, and extract dose was observed, particularly impacting H2S and CH4 production after 48 hours of incubation, alongside an increase of about 25.3% in metabolizable energy compared to the control. The use of CS and YSE significantly (p <0.0001) improved the CH4 conversion efficiency by 71.3% and 23.4% respectively, and at some point, the encapsulation of YSE resulted in a significant reduction in efficiency by up to about 49.5%. The study concluded that both CS and YSE have the potential to enhance digestibility in cattle and reduce CH4 production and its conversion efficiency. However, encapsulating YSE with CS may reduce the efficiency of either compound in optimizing ruminal fermentation, unless other influencing factors are carefully considered. Therefore, the optimal efficacy of nano-encapsulated YSE depends on finding a balance between extract type, dosage, and dietary CHO level.

Gradient boosting decision tree algorithms for accelerating nanofiltration membrane design and discovery

Interfacial polymerization is most widely used strategy for nanofiltration membrane fabrication. Despite extensive research on this technology, further improvement in permeance and salt rejection is still essential due to its multidimensional characteristics, including the types of membrane material and the conditions of membrane optimizing fabrication. Herein, we applied four gradient boosting decision tree algorithms to precisely identify the candidate monomers (represented by the molecular descriptors) and their fabrication conditions. The result of the model evaluation indicated the Extreme Gradient Boosting (XGBoost) algorithm had the best predictive performance in accuracy and generalization in predicting membrane permeance and salt rejection, with the corresponding determination coefficients on the test set being 0.76 and 0.88. Shapley additive explanation analysis showed that the aqueous monomer concentration was the most influential fabrication condition in membrane performance. Besides, the partition coefficient (Log P) and topological polar surface area were the most important molecular descriptors in water permeance and salt rejection, respectively. Overall, this study proposed innovative machine learning algorithms to disentangle the multidimensional interactions of various influencing factors on membrane performance, thus initiating a paradigm shift in the development of high-performance nanofiltration membranes.

Pathways to depressive symptoms in Chinese pregnant women and their influence on delivery approach: a qualitative comparative analysis.

The aim of this study was to apply complexity theory to explain and understand how risk factors combined in complex ways, eventually leading to a high prevalence of depressive symptoms among pregnant women. We also aimed to evaluate whether depressive symptoms affected delivery approach. The study had a longitudinal design and was conducted between May and September 2017. A total of 481 pregnant women were recruited to participate and completed closed-end surveys at two distinct times: during prenatal care at the hospital after 26 weeks of pregnancy and 1 to 4 weeks after delivery. This study identified eleven different pathways that led to an increase in depressive symptoms. Each pathway differentiated the effects of different influencing factors. Among the 481 pregnant women, 128 (26.6%) had cesarean deliveries without medical indications. Although depressive symptoms could affect delivery approach, it was not the most important factor. Surprisingly, the first production emerged as the key factor determining delivery mode. This study was innovative in that it examined which factors and which combinations of factors were necessary for the development of depressive symptoms. Additionally, this study provided a better understanding of the mechanisms underlying the choice of cesarean section without medical indications.

Identifying the influencing factors of soil nitrous acid emissions using random forest model

Gaseous nitrous acid (HONO) plays an important role in atmospheric chemistry, but there is still controversy regarding its sources. Recent studies have shown that soil can emit significant amounts of HONO. In order to further investigate the impact mechanism of soil HONO emissions and refine the estimation model of soil HONO emissions fluxes, this study employed a random forest model to estimate soil HONO emission fluxes and identified key influencing factors. By measuring in the laboratory and integrating global literature on soil HONO emissions, this study analyzed the characteristics of soil HONO emissions and their relationship with environmental factors. The results indicated that croplands emit significantly more HONO than other land use types. Furthermore, during wet-dry cycles, total soil HONO emissions showed a significant positive correlation with NO2- content and clay content, and also correlated significantly with maximum HONO emissions, total NO emissions, and maximum NO emissions (P<0.001). Using a random forest model, a mapping relationship between soil environmental factors and total HONO emissions was constructed, with soil pH, NH4+, NO3-, NO2-, clay, silt, sand, total nitrogen, total carbon, total organic carbon, carbon-nitrogen ratio, and soil texture as input features. The results indicated that the model accounts for 56% of the variance in total soil HONO emissions within the test set. Feature importance analysis of the model indicated that soil texture, pH, NH4+, NO3- and NO2- were key factors in predicting soil HONO emissions. This finding provides valuable information for future predictions of soil HONO emissions.

The effects of joint process parameters of two-step manufacturing processes on the mechanical performance of biocomposites using Taguchi and multiple regression techniques

This study evaluates the influence of joint parameters of extrusion (extrusion profile temperature) and injection molding (barrel profile temperature and mold temperature) manufacturing processes on the mechanical performance of biocomposite materials via the Taguchi and multiple regression techniques. Statistical analysis of variance (ANOVA) was performed to determine the most influential controllable factors for the individual responses. The results of the study revealed that the mechanical properties of the biocomposites are affected by the joint parameters of the two-step manufacturing techniques. This study will help in the process design of biocomposites with improved mechanical performance.

A machine learning-based method for predicting the shear behaviors of rock joints

In this study, machine learning prediction models (MLPMs), including artificial neural network (ANN), support vector regression (SVR), K-nearest neighbors (KNN), and random forest (RF) algorithms, were developed to predict the peak shear stress values and shear stress-displacement curves of rock joints. The database used contained 693 records of peak shear stress and 162 original shear stress-displacement curves derived from direct shear tests. The results demonstrated that the MLPMs provided reliable predictions for shear stress, with the mean squared errors (MSEs) between their predicted and measured shear stress varying from 0.003 to 0.069 and the coefficients of determination (R2 values) varying from 0.964 to 0.998. The feature importance values indicate that the joint surface roughness coefficient (JRC) is the most important influential factor in determining the peak shear stress, followed by the joint wall compressive strength (JCS), basic friction angle (φb), and shear surface area (As). Similarly, for the shear stress-displacement curve, the JRC is the dominant factor, followed by As, φb, and JCS. Additional direct shear tests were conducted for model validation. The validation shows that the MLPM predictions demonstrate improved consistency with the experimental results in relation to both the peak shear stress and peak shear displacement.

Estimation and assessment of water erosion in the Peixe Angical basin, Brazil

Water erosion causes the displacement of soil particles from higher to lower elevations, and this process intensifies when land use and vegetation cover change, such as through the conversion of forests into pastures or agricultural fields. Identifying priority areas for soil and water conservation practices is essential for promoting sustainable agriculture. Equally important is identifying the most influential factors driving erosion, as understanding these can guide effective land management strategies. Machine learning techniques, such as Random Forest, are valuable tools for analyzing large datasets and assessing the importance of variables. The primary aim of this study was to estimate soil losses due to land-use changes in the Peixe Angical Reservoir drainage basin using the Revised Universal Soil Loss Equation (RUSLE) within a Geographic Information System (GIS) framework, and to identify priority areas for soil conservation. Additionally, the study aimed to evaluate the contribution and importance of the RUSLE model factors (R, K, LS, and C) to soil loss using the Random Forest regression algorithm. Soil losses were computed for the chronological scenarios (1990, 2000, 2010, and 2017), using rasters with 90 m resolution to calculate the product of the R, K, LS, and C factors, along with the P factor. These soil losses were classified into erosion risk categories, ranging from very low (0 to 2.5 Mg ha-1 yr-1) to extremely high (greater than 100 Mg ha-1 yr-1). Soil losses in the basin increased over time. The Random Forest algorithm was applied to evaluate the importance of each factor. Rainfall erosivity was found to vary spatially, ranging from 7,047.64 MJ mm ha-1 h-1 yr-1 to 11,348.5 MJ mm ha-1 h-1 yr-1, while the LS factor exhibited values ranging from near 0 to over 20. Litholic Neosol (Entisol) was the predominant soil type in the drainage basin. In terms of land use, forests accounted for the largest portion of the basin: 55.60% in 1990, 51.31% in 2000, 48.88% in 2010, and 48.21% in 2017. The C factor, which reflects vegetation cover, was the most significant contributor to soil loss, accounting for 44.8% in 1990, 43.5% in 2000, 44.2% in 2010, and 44.4% in 2017, followed by the K factor (soil erodibility). These assessment techniques can be utilized in guiding conservation planning, thereby supporting sustainable land use practices.

Analysis of vegetation dynamics from 2001 to 2020 in China's Ganzhou rare earth mining area using time series remote sensing and SHAP-enhanced machine learning

Rare earth mining, essential for modern industries and economic growth, often leads to severe environmental degradation. Previous research has explored the ecological impacts of rare earth mining but has not fully investigated the intricate interplay and subdivisions of environmental and anthropogenic factors driving vegetation changes over extended periods. This study addresses this gap by employing time series remote sensing and SHAP-enhanced machine learning to analyze vegetation dynamics in China's Ganzhou rare earth mining area from 2001 to 2020. Using the kNDVI derived from Landsat data, we identified three distinct vegetation trajectory types: pro-environment, des-environment, and res-environment. An ensemble machine learning model combined with SHAP analysis revealed the cropland area proportion, PM10 levels, and shrubland area proportion as the most influential factors affecting vegetation across all mining types. Additionally, after 2012, the palmer drought severity index and downward surface shortwave radiation emerged as positive contributors to vegetation health, while population pressure had a more substantial negative influence in des-environment areas. Our findings highlight spatial heterogeneity in vegetation recovery patterns and highlight the complex interactions among land cover changes, air quality, climate factors, and human activities in shaping vegetation dynamics. This study provides valuable insights for developing targeted, context-specific restoration strategies in rare earth mining areas, contributing to more sustainable mining practices and global environmental management.