环境科学最新文献

{"title":"[Analysis of Influencing Factors and Sources of Soil Heavy Metals Based on Classification Regression Tree and PMF Model].","authors":"Yun-Yi Zhang, Yu-Jie Luo, Yu-Lian Jiang, Fei Yu, Ya-Wei Yu, Jia-Bin Wang, Ke-Qiang Zhong","doi":"10.13227/j.hjkx.202409306","DOIUrl":"https://doi.org/10.13227/j.hjkx.202409306","url":null,"abstract":"<p><p>To explore the sources and influencing factors of heavy metals in soil at the township scale， 280 surface soil samples were collected from a town in southeastern Chongqing， which served as the research area， and indicators such as As， Cd， Cr， Cu， Hg， Ni， Pb， Zn， pH， and C_org were analyzed and tested. The regional soil heavy metals were evaluated using the land accumulation index method， and the sources of eight heavy metals were analyzed using correlation analysis， cold and hot spot analysis， the classification regression tree model， and the positive matrix factorization （PMF） model. The results showed that the average contents of eight heavy metals， i.e.， As， Cd， Cr， Cu， Hg， Ni， Pb， and Zn， in the study area were higher than the soil background values in Chongqing. The main soil risk factors were Cd， As， and Hg. Distance from residential areas was the most critical factor affecting soil Hg， distance from highways was the most critical factor affecting soil Cd， and distance from industrial and mining enterprises was the most critical factor affecting As and Pb. There are four main sources of heavy metals in the research area， namely， agricultural production sources， traffic pollution and natural parent material composite sources， mining activity sources， and natural parent material sources， which account for 16%， 23%， 31%， and 30% of the heavy metals， respectively. Hg is mainly affected by agricultural production sources， Cd is mainly affected by traffic pollution and natural parent material composite sources， As and Pb are mainly affected by mining activity sources， and Cu， Ni， Zn， and Cr are mainly affected by natural parent material sources.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"6056-6065"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Assessing the Economic Value of Carbon Storage and Land Use Changes in Wuhan Based on the FLUS and InVEST Model].","authors":"Lu Li, Bin Zhang","doi":"10.13227/j.hjkx.202409345","DOIUrl":"https://doi.org/10.13227/j.hjkx.202409345","url":null,"abstract":"<p><p>Land use/land cover change is a key factor affecting the carbon storage of terrestrial ecosystems， and understanding the impact of land use change on ecosystem carbon storage and its economic value has great significance to the realization of the \"dual carbon\" goal. Using the FLUS and InVEST models， we analyzed the spatial and temporal characteristics of land use and carbon storage in Wuhan from 2000 to 2020 and further simulated the impacts of land use changes on carbon storage under different scenarios （natural development scenario， economic priority development scenario， and comprehensive development scenario） in 2035. We also estimated the economic value of carbon storage in each period by combining this value with the compound present value formulas. The study produced the following results： ① Cultivated land and water area are persistently the main land use types in Wuhan， and their proportion reached 73.208% in 2020. Construction land increased rapidly during the study period due to the transfer of cultivated， water， and forest land. ② During the period from 2000 to 2020， the total carbon storage showed a continuous declining trend， with a cumulative loss of 3.461 Tg. The spatial distribution pattern remained relatively stable， showing the characteristic of \"higher in the north and south， lower in the middle.\" During this period， changes in cultivated land and construction land were the main factors contributing to the decrease in carbon storage in Wuhan. ③ The spatial pattern of carbon storage under the different scenarios in 2035 is not much different from the pattern in 2020， but there are differences in the spatial changes of carbon storage under each scenario. Affected by the change of land use types， carbon storage decreases under all three scenarios， but the comprehensive development scenario suppresses the loss of carbon storage most significantly. ④ The economic value of carbon storage in Wuhan increased by 3.056 4 billion yuan from 2000 to 2020. The economic value of carbon storage in farmland increased by 1.511 8 billion yuan through the 20 years and was the main driving force for the increase in the economic value of carbon storage in Wuhan. From 2020 to 2035， the economic value of carbon storage varies under different scenarios. The highest economic value of carbon storage， which occurs under the comprehensive development scenario， is 11.169 8 billion yuan. The results of the study provide a scientific basis for the region to enhance its carbon sequestration capacity， optimize the allocation of land resources， and formulate policies for green sustainable development.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5777-5787"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Current Pollution Status， Health Risk Assessment and Source Apportionment of Heavy Metals in Vegetable Soil in Tongliang District， Chongqin].","authors":"Xu Luo, Lin Yang, Xiao-Ge Shen, Xue-Pin Zhan, Jian Fu, Xiao-Zhong Wang, Ran Xiao","doi":"10.13227/j.hjkx.202407282","DOIUrl":"https://doi.org/10.13227/j.hjkx.202407282","url":null,"abstract":"<p><p>Understanding the status and sources of vegetable soil heavy metals pollution has great significance for soil protection and vegetable production safety. In this study， the contents of five heavy metals， Cr， Cu， Zn， As， and Cd， were collected and determined in 151 surface vegetable soil samples from the typical vegetable soil of Tongliang District. The heavy metals pollution degree was evaluated by means of the geoaccumulation index， enrichment factor， and potential ecological risk index. The carcinogenic and non-carcinogenic risks of the heavy metals were evaluated using the health risk model. The sources of the heavy metals in the topsoil were analyzed by correlation analysis， principal component analysis （PCA）， cluster analysis， absolute principal component score-multiple linear regression （APCS-MLR）， and other qualitative and quantitative methods. The results showed that the average contents of Cu， Zn， and As in the vegetable garden soils of Tongliang District exceed background values， being 1.78， 1.71， and 3.32 times higher， respectively. The contents of Cu， Zn， As， and Cd in 15.89%， 11.26%， 4.64%， and 3.97% of the soil sites exceeded the risk screening values， respectively. Enrichment factor analysis classified As as light pollution， with 62.62% of the soil samples showing light pollution and 20.56% showing moderate pollution levels. The geoaccumulation index analysis revealed that As is at a moderate pollution level， while Cu and Zn fall into the light-to-moderate pollution category. The potential ecological risk assessment suggested that the study area primarily faces moderate ecological hazards， with As contributing 51.66% of the ecological risk. Source apportionment analysis revealed that the average contributions of agricultural-natural sources， atmospheric deposition， and unknown sources are 66.75%， 22.06%， and 11.19%， respectively. The health risk assessment further revealed that the non-carcinogenic risk quotient for As exceeds 1， indicating potential non-carcinogenic risks for both adults and children. Thus， there is an urgent need for effective management and remediation strategies to address As contamination and ensure the safety of vegetable production in the region.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"6037-6045"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Ecosystem Services and Trade-offs and Synergies in Shandong Province Under the Background of LUCC].","authors":"Jia-Qi Zhai, Yong-Zhong Luo, Xin Luo, Han Zhang","doi":"10.13227/j.hjkx.202407082","DOIUrl":"https://doi.org/10.13227/j.hjkx.202407082","url":null,"abstract":"<p><p>Shandong Province is an important part of the Bohai Economic District and the Yellow River Economic Belt， and it is also the only entrance to the sea in the lower reaches of the Yellow River， which is of great significance for ecological protection and flood mitigation. However， in recent years， due to the influence of human activities， the contradiction between ecological protection and socioeconomic development has become increasingly obvious. Taking Shandong Province as the study area， based on the spatial and temporal changes of land use from 2000 to 2020， the spatial and temporal changes of four ecosystem services， namely， water yield， soil retention， carbon storage， and habitat quality， from 2000 to 2020 were explored to assess the trade-off and synergistic relationships among ecosystem services by applying global correlation analysis and local spatial autocorrelation analysis. The study produced several interesting results： ① The reduction of cultivated land area in Shandong Province was most obvious between 2000 and 2020， when it decreased by 1.3033×10⁴ km²， of which 86.1% was transferred to construction land. Land use change was mainly concentrated in the northern coastal areas of Weifang， Dongying， and Binzhou. ② Various ecosystem services in Shandong Province showed a spatial distribution pattern of high in the central and southeastern areas and low in the lower Yellow River Basin. Water production and soil retention showed an increasing trend， with increases of 14.06×10⁸ m³ and 1.06×10⁷ t， while carbon storage and habitat quality showed an overall decreasing trend， with decreases of 7.81×10⁷ t and 0.011， respectively. ③ There were different degrees of correlation between ecosystem services. Among the ecosystem services that correlated， all relationships were synergistic， except for carbon storage-water yield and habitat quality-water yield， which were trade-offs. ④ The global trade-offs and synergistic relationships between ecosystem services and the local trade-offs and synergistic relationships were basically the same， but some ecosystem services had regional variability at global and local scales， having different effects at different scales. This study provides a reference for the scientific management of the lower Yellow River ecosystem and the high-quality development of Shandong Province.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5907-5918"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Ecological Vulnerability Evaluation and Its Driving Mechanism of Mineral Resource-based Region].","authors":"Nan Guo, Yu Nong, Xiao-Hui Yang, An-Min Li, Fu-Qiang Li","doi":"10.13227/j.hjkx.202407315","DOIUrl":"https://doi.org/10.13227/j.hjkx.202407315","url":null,"abstract":"<p><p>Dingxi has abundant mineral resources and complex landforms， and the contradiction between ecological environment and economic development is prominent. Thus， studying the ecological vulnerability and driving mechanism of Dingxi City has great significance for the protection and management of the regional ecological environment and the classification and evaluation methods of mine restoration. Based on a combination of four screening methods and four machine learning prediction models， 19 basic environmental factors were selected from natural and social environmental factors， and the spatial distribution characteristics of ecological vulnerability in Dingxi City were compared and analyzed by using training and testing prediction models. Based on the principle of screening method， correlation， principal component analysis， regression analysis， and importance analysis of the selected basic environmental factors were carried out to reveal the driving mechanism. The results follow： ① The prediction accuracy of the prediction model based on the screening method was entirely above 80%， which meets the accuracy requirements of ecological vulnerability assessment. Therefore， the combined model can be used as a new method for mine ecological environment assessment and ecological vulnerability assessment. ② The ecologically fragile area of Dingxi City showed a spatial distribution pattern of \"high in the northeast， low in the middle， and high in the southwest.\" The ecological environment in the central， western， and southeastern regions is better than the environment in the northeast and southwest regions. ③ The annual average precipitation， road density， and river network density in the study area， which are the results of the combined effects of climate， human activities， and complex topography， are the main driving factors of ecological vulnerability. ④ The historical mining area is indeed a serious ecologically fragile area， and other types of mining areas are also closely related to the ecological vulnerability in the region. Therefore， the timely treatment and restoration of mining areas is a key link in the protection of the ecological environment.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5895-5906"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Impact Effect and Action Mechanism of New Quality Productivity on the Pollution and Carbon Emission Reduction].","authors":"Ying Gao","doi":"10.13227/j.hjkx.202410169","DOIUrl":"https://doi.org/10.13227/j.hjkx.202410169","url":null,"abstract":"<p><p>Exploring the impacts of new quality productivity on pollution and carbon emission reduction has important theoretical guiding significance for accelerating China's green and low-carbon transformation. Using panel data of 30 provinces in China from 2010 to 2022 as a research sample and based on the calculation of new quality productivity， environmental pollution emissions， and carbon emissions in each province through the years， the concrete impacts of new quality productivity on pollution and carbon emission reduction and their action mechanism， regional heterogeneity， and spatial spillover effect were investigated. Relevant policy recommendations pertaining to new quality productivity empowering pollution and carbon emission reductions were proposed. The study produced several notable results： ① From 2010 to 2022， China's new quality productivity showed a steady growth trend. The index of new labor materials grew the fastest， followed by the index of new workers； the index of new labor objects grew the slowest. The development difference of new quality productivity in different regions showed an increasing trend through time， and the inter-regional difference was the main source of the spatial difference of new quality productivity. ② From 2010 to 2022， environmental pollution emissions and carbon emissions in the country and the four regions showed a clear increasing trend， while the total carbon emission and carbon emission intensity showed a scissor-like difference pattern of change. ③ New quality productivity played a significant role in promoting the reduction of pollution and carbon emissions through the transformation and upgrading of industrial structure and the optimal allocation of resources. It played a positive role in reducing emissions of pollution and carbon in the eastern and western regions， but in the central and northeast regions， the impact was not satisfactory. The diffusion and interaction of new quality productivity across different regions had significant and positive spatial spillover effects， thereby promoting pollution and carbon emission reductions of the whole economy effectively.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5543-5553"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Digital Economy and Carbon Productivity： Evidence from the Logistics Industry].","authors":"Hong-Yu Gong, Chun Ni, Yu-Liang Cao","doi":"10.13227/j.hjkx.202406049","DOIUrl":"https://doi.org/10.13227/j.hjkx.202406049","url":null,"abstract":"<p><p>Low-carbon transformation is an inevitable requirement for China to transform its economic development mode in the new stage of development. As a new driving force for high-quality economic development in China， the digital economy brings new opportunities for the realization of the dual-carbon goal. Using panel data of 30 provinces， municipalities， and autonomous regions of China from 2011-2020 and input-output model logistics carbon productivity， this paper discusses the direct effect of the digital economy on logistics carbon productivity， the action path， the space correlation and space spillover effect， and the influence of the digital economy on the logistics carbon productivity of regional heterogeneity. The results show that China's digital economy had a significant \"U-shaped\" nonlinear influence on the logistics industry during the investigation period. The results also indicate that the digital economy affects logistics carbon productivity through labor productivity， industrial structure， and energy transition， including labor efficiency and energy transition； that it has a significant spatial spillover effect on the logistics carbon productivity； and that the influence of the digital economy on logistics carbon productivity has regional heterogeneity.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5465-5474"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Effects of Tillage and Straw Return on the Distribution of Soil Aggregates and Integration of Organic Carbon in Farmland Soil].","authors":"Tian-Zi Li, Yan-Jun Zhang, Shui-Na Dang, Jing Li","doi":"10.13227/j.hjkx.202407094","DOIUrl":"https://doi.org/10.13227/j.hjkx.202407094","url":null,"abstract":"<p><p>Farmland management practices， especially tillage depth and straw return， are among the most important factors affecting farmland soil aggregates and soil organic carbon （SOC）. However， the mechanism of their interaction on SOC in farmland soil aggregates remains unclear. Therefore， in consideration of China's dryland farmland ecosystem and with the help of Meta-analysis technology， 71 published research papers were integrated and analyzed to explore the effects of tillage and straw return and their interactions on farmland soil aggregates and SOC. The results showed that tillage depth significantly affected the distribution of soil aggregates and SOC content. The mass fraction of macroaggregates increased by 36.55% under the no-tillage （NT） condition （shallow tillage &gt; deep tillage）. In particular， shallow tillage increased the SOC of macroaggregates by 60.98% （<i>P</i> &lt; 0.05）. Compared with traditional tillage， straw return could increase the input of organic matter and also promote the transformation of small- and medium-sized aggregates to large-sized aggregates， thus increasing the mass fraction of soil aggregates and its SOC. In particular， the mass fraction of large aggregates increased by 15.1% （<i>P</i> &lt; 0.05）， and the SOC of large aggregates increased by 16.61% （<i>P</i> &lt; 0.05）. In addition， the interaction between tillage depth and straw return had significant effects on soil aggregate distribution and aggregate SOC. Shallow tillage with straw return （STS） had the most significant effect； it increased the mass fraction of macroaggregates and the SOC of macroaggregates by 71.3% （<i>P</i> &lt; 0.05） and 60.3% （<i>P</i> &lt; 0.05）， respectively. Furthermore， the increase of SOC under different tillage depths after straw return was closely related to the stability of soil aggregates and the change of SOC in soil aggregates. Geometric mean diameter had the largest contribution rate to soil aggregate stability， and soil microaggregate SOC made the largest contribution to soil aggregate SOC. Therefore， in China's dryland farmland ecosystem， tillage depth and straw return and their interaction affect the distribution of soil aggregates and SOC. For total SOC， geometric mean diameter and microaggregate SOC have the highest contribution rates. In conclusion， shallow tillage straw return may be an important agricultural management measure to improve soil stability and carbon sequestration capacity.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5694-5704"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Spatial and Temporal Evolution and Prediction of Carbon Storage in Dali County Based on InVEST-PLUS Model].","authors":"Jia-Yi Sun, Li-Li Zhao, Kang-Hui Zhu, Miao Wen, Feng-Peng Han","doi":"10.13227/j.hjkx.202405321","DOIUrl":"https://doi.org/10.13227/j.hjkx.202405321","url":null,"abstract":"<p><p>This study aimed to investigate the impact of land use changes on the spatiotemporal dynamics of carbon storage from the perspective of territorial spatial planning， using Dali County as a case study. The spatiotemporal characteristics of land use types and carbon storage were analyzed from 1990 to 2020 using the InVEST and PLUS models. Then， the changes of the land use and carbon storage in 2030 were predicted under three scenarios： natural development， ecological protection， and economic development. The results are as follows： ①The land use type of Dali County is mainly cultivated land， accounting for more than 70% of the total area， followed by forest land， grassland， water bodies， construction land， and unused land. From 1990 to 2020， the area of grassland and unused land decreases， while the area of cultivated land， forest land， water bodies， and construction land increase. Notably， the area of construction land experiences the most rapid increase of 78.72%. ② Spatially， the regions with a significant increase in carbon storage are located mainly in the southern sandy areas of Dali County， the regions with a decrease in carbon storage are scattered， and the carbon storage in the Yellow River beach area has a notable general downward trend. Temporally， the carbon storage in Dali County shows an increasing trend from 1990 to 2000. However， with the acceleration of urbanization and the expansion of construction land area during 2000 to 2020， the loss rate of carbon storage increases， and the loss amount reaches 50.78×10⁶ t. ③ Obvious differences of carbon storage in 2030 emerge among the different scenarios. In the ecological protection scenario， carbon storage increases because the protection of forest and grass resources and strict constraints on the expansion of construction land are effectively ensured. In the natural development scenario， less carbon is lost. In the economic development scenario， the significant conversion of high-density carbon agricultural land to low-density carbon construction land leads to the greatest carbon loss. In light of these results， future land use planning in Dali County should focus on enhancing the control and protection of ecological nodes， strictly regulating the addition of new construction land， optimizing land use patterns， improving ecosystem service functions， increasing carbon sequestration efficiency， and promoting coordinated development between the county's economy and environment.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5765-5776"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Application of Machine Learning Techniques for Antimicrobial Resistance Prediction].","authors":"Chao Huang, Lu-Kai Qiao, Yi-Chun Wang, Yi-Hao Yu, Hong Bai, Fang-Zhou Gao, Jian-Liang Zhao, You-Sheng Liu, Liang-Ying He, Guang-Guo Ying","doi":"10.13227/j.hjkx.202408015","DOIUrl":"https://doi.org/10.13227/j.hjkx.202408015","url":null,"abstract":"<p><p>Due to the abuse or excessive use of antimicrobials， particularly antibiotics， antimicrobial resistance （AMR） has become one of the major challenges in global public health. The rapid growth of microbial data， facilitated by advancements in high-throughput sequencing technology， underscores the importance of leveraging machine learning for predicting AMR and identifying resistance markers. Machine learning， encompassing supervised and unsupervised learning， has been proven effective by early studies of AMR prediction. By analyzing microbial genomes and AMR data to build machine learning models， we can improve predictions of microbial resistance and develop more effective antibiotic use strategies， thereby controlling the spread of resistance. This review article focuses on the specific construction processes of machine learning algorithms and the models commonly employed in AMR studies. It also highlights the diverse applications and prospects of machine learning in AMR prediction， with the goal of offering a scientific foundation for future environmental AMR monitoring initiatives.</p>","PeriodicalId":35937,"journal":{"name":"环境科学","volume":"46 9","pages":"5659-5671"},"PeriodicalIF":0.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}