工业工程最新文献

In the current era， the rapid development of environmental science and computer technology complement each other. Among them， the application of machine learning in the research field of water quality purification in constructed wetlands has become increasingly prominent， showing vigorous vitality and broad prospects. This paper focuses on this aspect and systematically reviews the main research progress of machine learning in water quality purification in constructed wetlands in recent years， striving to comprehensively and deeply analyze its key threads. On the one hand， an in-depth exploration of the diverse application directions of machine learning algorithms in constructed wetlands is carried out， covering key links in water quality purification such as microbial metabolism and pollutant degradation， plant absorption and transformation processes， substrate adsorption and filtration mechanisms， and hydraulic conditions， accurately grasping the adaptation patterns of algorithms in each link. At the same time， the characteristics of constructed wetland data are deeply excavated to lay a solid foundation for algorithm optimization. Further， it is elaborated from three core dimensions， in which we： ① focus on the key processes of water purification assisted by machine learning and clarify the complex interaction mechanisms among microorganisms， plants， substrates， and hydraulic conditions； ② commit to multi-dimensional data fusion to reshape the architecture of water purification mechanisms and drive in-depth understanding with data； and ③ explore the practical applications of machine learning in the design optimization and operation control of constructed wetlands to enhance wetland efficiency. In addition， the article takes a long-term view and looks ahead to future research directions from five aspects， namely model improvement and innovation， data fusion and sharing， real-time monitoring and intelligent control， integration with other technologies， and environmental impact assessment and ecological restoration. To summarize， machine learning injects new vitality into the research on water quality purification in constructed wetlands， opens up new perspectives， and effectively promotes the efficiency of water quality purification and management levels. However， at present， continuous efforts still need to be made in the in-depth optimization of algorithms and solving practical application problems to fully release its potential.

Ecological management zoning is a crucial tool for land use governance and spatial optimization， serving as a foundational strategy for implementing differentiated regional management and protection. It plays a key role in mitigating human-environment conflicts and fostering the sustainable development of both ecological and socio-economic systems. Focusing on the Three Gorges Reservoir area， an essential ecological corridor in the middle Yangtze River Basin， this study quantitatively analyzes the supply and demand of ecosystem services. Using a bivariate local spatial autocorrelation model and a coupling coordination model， the study explores the relationship between ecosystem service supply and demand and the intensity of land use. The study then delineates ecological management zones and simulates changes in zoning patterns under two distinct scenarios for 2030. The results show that： ① In 2020， both natural factors and human activities influenced the supply and demand of ecosystem services in the Three Gorges Reservoir area， resulting in significant spatial heterogeneity. Notably， the main urban area of Chongqing exhibited a severe imbalance in the supply-demand relationship of ecosystem services. ② Based on the coupling coordination analysis of ecosystem service supply-demand and land use intensity， the Three Gorges Reservoir area was categorized into four ecological zones： the ecological coordinated development zone， ecological potential development zone， ecological imbalance risk zone， and ecological strict control zone. This zoning approach aids in accurately identifying the ecological status of different regions and formulating targeted protection and development strategies， thereby promoting the sustainable integration of ecological and economic development. ③ Scenario simulations for 2030 indicated an expansion of the ecological coordinated development zone in both scenarios， particularly in certain areas of the urban core of Chongqing. This suggests that urban areas are not entirely dominated by human-environment conflicts and that regions of ecological coupling coordination still exist. Future research should focus on enhancing ecological coordination within urban areas to further optimize the relationship between ecological conservation and human activities. These findings provide valuable insights for maintaining ecological balance and advancing sustainable development in the Three Gorges Reservoir area.

The frequent O₃ pollution in China occurs mainly in volatile organic compounds （VOCs） control areas. However， a simulation focusing on the influence of reduction from different VOCs sources is lacking. Thereby， we conducted online observations of 116 types of VOCs and HCHO based on liquid phase chemistry in the summer of 2024 in Nanjing. A positive matrix factorization （PMF） model was further combined with observational-based model （OBM） to explore O₃ control policies for emission reduction from different pollution sources. As a result， the maximum 8h moving average of O₃[ρ（MDA8-O₃）] in Nanjing exceeded the national standard （222 μg·m^-3）， and the average volume mixing ratio of total VOCs （including HCHO） was 30.2×10^-9， dominated by oxygenated VOCs and alkanes. Acetaldehyde， formaldehyde， and isoprene as the top three species contributed 51.8% of the total ozone formation potential （151 μg·m^-3）. Motor vehicle sources （33.9%） and industrial sources （26.4%） were the main sources of TVOCs. OBM simulation captured the measured O₃ （R=0.86） well， and the O₃ pollution in Nanjing was found to be in the VOCs control areas by the EKMA curve. The O₃ could reach the standard through a moderate reduction of VOCs （40%） or substantial reduction of NO_x （70%）. The scenario based on the observations and PMF resolved spectrum showed that O₃ pollution was more sensitive to motor vehicle sources and industrial sources， wherein reducing 90% of either source， respectively， could significantly reduce O₃ and reach the standard. This study on a basis of the measured pollutants could simulate the photochemical process in the real atmosphere to provide a theoretical suggestion for O₃ pollution control.

As a major global carbon emitter， China's provinces and municipalities contribute more than 90% of the country's carbon emissions， while the rest is mainly emitted by special administrative regions， trans-regional emission sources， and airspace and sea areas. How to accurately predict the carbon emissions of different provinces and municipalities and formulate emission reduction policies is the basis for realizing the national dual-carbon target and high-quality synergistic economic development. Taking Shaanxi Province， located in Northwest China， as an example， a top-down and bottom-up integrated RR-STIRPAT-LEAP model is developed using relevant cross-section data from 2000 to 2021， and the prediction accuracy is improved by optimizing the weights of sub-models. On this basis， the carbon emissions of Shaanxi Province from 2022 to 2060 are forecasted， and five joint scenarios are designed to simulate the dual-carbon pathway of Shaanxi Province in combination with the carbon sink absorption model. The ReliefF algorithm is used to analyze the important potential drivers of carbon emission reduction. The results found that the prediction accuracy of the RR-STIRPAT-LEAP-Shaanxi model was significantly better than that of a single model， and the optimized model error was 0.24%. It was predicted that Shaanxi Province will reach its peak in 2030， and the emissions （in terms of tons） will be 419.09 million tons （Mt）. Under the joint scenario， macro-control-EMT-F Shaanxi Province will achieve carbon neutrality by 2060， with an emission of -25.69 million tons， indicating that ecological carbon sinks played an important role in achieving carbon neutrality. Comparison of carbon emission changes under different joint scenarios revealed that upgrading the energy structure and improving energy efficiency were the key drivers of Shaanxi Province's low-carbon transition and that the implementation of macroeconomic and sectoral energy consumption control strategies could reduce more carbon emissions. ReliefF showed that Shaanxi Province's carbon emission reduction focused on the following industrial sectors in order： industry > power generation > agriculture > residential sector > transportation， storage， and postal services > construction > other services. Among them， agriculture was not only an important source of carbon emissions but also an important carbon sink， and its potential for emission reduction should not be ignored. After comprehensively analyzing the short and medium to long-term carbon emission pathways and carbon emission reduction drivers， this study provides a pathway map for the synergistic development of Shaanxi Province， which will provide a scientific basis for government policymakers and relevant enterprises to formulate low-carbon and high-quality economic development plans.

Nature reserves are effective avenues for providing ecosystem services and conserving biodiversity. Quantitative assessments of ecosystem services and their driving factors are crucial for conservation management and planning in nature reserves. Taking Saihanwula National Nature Reserve as the study area， this study quantified four ecosystem services， including water yield， carbon sequestration， habitat quality， and soil conservation， spanning from 2000 to 2020. We explored the influence of different driving factors on the spatio-temporal patterns of ecosystem services by using the Geodetector and Geographically Weighted Regression （GWR） models. Furthermore， we identified ecosystem service clusters based on the Self-Organizing Map （SOM） neural network and proposed management recommendations accordingly. The results showed that each ecosystem service in Saihanwula National Nature Reserve exhibited spatial heterogeneity. From 2000 to 2020， water yield and soil conservation significantly enhanced， increasing by 89.8% and 126.1%； carbon storage enhanced by 5.2%； and habitat quality remained essentially unchanged， with a change of only 0.7%. Precipitation and land use type were the main ecosystem service driving factors， and the combined effects of various driving factors were greater than those of a single factor. We identified three types of ecosystem service bundles， including the ecological core service bundle， ecological transition service bundle， and ecological fragile service bundle. We then proposed diversified zoning management recommendations for nature reserves from the perspectives of conservation， planning， and management. The results of this study can provide a scientific basis for the zoning management and optimization of Saihanwula National Nature Reserve.

The adsorption characteristics of microplastics （MPs） for pollutants in the aqueous environment have received extensive attention； however， the adsorption characteristics of UV-aged MPs for arsenic （As） are not yet fully understood. In this study， the adsorption kinetics and isothermal adsorption of As（Ⅴ） from aqueous solutions by pristine and UV-aged MPs were investigated in static adsorption mode. Polypropylene microplastics （PP MPs） were used as the adsorbent， and the effects of environmental factors （pH， dissolved organic matter， and NO₃^-） on the adsorption process were also explored. The results showed that UV aging produced a substantial number of rough folded structures with irregular protrusions and pores on the surface of PP MPs. Furthermore， an enhancement in the prevalence of oxygen-containing functional groups， concomitant with an escalation in the crystallinity of the MPs， was observed. The adsorption of As（Ⅴ） by PP MPs tended to reach equilibrium within 12 h， and the adsorption kinetics of As（Ⅴ） on UV-aged MPs exhibited a stronger correlation with the pseudo-second-order model （R²=0.980）， indicating that the adsorption of As（Ⅴ） by UV-aged PP MPs was dominated by chemisorption. The Freundlich and Langmuir models were found to be applicable to the isothermal adsorption of As（Ⅴ） by aged MPs， with the Freundlich model providing a superior fit to the data. This finding suggests that the adsorption of As（Ⅴ） on aged MPs was predominantly influenced by surface complexation and van der Waals forces. The theoretical maximum adsorption （Q_m） of As（Ⅴ） by UV-aged MPs fitted by the Langmuir model increased by 11.8% compared to that by the pristine MPs. In addition， the adsorption of As（Ⅴ） by aged PP MPs exhibited an increasing trend， followed by a decrease， with elevated NO₃^- and dissolved organic matter concentrations. This study provides a significant theoretical foundation for investigating the biogeochemical cycling and ecological risk assessment of As from aging MPs.

Soil salinity and alkalinity are key factors limiting sustainable agricultural development. Timely acquisition of salinity and alkalinity information is crucial for soil improvement and long-term fertility enhancement. After orthogonal signal correction （OSC） transformation of the hyperspectral reflectance， competitive adaptive reweighted sampling （CARS） was used to screen the characteristic bands of salinity and alkalinity information using the ground hyperspectral and measured soil salinity （SSC） and pH values of the Hetao Plain as data sources. Then， environmental variables and microwave remote sensing data were introduced to build the inversion models based on six integrated machine learning algorithms， including extreme gradient boosting （XGBoost）， adaptive boosting （AdaBoost）， and random forest （RF）， and six integrated machine learning algorithms were used to build inversion models of SSC and pH. The models were visualized and analyzed using Shapley additive explanations （SHAP）. The results showed that： ① The salinity and alkalinity grades of farmland soils in the Hetao Plain were generally mild to moderate， with strong spatial heterogeneity in salinity and alkalinity. ② The OSC transform optimized the structure of the spectral data， which greatly improved the resolution ability under the complex background. CARS effectively screened out the characteristic bands related to salinity and alkalinity information， and the SSC characteristic bands included 13 bands such as 450， 470， and 600 nm. The pH characteristic bands included 15 bands such as 680， 730， and 740 nm. ③ The AdaBoost algorithm performed optimally for SSC inversion with validation set R_p²， root mean square error （RMSE）， and relative analysis error （RPD） of 0.852， 1.352， and 2.88， respectively， whereas pH was best with the XGBoost model， which had an R_p²， RMSE， and RPD of 0.908， 0.151， and 3.31， respectively. ④ SHAP analysis showed that the prediction models for SSC and pH reflected multifactorial synergies. Waveband and climate factors were the dominant factors in SSC modeling with a cumulative contribution of 80.8%. Soil attributes （24.88%） had the highest contribution to pH modeling， waveband data had the smallest contribution of 15.13%， microwave remote sensing data had limited contribution to salinity and alkalinity modeling， and the combination of multi-source data provided a strong support for the accurate monitoring of soil salinization and alkalization. The study conclusions help to promote sustainable land management and efficient agricultural production.

To enhance the technical support of soil environmental quality monitoring services for territorial spatial planning and the sustainable development of ecological civilization in the Beijing Municipal Administrative Center， this study systematically investigated the changes in heavy metal contamination status and sources in the soils of Tongzhou District over the past two decades. Using inverse distance weighted （IDW） spatial interpolation， the geo-accumulation index， the single-factor pollution index， and the Nemerow comprehensive pollution index， this study conducted a sectional evaluation of the spatial distribution and accumulation characteristics of eight heavy metal elements （As， Cd， Cr， Cu， Hg， Ni， Pb， and Zn） in the soils of Tongzhou District from 2005 to 2023. Correlation analysis， principal component analysis （PCA）， and the positive matrix factorization （PMF） model were employed to identify the principal components and source contributions of heavy metals. The results showed that the concentrations of Cr， Cu， Ni， Pb， and Zn exhibited minimal variation across the four selected years （2005， 2011， 2018， and 2023）， while the median values of Cd， Hg， and Zn exceeded the background values of Beijing. The concentrations of Cd and Hg in top soil were significantly higher than those in deeper layers， with the proportion of Cd enriched sites showing a decreasing trend over the years， whereas Hg exhibited strong spatial heterogeneity. From 2005 to 2011， Cd， Hg， Cu， and Pb were highly enriched in areas with intense industrial activities， incineration sources， and traffic emissions. In 2018， high concentrations of Cd， Zn， Cu， and Pb were primarily distributed in the central and eastern agricultural lands of the study area. Compared to that in 2005， the enrichment extent of Cd， Hg， Cu， Pb， and Zn in 2023 was significantly reduced. In 2005， As， Cr， Cu， Ni， Pb， and Zn mainly originated from natural/agricultural mixed sources， while in 2011， these elements were primarily derived from natural， traffic， and agricultural mixed sources. Cd was mainly associated with industrial sources in both 2005 and 2011. In 2018 and 2023， As， Cr， Cu， Ni， and Pb were predominantly attributed to natural， traffic， and agricultural mixed sources， whereas Cd and Zn were mainly from industrial sources. Hg in soil across all four years was primarily derived from atmospheric deposition. Key factors influencing variations in source contributions included land development intensity， agricultural fertilization rates， traffic emissions， the scale of industrial pollution enterprises， energy combustion emissions， and overall atmospheric pollution levels.