39 soil samples surrounding a lead-zinc mining area in Guangxi were collected,and the contents of Pb,Hg,Cd,Cr,As,Cu,Zn,and Ni were determined to investigate the pollution characteristics and sources of heavy metals.Ar...39 soil samples surrounding a lead-zinc mining area in Guangxi were collected,and the contents of Pb,Hg,Cd,Cr,As,Cu,Zn,and Ni were determined to investigate the pollution characteristics and sources of heavy metals.ArcGIS inverse distance weight difference method was used to analyze the characteristics of pollution distribution,and single-factor pollution index,Nemerow comprehensive pollution index,ground accumulation index,and potential ecological risk index were selected to evaluate the characteristics of heavy metal pollution.Based on correlation analysis,the absolute principal component-multiple linear regression(APCS-MLR)and positive definite matrix factorization(PMF)models were used to analyze the sources of soil heavy metals.The results showed that the average concentrations of all eight heavy metals exceeded both national and Guangxi soil background values.Hg,Cd,and Zn exhibited high variation(greater than 0.5),indicating significant external disturbances,and their spatial distribution was closely related to mining activity locations.The single-factor pollution index evaluation indicated varying degrees of pollution risk for Cd,Zn,and As,with Cd and Zn being the most severe pollutants,as 69.23%and 30.77%of the samples fell into the moderate pollution or higher category.The geoaccumulation index analysis ranked the mean pollution levels of the eight elements as follows:Zn>Cd>Ni>Pb>Cu>Cr>Hg>As,with Cd and Zn showing the most severe contamination,and 51.28%of the samples exhibiting moderate or higher pollution levels.The Nemerow comprehensive pollution index evaluation showed that 74.35%of soil samples were classified as moderate to heavy pollution.The potential ecological risk index assessment indicated significant ecological risks posed by Cd and Zn,with 82.05%and 5.12%of the samples classified as causing strong to extreme ecological risks,respectively.The source apportionment analysis revealed minor differences between the two models.The APCS-MLR model identified three pollution sources and their contribution rates:anthropogenic mining sources(31.13%),parent material sources(40.38%),and unidentified sources(28.49%).The PMF model identified three pollution sources with contribution rates of anthropogenic mining sources(26.10%),parent material sources(46.96%),and a combined traffic and agricultural source(26.61%).Pb,Hg,Cd,and Zn mainly originated from mining activities;Cr,As,and Ni were primarily derived from the parent material,while Cu was predominantly attributed to traffic and agricultural sources.These findings provide a scientific basis for the prevention and control of heavy metal pollution in mining areas.展开更多
Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLM...Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.展开更多
Analysis Method of ^(131)I Activity in Carbon Cartridge and Internal Dose Assessment for Nuclear Medicine Workers.Shuo Wang1,Fei Tuo1,Jian-feng Zhang1,Xiao-liang Li1,Bao-lu Yang1,Qiang Zhou1,Ze-shu Li1,Shu-ying Kong1,...Analysis Method of ^(131)I Activity in Carbon Cartridge and Internal Dose Assessment for Nuclear Medicine Workers.Shuo Wang1,Fei Tuo1,Jian-feng Zhang1,Xiao-liang Li1,Bao-lu Yang1,Qiang Zhou1,Ze-shu Li1,Shu-ying Kong1,and Wei-hao Qin1(1.National Institute for Radiological Protection,Chinese Center for Disease Control and Prevention,Beijing,100088,China.)展开更多
Analysis of the environmental and economic performance of fishing vessels has received limited attention compared with other ship types despite their notable contribution to global greenhouse gas(GHG)emissions.This st...Analysis of the environmental and economic performance of fishing vessels has received limited attention compared with other ship types despite their notable contribution to global greenhouse gas(GHG)emissions.This study evaluates the carbon footprint(CF)and economic viability of a liquefied natural gas(LNG)-fueled fishing vessel,using real engine operation simulations to provide precise and dynamic evaluation of fuel consumption and GHG emissions.Operational profiles are obtained through the utilization of onboard monitoring systems,whereas engine performance is simulated using the 1D/0D AVL Boost^(TM)model.Life cycle assessment(LCA)is conducted to quantify the environmental impact,whereas life cycle cost assessment(LCCA)is performed to analyze the profitability of LNG as an alternative fuel.The potential impact of the future fuel price uncertainties is addressed using Monte Carlo simulations.The LCA findings indicate that LNG has the potential to reduce the CF of the vessel by 14%to 16%,in comparison to a diesel power system configuration that serves as the baseline scenario.The LCCA results further indicate that the total cost of an LNG-powered ship is lower by 9.5%-13.8%,depending on the share of LNG and pilot fuels.This finding highlights the potential of LNG to produce considerable environmental benefits while addressing economic challenges under diverse operational and fuel price conditions.展开更多
Objective:To assess prenatal Bisphenol A(BPA)exposure levels and explore their preliminary associations with maternal and fetal characteristics in a population from Northeastern Yunnan.Methods:A cross-sectional analys...Objective:To assess prenatal Bisphenol A(BPA)exposure levels and explore their preliminary associations with maternal and fetal characteristics in a population from Northeastern Yunnan.Methods:A cross-sectional analysis was performed using data and urine samples from 70 pregnant women in their third trimester recruited at Qujing Central Hospital.Urinary BPA was measured by HPLC-MS/MS.Participants were stratified into high and low BPA exposure groups based on the median concentration.Results:BPA was detected in all samples(100%)with a median concentration of 2.41μg/L(IQR:0.68-4.96).The high BPA exposure group(≥2.41μg/L)had a significantly higher proportion of gestational diabetes mellitus(GDM)(42.9%vs.17.1%,p=0.021)and a lower median fetal birth weight(3250 g vs.3450 g,p=0.048)compared to the low exposure group.Conclusion:This pilot study reveals ubiquitous BPA exposure in pregnant women from Northeastern Yunnan.The observed preliminary associations with GDM and reduced fetal birth weight warrant further investigation in larger,longitudinal studies.展开更多
Arbitration is a key non-litigation commercial mechanism for the resolution of disputes, and the quality and credibility of its awards depend largely on the competency of the arbitrators. However, the selection and ev...Arbitration is a key non-litigation commercial mechanism for the resolution of disputes, and the quality and credibility of its awards depend largely on the competency of the arbitrators. However, the selection and evaluation systems for arbitrators in China have long faced challenges such as the vague criteria for competency and an unclear professionalization path for arbitrators. To address these issues, this study is grounded in the context of actual Chinese arbitration practice and based on the competency iceberg model. Through a methodological approach encompassing literature reviews, behavioral event interviews, expert revisions, and questionnaire surveys, a Chinese Arbitrator Competency Scale was developed and validated in this study. Examination of the findings indicated that the scale needed to consist of five dimensions—communication and coordination, cognitive skills, ethical conduct, work motivation, and personality traits—and possess a total of 28 specific indicators. Confirmatory analysis of the factors demonstrates a good fit for the five-dimensional model, with each of the dimensions exhibiting high reliability and validity. This scale is innovative in integrating the competency elements with Chinese characteristics, such as commercial acumen, crosscultural mediation skills, and adaptability to the local rule of law. This research not only enriches the competency theory in regard to the field of human resource management but also provides a scientific framework of standards and measurement tools for the selection, training, and evaluation of arbitrators. It thus has significant practical value for enhancing the professionalism and international competitiveness of China's arbitration system.展开更多
Debris flow events are frequent in Tajikistan,yet comprehensive investigations at the regional scale are limited.This study integrates remote sensing,Geographic Information System,and machine learning techniques to ev...Debris flow events are frequent in Tajikistan,yet comprehensive investigations at the regional scale are limited.This study integrates remote sensing,Geographic Information System,and machine learning techniques to evaluate debris flow susceptibility and associated hazards across Tajikistan.A dataset comprising 405 documented debris flow points and 14 influencing factors,encompassing geological,climatic-hydrological,and anthropogenic variables,was established.Three machine learning algorithms—Random Forest,Support Vector Machine(SVM),and Multi-layer Perceptron—were applied to generate susceptibility maps and delineate debris flow risk zones.The results indicate that the areas of higher and high susceptibility accounted for 20.43%and 4.41%of the national area,respectively,and were predominantly concentrated along the Zeravshan and Vakhsh river basins.Among the evaluated models,SVM model demonstrated the highest predictive performance.Beyond conventional topographic and environmental controls,drought conditions were identified as a critical factor influencing debris flow occurrence within the arid and semi-arid mountainous regions of Tajikistan.These findings provide a scientific basis for regional debris flow risk management and disaster mitigation planning,and offer practical guidance for selecting conditioning factors in machine-learning-based susceptibility assessments in other dry mountainous environments.展开更多
This report presents a forensic evaluation of a case involving blindness(visual acuity grade 5)following a bee/wasp sting to the left eye.Through systematic analysis of the patient’s multiple hospital admissions,post...This report presents a forensic evaluation of a case involving blindness(visual acuity grade 5)following a bee/wasp sting to the left eye.Through systematic analysis of the patient’s multiple hospital admissions,postoperative follow-up data,and a review of the pathological mechanisms of ocular injury caused by bee venom,this study comprehensively assesses the injury characteristics,treatment course,and visual outcomes.Bee venom induces severe complications such as corneal damage,uveitis,cataract,and secondary glaucoma through multiple mechanisms including direct cytotoxicity,immune-inflammatory responses,and enzymatic hydrolysis.Despite interventions including anterior chamber irrigation,phacoemulsification with intraocular lens implantation,and antiglaucoma surgery,the affected eye ultimately lost light perception.Forensic examination confirmed the absence of light perception in the left eye and abnormal visual pathway function,consistent with clinical observations.According to the relevant Chinese disability assessment standard(JR/T 0083-2013,Article 4.2.2),the injury was classified as grade 7 disability.This study provides an in-depth discussion of the mechanisms and key forensic identification points in bee-sting-induced blindness,offering a scientific reference for similar forensic clinical cases.展开更多
Excessive levels of Fluoride(F−)and Cadmium(Cd)in drinking groundwater may pose health risks.This study assessed the health risks associated with F−and Cd contamination in rural drinking groundwater sources in Wutai C...Excessive levels of Fluoride(F−)and Cadmium(Cd)in drinking groundwater may pose health risks.This study assessed the health risks associated with F−and Cd contamination in rural drinking groundwater sources in Wutai County,Shanxi Province,China,to support population health protection,water resource management,and environmental decision-making.Groundwater samples were collected and analyzed,and a Human Health Risk Model(HHRA)was applied to evaluate groundwater quality.The results showed that both contents of F−and Cd in groundwater exceeded the Class III limits of China's national groundwater quality standard(GB/T 14848—2024).Fluoride levels met the Class V threshold,with enrichment area mainly located in the east part of the study area.Cadmium levels reached Class IV,with elevated concentrations primarily observed in the western and northwestern regions.Correlation analysis revealed that F−showed weak or no correlation with other measured substances,indicating independent sources.Health risk assessment results indicated that F−poses potential health risks to rural residents,while cadmium,due to its relatively low concentrations,does not currently present a significant health risk.Among different demographic groups,the health risk levels of F−exposure followed the order:Infants>children>adult females>adult males.The findings highlight that fluoride is the primary contributor to health risks associated with groundwater consumption in the study area.Strengthened monitoring and prevention of F−contamination are urgently needed.This research provides a scientific basis for the prevention and control of fluoride pollution in groundwater and offers practical guidance for safeguarding drinking water safety in rural China.展开更多
Background and Objectives:The perception of sound in the vertical plane supports spatial hearing by enabling listeners to detect sources located above and below.Sounds originating from both the front and back elevatio...Background and Objectives:The perception of sound in the vertical plane supports spatial hearing by enabling listeners to detect sources located above and below.Sounds originating from both the front and back elevations along the mid-sagittal plane further contribute to a three-dimensional auditory experience.This study aimed to characterize the variability in vertical sound localization abilities among normal-hearing(NH)individuals using spatialized audio.Materials and Methods:Fifty-one NH participants(aged 18 to 35 years)completed three vertical localization tasks under headphones as part of a single-group,within-subject experimental study.These tasks included two-plane identification:(1)top-down localization,(2)front-back localization,and one discrimination task in the front plane.Hierarchical Cluster Analysis(HCA)was employed to identify distinct patterns in spatial localization profiles specific to the vertical-median plane.Fisher's Discriminant Function Analysis(FDA)was used to validate the accuracy of HCA and estimate classification error.Results:HCA revealed three distinct listener clusters:(1)cluster 1 with good performance across all three tasks,(2)cluster 2 with selective impairment in top-bottom identification,and(3)cluster 3 with selective deficits in front-back identification.FDA validated group membership of the clusters identified by the HCA,with a prediction accuracy of 98%.Conclusions:Individuals with clinically NH exhibited three distinct vertical localization profiles:uniform performers,those impaired in top-bottom identification,and those impaired in front-back identification.These profiles may be linked to the interplay between acoustic and non-acoustic perceptual factors.展开更多
Nonlinear static procedures are widely adopted in structural engineering practice for seismic performance assessment due to their simplicity and computational efficiency.However,their reliability depends heavily on ho...Nonlinear static procedures are widely adopted in structural engineering practice for seismic performance assessment due to their simplicity and computational efficiency.However,their reliability depends heavily on how the nonlinear behaviour of structural components is represented.The recent earthquakes in Albania(2019)and Türkiye(2023)have underscored the need for accurate assessment techniques,particularly for older reinforced concrete buildings with poor detailing.This study quantifies the discrepancies between default and user-defined component modelling in pushover analysis of pre-modern reinforced concrete structures,analysing two representative low-and mid-rise reinforced concrete frame buildings.The lumped plasticity approach incorporates moment-rotation relationships derived from actual member properties and reinforcement configurations,while the distributed plasticity approach uses software-generated default properties based on modern codes.Results show that the distributed plasticity models systematically overestimate both the strength and the deformation capacity by up to 35%compared to lumped plasticity models,especially in buildings with poor detailing and low concrete strength.These findings demonstrate that default software procedures,widely used in practice but not validated for pre-modern structures,produce dangerously unconservative seismic performance estimates.The study provides quantitative evidence of the critical need for tailored modelling strategies that reflect the actual conditions of the existing building stock.展开更多
To ensure the compatibility between rolling stock and infrastructure when dynamically assessing railway bridges under high-speed traffic,the damping properties considered in the calculation model significantly influen...To ensure the compatibility between rolling stock and infrastructure when dynamically assessing railway bridges under high-speed traffic,the damping properties considered in the calculation model significantly influence the predicted acceleration amplitude at resonance.However,due to the normative specifications of EN 1991-2,which are considered to be overly conservative,damping factors that are far below the actual damping have to be used when predicting vibrations of railway bridges,which means that accelerations at resonance tend to be overestimated to an uneconomical extent.Comparisons between damping factors prescribed by the standard and those identified based on in situ structure measurements always reveal a large discrepancy between reality and regulation.Given this background,this contribution presents a novel approach for defining the damping factor of railway bridges with ballasted tracks,where the damping factor for bridges is mathematically determined based on three different two-dimensional mechanical models.The basic principle of the approach for mathematically determining the damping factor is to separately define and superimpose the dissipative contributions of the supporting structure(including the substructure)and the superstructure.Using the results of a measurement campaign on 15 existing steel railway bridges in the Austrian rail network,the presented mechanical models are calibrated,and by analysing the energy dissipation in the ballasted track,guiding principles for practical application are defined.This guideline is intended to establish an alternative to the currently valid specifications of EN 1991-2,enabling the damping factor of railway bridges to be assessed in a realistic range by mathematical calculation and thus without the need for extensive in situ measurements on the individual structure.In this way,the existing potential of the infrastructure with regard to the damping properties of bridges can be utilised.This contribution focuses on steel bridges,but the mathematical approach for determining the damping factor applies equally to other bridge types(concrete,composite,or filler beam).展开更多
Aberrant activation of Receptor Tyrosine Kinases(RTKs)is a well-established trigger of tumorigenesis,and the over-use of RTK inhibitors often leads to drug resistance and tumor recurrence.While current Drug-Target Int...Aberrant activation of Receptor Tyrosine Kinases(RTKs)is a well-established trigger of tumorigenesis,and the over-use of RTK inhibitors often leads to drug resistance and tumor recurrence.While current Drug-Target Interaction(DTI)prediction methods(including those based on heterogeneous information networks)have shown promise,they remain limited in their ability to fully capture the nature of DTIs and often lack interpretability.To overcome these limitations,this study introduces a novel hybrid optimization model termed MDBO-RF,which integrates a Modified Dung Beetle Optimizer(MDBO)with Random Forest(RF).The key innovation lies in the enhancement of the DBO algorithm through a quaternion-based learning mechanism and the Cauchy mutation strategy,specifically designed to overcome the slow convergence and susceptibility to local optima that plague traditional metaheuristic algorithms used for hyperparameter tuning.The model leverages commonly used molecular descriptors to enhance the prediction of Tyrosine Kinase(TK)inhibitory activity and enable efficient compound screening.Our results demonstrate that MDBO-RF achieves a 3.41%increase in prediction accuracy compared to the standard RF model and outperforms several other contemporary machine learning approaches.The model effectively streamlines the RTK inhibitor screening process by improving prediction accuracy in multi-target competitive binding scenarios and reducing false-positive screening due to off-target effects.This work underscores the value of hybrid optimization strategies in bioinformatics and provides a robust,interpretable tool for accelerating drug discovery.展开更多
Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effect...Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effects,and greater runoff from parks and other green spaces.Addressing these challenges requires prioritizing green infrastructure and other sustainable urban development strategies.This study introduces a novel Integrated Decision Support System that combines Pythagorean Fuzzy Sets with the Advanced Alternative Ranking Order Method allowing for Two-Step Normalization(AAROM-TN),enhanced by a dual weighting strategy.The weighting approach integrates the Criteria Importance Through Intercriteria Correlation(CRITIC)method with the Criteria Importance through Means and Standard Deviation(CIMAS)technique.The originality of the proposed framework lies in its ability to objectively quantify criteria importance using CRITIC,incorporate decision-makers’preferences through CIMAS,and capture the uncertainty and hesitation inherent in human judgment via Pythagorean Fuzzy Sets.A case study evaluating green infrastructure alternatives in metropolitan regions demonstrates the applicability and effectiveness of the framework.A sensitivity analysis is conducted to examine how variations in criteria weights affect the rankings and to evaluate the robustness of the results.Furthermore,a comparative analysis highlights the practical and financial implications of each alternative by assessing their respective strengths and weaknesses.展开更多
Plants constitute nearly 80%of the planet’s total biomass(Bar-On et al.,2018);however,this vital group is experiencing severe threats,and recent evaluations indicate that approximately 45%of the world's described...Plants constitute nearly 80%of the planet’s total biomass(Bar-On et al.,2018);however,this vital group is experiencing severe threats,and recent evaluations indicate that approximately 45%of the world's described plant species are at risk of extinction(Bachman et al.,2024).The number of plant extinctions has increased by 60%in the last 100 years(Di Marco et al.,2017).Over the past 250 years,571 plant species have gone extinct—more than twice the combined total of extinct birds,mammals,and amphibians(217 species)(Briggs,2019).展开更多
Multichannel signals have the characteristics of information diversity and information consistency.To better explore and utilize the affinity relationship within multichannel signals,a new graph learning technique bas...Multichannel signals have the characteristics of information diversity and information consistency.To better explore and utilize the affinity relationship within multichannel signals,a new graph learning technique based on low rank tensor approximation is proposed for multichannel monitoring signal processing and utilization.Firstly,the affinity relationship of multichannel signals can be acquired based on the clustering results of each channel signal.Wherein an affinity tensor is constructed to integrate the diverse and consistent information of the clustering information among multichannel signals.Secondly,a low-rank tensor optimization model is built and the joint affinity matrix is optimized with the assistance of the strong confidence affinity matrix.Through solving the optimization model,the fused affinity relationship graph of multichannel signals can be obtained.Finally,the multichannel fused clustering results can be acquired though the updated joint affinity relationship graph.The multichannel signal utilization examples in health state assessment with public datasets and microwave detection with actual echoes verify the advantages and effectiveness of the proposed method.展开更多
Slope units are divided according to the real topography and have clear geological characteristics,making them ideal units for evaluating the susceptibility to geological disasters.Based on the results of automaticall...Slope units are divided according to the real topography and have clear geological characteristics,making them ideal units for evaluating the susceptibility to geological disasters.Based on the results of automatically and manually corrected hydrological slope unit division,the Longhua District,Shenzhen City,Guangdong Province,was selected as the study area.A total of 15 influencing factors,namely Fluctuation,slope,slope aspect,curvature,topographic witness index(TWI),stream power index(SPI),topographic roughness index(TRI),annual average rainfall,distance to water system,engineering rock group,distance to fault,land use,normalized difference vegetation index(NDVI),nighttime light,and distance to road,were selected as evaluation indicators.The information volume model(IV)and random points were used to select non-geological disaster units,and then the random forest model(RF)was used to evaluate the susceptibility to geological disasters.The automatic slope unit and the hydrological slope unit were compared and analyzed in the random forest and information volume random forest models.The results show that the area under the curve(AUC)values of the automatic slope unit evaluation results are 0.931 for the IV-RF model and 0.716 for the RF model,which are 0.6%(IV-RF model)and 1.9%(RF model)higher than those for the hydrological slope unit.Based on a comparison of the evaluation methods based on the two types of slope units,the hydrological slope unit evaluation method based on manual correction is highly subjective,is complicated to operate,and has a low evaluation accuracy,whereas the evaluation method based on automatic slope unit division is efficient and accurate,is suitable for large-scale efficient geological disaster evaluation,and can better deal with the problem of geological disaster susceptibility evaluation.展开更多
Objective:To investigate the quantitative assessment efficacy of chest CT combined with serum Vanin-1 and SPP1 in determining the progression stage of chronic obstructive pulmonary disease(COPD).Methods:A total of 100...Objective:To investigate the quantitative assessment efficacy of chest CT combined with serum Vanin-1 and SPP1 in determining the progression stage of chronic obstructive pulmonary disease(COPD).Methods:A total of 100 COPD subjects from our hospital from January 2020 to December 2023 were included and randomly divided into a healthy control group and an experimental group(50 cases each).The healthy control group underwent slow vital capacity measurement using a spirometer,while the experimental group underwent high-resolution thin-slice CT scans and serum Vanin-1 and SPP1 concentration measurements.Pulmonary function parameters,symptom burden,biomarker concentrations,and imaging characteristics were compared between the two groups.Results:The FEV1/FVC ratio in the experimental group(58.3±7.2)was lower than that in the healthy control group(92.1±4.8);the total CAT score(22.4±3.5)was higher than that in the healthy control group(3.1±1.2);both Vanin-1(18.7±2.3μg/L)and SPP1(25.6±4.1μg/L)levels were higher than those in the healthy control group;LAA%-950(38.7±6.2%)and WA%(68.5±5.3%)were significantly higher than those in the healthy control group(all p<0.001).Conclusion:Chest CT combined with serum Vanin-1 and SPP1 can accurately quantify the pathological progression of COPD,providing a dual basis for clinical staging and individualized intervention.展开更多
The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unatt...The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unattainable.However,the black-box nature of these systems presents a significant barrier,hindering their operational adoption,regulatory approval,and full scientific validation.This paper provides a systematic review and synthesis of the emerging field of explainable artificial intelligence(XAI)as applied to geohazard science(GeoXAI),a domain that aims to resolve the long-standing trade-off between model performance and interpretability.A rigorous synthesis of 87 foundational studies is used to map the intellectual and methodological contours of this rapidly expanding field.The analysis reveals that current research efforts are concentrated predominantly on landslide and flood assessment.Methodologically,tree-based ensembles and deep learning models dominate the literature,with SHapley Additive exPlanations(SHAP)frequently adopted as the principal post-hoc explanation technique.More importantly,the review further documents how the role of XAI has shifted:rather than being used solely as a tool for interpreting models after training,it is increasingly integrated into the modeling cycle itself.Recent applications include its use in feature selection,adaptive sampling strategies,and model evaluation.The evidence also shows that GeoXAI extends beyond producing feature rankings.It reveals nonlinear thresholds and interaction effects that generate deeper mechanistic insights into hazard processes and mechanisms.Nevertheless,several key challenges remain unresolved within the field.These persistent issues are especially pronounced when considering the crucial necessity for interpretation stability,the demanding scholarly task of reliably distinguishing correlation from causation,and the development of appropriate methods for the treatment of complex spatio-temporal dynamics.展开更多
文摘39 soil samples surrounding a lead-zinc mining area in Guangxi were collected,and the contents of Pb,Hg,Cd,Cr,As,Cu,Zn,and Ni were determined to investigate the pollution characteristics and sources of heavy metals.ArcGIS inverse distance weight difference method was used to analyze the characteristics of pollution distribution,and single-factor pollution index,Nemerow comprehensive pollution index,ground accumulation index,and potential ecological risk index were selected to evaluate the characteristics of heavy metal pollution.Based on correlation analysis,the absolute principal component-multiple linear regression(APCS-MLR)and positive definite matrix factorization(PMF)models were used to analyze the sources of soil heavy metals.The results showed that the average concentrations of all eight heavy metals exceeded both national and Guangxi soil background values.Hg,Cd,and Zn exhibited high variation(greater than 0.5),indicating significant external disturbances,and their spatial distribution was closely related to mining activity locations.The single-factor pollution index evaluation indicated varying degrees of pollution risk for Cd,Zn,and As,with Cd and Zn being the most severe pollutants,as 69.23%and 30.77%of the samples fell into the moderate pollution or higher category.The geoaccumulation index analysis ranked the mean pollution levels of the eight elements as follows:Zn>Cd>Ni>Pb>Cu>Cr>Hg>As,with Cd and Zn showing the most severe contamination,and 51.28%of the samples exhibiting moderate or higher pollution levels.The Nemerow comprehensive pollution index evaluation showed that 74.35%of soil samples were classified as moderate to heavy pollution.The potential ecological risk index assessment indicated significant ecological risks posed by Cd and Zn,with 82.05%and 5.12%of the samples classified as causing strong to extreme ecological risks,respectively.The source apportionment analysis revealed minor differences between the two models.The APCS-MLR model identified three pollution sources and their contribution rates:anthropogenic mining sources(31.13%),parent material sources(40.38%),and unidentified sources(28.49%).The PMF model identified three pollution sources with contribution rates of anthropogenic mining sources(26.10%),parent material sources(46.96%),and a combined traffic and agricultural source(26.61%).Pb,Hg,Cd,and Zn mainly originated from mining activities;Cr,As,and Ni were primarily derived from the parent material,while Cu was predominantly attributed to traffic and agricultural sources.These findings provide a scientific basis for the prevention and control of heavy metal pollution in mining areas.
文摘Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.
文摘Analysis Method of ^(131)I Activity in Carbon Cartridge and Internal Dose Assessment for Nuclear Medicine Workers.Shuo Wang1,Fei Tuo1,Jian-feng Zhang1,Xiao-liang Li1,Bao-lu Yang1,Qiang Zhou1,Ze-shu Li1,Shu-ying Kong1,and Wei-hao Qin1(1.National Institute for Radiological Protection,Chinese Center for Disease Control and Prevention,Beijing,100088,China.)
文摘Analysis of the environmental and economic performance of fishing vessels has received limited attention compared with other ship types despite their notable contribution to global greenhouse gas(GHG)emissions.This study evaluates the carbon footprint(CF)and economic viability of a liquefied natural gas(LNG)-fueled fishing vessel,using real engine operation simulations to provide precise and dynamic evaluation of fuel consumption and GHG emissions.Operational profiles are obtained through the utilization of onboard monitoring systems,whereas engine performance is simulated using the 1D/0D AVL Boost^(TM)model.Life cycle assessment(LCA)is conducted to quantify the environmental impact,whereas life cycle cost assessment(LCCA)is performed to analyze the profitability of LNG as an alternative fuel.The potential impact of the future fuel price uncertainties is addressed using Monte Carlo simulations.The LCA findings indicate that LNG has the potential to reduce the CF of the vessel by 14%to 16%,in comparison to a diesel power system configuration that serves as the baseline scenario.The LCCA results further indicate that the total cost of an LNG-powered ship is lower by 9.5%-13.8%,depending on the share of LNG and pilot fuels.This finding highlights the potential of LNG to produce considerable environmental benefits while addressing economic challenges under diverse operational and fuel price conditions.
文摘Objective:To assess prenatal Bisphenol A(BPA)exposure levels and explore their preliminary associations with maternal and fetal characteristics in a population from Northeastern Yunnan.Methods:A cross-sectional analysis was performed using data and urine samples from 70 pregnant women in their third trimester recruited at Qujing Central Hospital.Urinary BPA was measured by HPLC-MS/MS.Participants were stratified into high and low BPA exposure groups based on the median concentration.Results:BPA was detected in all samples(100%)with a median concentration of 2.41μg/L(IQR:0.68-4.96).The high BPA exposure group(≥2.41μg/L)had a significantly higher proportion of gestational diabetes mellitus(GDM)(42.9%vs.17.1%,p=0.021)and a lower median fetal birth weight(3250 g vs.3450 g,p=0.048)compared to the low exposure group.Conclusion:This pilot study reveals ubiquitous BPA exposure in pregnant women from Northeastern Yunnan.The observed preliminary associations with GDM and reduced fetal birth weight warrant further investigation in larger,longitudinal studies.
基金Research on Problems and Countermeasures in Building the Capacity of the Grassroots International Chambers of Commerce in the Context of High-Quality Development (W2024H03841)a key research project of the China Council for the Promotion of International Trade in 2025。
文摘Arbitration is a key non-litigation commercial mechanism for the resolution of disputes, and the quality and credibility of its awards depend largely on the competency of the arbitrators. However, the selection and evaluation systems for arbitrators in China have long faced challenges such as the vague criteria for competency and an unclear professionalization path for arbitrators. To address these issues, this study is grounded in the context of actual Chinese arbitration practice and based on the competency iceberg model. Through a methodological approach encompassing literature reviews, behavioral event interviews, expert revisions, and questionnaire surveys, a Chinese Arbitrator Competency Scale was developed and validated in this study. Examination of the findings indicated that the scale needed to consist of five dimensions—communication and coordination, cognitive skills, ethical conduct, work motivation, and personality traits—and possess a total of 28 specific indicators. Confirmatory analysis of the factors demonstrates a good fit for the five-dimensional model, with each of the dimensions exhibiting high reliability and validity. This scale is innovative in integrating the competency elements with Chinese characteristics, such as commercial acumen, crosscultural mediation skills, and adaptability to the local rule of law. This research not only enriches the competency theory in regard to the field of human resource management but also provides a scientific framework of standards and measurement tools for the selection, training, and evaluation of arbitrators. It thus has significant practical value for enhancing the professionalism and international competitiveness of China's arbitration system.
基金supported by the National Natural Science Foundation of China(42361144880)the Science and Technology Program of Xizang Autonomous Region,China(XZ202402ZD0001)the Qinghai Province Basic Research Program Project,China(2024-ZJ-904).
文摘Debris flow events are frequent in Tajikistan,yet comprehensive investigations at the regional scale are limited.This study integrates remote sensing,Geographic Information System,and machine learning techniques to evaluate debris flow susceptibility and associated hazards across Tajikistan.A dataset comprising 405 documented debris flow points and 14 influencing factors,encompassing geological,climatic-hydrological,and anthropogenic variables,was established.Three machine learning algorithms—Random Forest,Support Vector Machine(SVM),and Multi-layer Perceptron—were applied to generate susceptibility maps and delineate debris flow risk zones.The results indicate that the areas of higher and high susceptibility accounted for 20.43%and 4.41%of the national area,respectively,and were predominantly concentrated along the Zeravshan and Vakhsh river basins.Among the evaluated models,SVM model demonstrated the highest predictive performance.Beyond conventional topographic and environmental controls,drought conditions were identified as a critical factor influencing debris flow occurrence within the arid and semi-arid mountainous regions of Tajikistan.These findings provide a scientific basis for regional debris flow risk management and disaster mitigation planning,and offer practical guidance for selecting conditioning factors in machine-learning-based susceptibility assessments in other dry mountainous environments.
文摘This report presents a forensic evaluation of a case involving blindness(visual acuity grade 5)following a bee/wasp sting to the left eye.Through systematic analysis of the patient’s multiple hospital admissions,postoperative follow-up data,and a review of the pathological mechanisms of ocular injury caused by bee venom,this study comprehensively assesses the injury characteristics,treatment course,and visual outcomes.Bee venom induces severe complications such as corneal damage,uveitis,cataract,and secondary glaucoma through multiple mechanisms including direct cytotoxicity,immune-inflammatory responses,and enzymatic hydrolysis.Despite interventions including anterior chamber irrigation,phacoemulsification with intraocular lens implantation,and antiglaucoma surgery,the affected eye ultimately lost light perception.Forensic examination confirmed the absence of light perception in the left eye and abnormal visual pathway function,consistent with clinical observations.According to the relevant Chinese disability assessment standard(JR/T 0083-2013,Article 4.2.2),the injury was classified as grade 7 disability.This study provides an in-depth discussion of the mechanisms and key forensic identification points in bee-sting-induced blindness,offering a scientific reference for similar forensic clinical cases.
基金supported by the Northeast Geological Science and Technology Innovation Center of China Geological Survey(Grant NO.QCJJ2022-43)the Natural Resources Comprehensive Survey Project(Grant Nos.DD20230470,DD20230508)the National Groundwater Monitoring Network Operation and Maintenance Program(Grant No.DD20251300109).
文摘Excessive levels of Fluoride(F−)and Cadmium(Cd)in drinking groundwater may pose health risks.This study assessed the health risks associated with F−and Cd contamination in rural drinking groundwater sources in Wutai County,Shanxi Province,China,to support population health protection,water resource management,and environmental decision-making.Groundwater samples were collected and analyzed,and a Human Health Risk Model(HHRA)was applied to evaluate groundwater quality.The results showed that both contents of F−and Cd in groundwater exceeded the Class III limits of China's national groundwater quality standard(GB/T 14848—2024).Fluoride levels met the Class V threshold,with enrichment area mainly located in the east part of the study area.Cadmium levels reached Class IV,with elevated concentrations primarily observed in the western and northwestern regions.Correlation analysis revealed that F−showed weak or no correlation with other measured substances,indicating independent sources.Health risk assessment results indicated that F−poses potential health risks to rural residents,while cadmium,due to its relatively low concentrations,does not currently present a significant health risk.Among different demographic groups,the health risk levels of F−exposure followed the order:Infants>children>adult females>adult males.The findings highlight that fluoride is the primary contributor to health risks associated with groundwater consumption in the study area.Strengthened monitoring and prevention of F−contamination are urgently needed.This research provides a scientific basis for the prevention and control of fluoride pollution in groundwater and offers practical guidance for safeguarding drinking water safety in rural China.
文摘Background and Objectives:The perception of sound in the vertical plane supports spatial hearing by enabling listeners to detect sources located above and below.Sounds originating from both the front and back elevations along the mid-sagittal plane further contribute to a three-dimensional auditory experience.This study aimed to characterize the variability in vertical sound localization abilities among normal-hearing(NH)individuals using spatialized audio.Materials and Methods:Fifty-one NH participants(aged 18 to 35 years)completed three vertical localization tasks under headphones as part of a single-group,within-subject experimental study.These tasks included two-plane identification:(1)top-down localization,(2)front-back localization,and one discrimination task in the front plane.Hierarchical Cluster Analysis(HCA)was employed to identify distinct patterns in spatial localization profiles specific to the vertical-median plane.Fisher's Discriminant Function Analysis(FDA)was used to validate the accuracy of HCA and estimate classification error.Results:HCA revealed three distinct listener clusters:(1)cluster 1 with good performance across all three tasks,(2)cluster 2 with selective impairment in top-bottom identification,and(3)cluster 3 with selective deficits in front-back identification.FDA validated group membership of the clusters identified by the HCA,with a prediction accuracy of 98%.Conclusions:Individuals with clinically NH exhibited three distinct vertical localization profiles:uniform performers,those impaired in top-bottom identification,and those impaired in front-back identification.These profiles may be linked to the interplay between acoustic and non-acoustic perceptual factors.
文摘Nonlinear static procedures are widely adopted in structural engineering practice for seismic performance assessment due to their simplicity and computational efficiency.However,their reliability depends heavily on how the nonlinear behaviour of structural components is represented.The recent earthquakes in Albania(2019)and Türkiye(2023)have underscored the need for accurate assessment techniques,particularly for older reinforced concrete buildings with poor detailing.This study quantifies the discrepancies between default and user-defined component modelling in pushover analysis of pre-modern reinforced concrete structures,analysing two representative low-and mid-rise reinforced concrete frame buildings.The lumped plasticity approach incorporates moment-rotation relationships derived from actual member properties and reinforcement configurations,while the distributed plasticity approach uses software-generated default properties based on modern codes.Results show that the distributed plasticity models systematically overestimate both the strength and the deformation capacity by up to 35%compared to lumped plasticity models,especially in buildings with poor detailing and low concrete strength.These findings demonstrate that default software procedures,widely used in practice but not validated for pre-modern structures,produce dangerously unconservative seismic performance estimates.The study provides quantitative evidence of the critical need for tailored modelling strategies that reflect the actual conditions of the existing building stock.
基金funded by the Austrian Federal Railways(ÖBB Infrastruktur AG)in the context of the research project‘VeMoDiss’(acronym)。
文摘To ensure the compatibility between rolling stock and infrastructure when dynamically assessing railway bridges under high-speed traffic,the damping properties considered in the calculation model significantly influence the predicted acceleration amplitude at resonance.However,due to the normative specifications of EN 1991-2,which are considered to be overly conservative,damping factors that are far below the actual damping have to be used when predicting vibrations of railway bridges,which means that accelerations at resonance tend to be overestimated to an uneconomical extent.Comparisons between damping factors prescribed by the standard and those identified based on in situ structure measurements always reveal a large discrepancy between reality and regulation.Given this background,this contribution presents a novel approach for defining the damping factor of railway bridges with ballasted tracks,where the damping factor for bridges is mathematically determined based on three different two-dimensional mechanical models.The basic principle of the approach for mathematically determining the damping factor is to separately define and superimpose the dissipative contributions of the supporting structure(including the substructure)and the superstructure.Using the results of a measurement campaign on 15 existing steel railway bridges in the Austrian rail network,the presented mechanical models are calibrated,and by analysing the energy dissipation in the ballasted track,guiding principles for practical application are defined.This guideline is intended to establish an alternative to the currently valid specifications of EN 1991-2,enabling the damping factor of railway bridges to be assessed in a realistic range by mathematical calculation and thus without the need for extensive in situ measurements on the individual structure.In this way,the existing potential of the infrastructure with regard to the damping properties of bridges can be utilised.This contribution focuses on steel bridges,but the mathematical approach for determining the damping factor applies equally to other bridge types(concrete,composite,or filler beam).
基金National Key Research and Development Program of China(No.2022YFD1802104).
文摘Aberrant activation of Receptor Tyrosine Kinases(RTKs)is a well-established trigger of tumorigenesis,and the over-use of RTK inhibitors often leads to drug resistance and tumor recurrence.While current Drug-Target Interaction(DTI)prediction methods(including those based on heterogeneous information networks)have shown promise,they remain limited in their ability to fully capture the nature of DTIs and often lack interpretability.To overcome these limitations,this study introduces a novel hybrid optimization model termed MDBO-RF,which integrates a Modified Dung Beetle Optimizer(MDBO)with Random Forest(RF).The key innovation lies in the enhancement of the DBO algorithm through a quaternion-based learning mechanism and the Cauchy mutation strategy,specifically designed to overcome the slow convergence and susceptibility to local optima that plague traditional metaheuristic algorithms used for hyperparameter tuning.The model leverages commonly used molecular descriptors to enhance the prediction of Tyrosine Kinase(TK)inhibitory activity and enable efficient compound screening.Our results demonstrate that MDBO-RF achieves a 3.41%increase in prediction accuracy compared to the standard RF model and outperforms several other contemporary machine learning approaches.The model effectively streamlines the RTK inhibitor screening process by improving prediction accuracy in multi-target competitive binding scenarios and reducing false-positive screening due to off-target effects.This work underscores the value of hybrid optimization strategies in bioinformatics and provides a robust,interpretable tool for accelerating drug discovery.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R259)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.Ashit Kumar Dutta would like to thank AlMaarefa University for supporting this research under project number MHIRSP2025017.
文摘Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effects,and greater runoff from parks and other green spaces.Addressing these challenges requires prioritizing green infrastructure and other sustainable urban development strategies.This study introduces a novel Integrated Decision Support System that combines Pythagorean Fuzzy Sets with the Advanced Alternative Ranking Order Method allowing for Two-Step Normalization(AAROM-TN),enhanced by a dual weighting strategy.The weighting approach integrates the Criteria Importance Through Intercriteria Correlation(CRITIC)method with the Criteria Importance through Means and Standard Deviation(CIMAS)technique.The originality of the proposed framework lies in its ability to objectively quantify criteria importance using CRITIC,incorporate decision-makers’preferences through CIMAS,and capture the uncertainty and hesitation inherent in human judgment via Pythagorean Fuzzy Sets.A case study evaluating green infrastructure alternatives in metropolitan regions demonstrates the applicability and effectiveness of the framework.A sensitivity analysis is conducted to examine how variations in criteria weights affect the rankings and to evaluate the robustness of the results.Furthermore,a comparative analysis highlights the practical and financial implications of each alternative by assessing their respective strengths and weaknesses.
基金support of the ORG.one project of Oxford Nanopore Technologies(ONT),the Rufford Grants(45249-1)the Idea Wild Grants(Project ID-KJOSINDI0125-00)the Mohamed Bin Zyed Species Conservation(MBZ)(GEF Grant no-240535253)Funds in our efforts to conserve threatened trees in the Western Ghats Biodiversity Hotspot Forest regions.
文摘Plants constitute nearly 80%of the planet’s total biomass(Bar-On et al.,2018);however,this vital group is experiencing severe threats,and recent evaluations indicate that approximately 45%of the world's described plant species are at risk of extinction(Bachman et al.,2024).The number of plant extinctions has increased by 60%in the last 100 years(Di Marco et al.,2017).Over the past 250 years,571 plant species have gone extinct—more than twice the combined total of extinct birds,mammals,and amphibians(217 species)(Briggs,2019).
基金supported by Shanghai Aerospace Science and Technology Innovation Foundation(SAST2023-075)。
文摘Multichannel signals have the characteristics of information diversity and information consistency.To better explore and utilize the affinity relationship within multichannel signals,a new graph learning technique based on low rank tensor approximation is proposed for multichannel monitoring signal processing and utilization.Firstly,the affinity relationship of multichannel signals can be acquired based on the clustering results of each channel signal.Wherein an affinity tensor is constructed to integrate the diverse and consistent information of the clustering information among multichannel signals.Secondly,a low-rank tensor optimization model is built and the joint affinity matrix is optimized with the assistance of the strong confidence affinity matrix.Through solving the optimization model,the fused affinity relationship graph of multichannel signals can be obtained.Finally,the multichannel fused clustering results can be acquired though the updated joint affinity relationship graph.The multichannel signal utilization examples in health state assessment with public datasets and microwave detection with actual echoes verify the advantages and effectiveness of the proposed method.
文摘Slope units are divided according to the real topography and have clear geological characteristics,making them ideal units for evaluating the susceptibility to geological disasters.Based on the results of automatically and manually corrected hydrological slope unit division,the Longhua District,Shenzhen City,Guangdong Province,was selected as the study area.A total of 15 influencing factors,namely Fluctuation,slope,slope aspect,curvature,topographic witness index(TWI),stream power index(SPI),topographic roughness index(TRI),annual average rainfall,distance to water system,engineering rock group,distance to fault,land use,normalized difference vegetation index(NDVI),nighttime light,and distance to road,were selected as evaluation indicators.The information volume model(IV)and random points were used to select non-geological disaster units,and then the random forest model(RF)was used to evaluate the susceptibility to geological disasters.The automatic slope unit and the hydrological slope unit were compared and analyzed in the random forest and information volume random forest models.The results show that the area under the curve(AUC)values of the automatic slope unit evaluation results are 0.931 for the IV-RF model and 0.716 for the RF model,which are 0.6%(IV-RF model)and 1.9%(RF model)higher than those for the hydrological slope unit.Based on a comparison of the evaluation methods based on the two types of slope units,the hydrological slope unit evaluation method based on manual correction is highly subjective,is complicated to operate,and has a low evaluation accuracy,whereas the evaluation method based on automatic slope unit division is efficient and accurate,is suitable for large-scale efficient geological disaster evaluation,and can better deal with the problem of geological disaster susceptibility evaluation.
基金Baoding Science and Technology Plan Project(Project No.:2341ZF214)。
文摘Objective:To investigate the quantitative assessment efficacy of chest CT combined with serum Vanin-1 and SPP1 in determining the progression stage of chronic obstructive pulmonary disease(COPD).Methods:A total of 100 COPD subjects from our hospital from January 2020 to December 2023 were included and randomly divided into a healthy control group and an experimental group(50 cases each).The healthy control group underwent slow vital capacity measurement using a spirometer,while the experimental group underwent high-resolution thin-slice CT scans and serum Vanin-1 and SPP1 concentration measurements.Pulmonary function parameters,symptom burden,biomarker concentrations,and imaging characteristics were compared between the two groups.Results:The FEV1/FVC ratio in the experimental group(58.3±7.2)was lower than that in the healthy control group(92.1±4.8);the total CAT score(22.4±3.5)was higher than that in the healthy control group(3.1±1.2);both Vanin-1(18.7±2.3μg/L)and SPP1(25.6±4.1μg/L)levels were higher than those in the healthy control group;LAA%-950(38.7±6.2%)and WA%(68.5±5.3%)were significantly higher than those in the healthy control group(all p<0.001).Conclusion:Chest CT combined with serum Vanin-1 and SPP1 can accurately quantify the pathological progression of COPD,providing a dual basis for clinical staging and individualized intervention.
文摘The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unattainable.However,the black-box nature of these systems presents a significant barrier,hindering their operational adoption,regulatory approval,and full scientific validation.This paper provides a systematic review and synthesis of the emerging field of explainable artificial intelligence(XAI)as applied to geohazard science(GeoXAI),a domain that aims to resolve the long-standing trade-off between model performance and interpretability.A rigorous synthesis of 87 foundational studies is used to map the intellectual and methodological contours of this rapidly expanding field.The analysis reveals that current research efforts are concentrated predominantly on landslide and flood assessment.Methodologically,tree-based ensembles and deep learning models dominate the literature,with SHapley Additive exPlanations(SHAP)frequently adopted as the principal post-hoc explanation technique.More importantly,the review further documents how the role of XAI has shifted:rather than being used solely as a tool for interpreting models after training,it is increasingly integrated into the modeling cycle itself.Recent applications include its use in feature selection,adaptive sampling strategies,and model evaluation.The evidence also shows that GeoXAI extends beyond producing feature rankings.It reveals nonlinear thresholds and interaction effects that generate deeper mechanistic insights into hazard processes and mechanisms.Nevertheless,several key challenges remain unresolved within the field.These persistent issues are especially pronounced when considering the crucial necessity for interpretation stability,the demanding scholarly task of reliably distinguishing correlation from causation,and the development of appropriate methods for the treatment of complex spatio-temporal dynamics.
