南方科技大学知识苑(SUSTech KC): 基于机器学习与过程模型的水环境容量估算与土壤修复研究

题名	基于机器学习与过程模型的水环境容量估算与土壤修复研究
其他题名	RESEARCH ON WATER ENVIRONMENTAL CAPACITY ESTIMATION AND SOIL REMEDIATION BASED ON MACHINE LEARNING AND PROCESS-BASED MODELS
姓名	王欣
姓名拼音	WANG Xin
学号	11849583
学位类型	博士
学位专业	083001 环境科学
学科门类/专业学位类别	08 工学
导师	刘崇炫
导师单位	环境科学与工程学院
论文答辩日期	2023-04-09
论文提交日期	2023-06-14
学位授予单位	哈尔滨工业大学
学位授予地点	哈尔滨
摘要	作为建设生态文明的关键研究领域，水土环境污染防治和修复是保障国家生态安全和实现建设美丽中国的重要支柱。过程模型常被用于模拟水和土壤环境中各类水文、生物、地球化学等过程。由于过程模型存在监测数据难以获取、计算成本高以及时空非均质性强等问题，过程模型在描述水和土壤环境中各类过程和它们的相互作用时具有一定的局限性。机器学习是一种强大的数据分析工具，在适应数据方面高度灵活，可以识别过程模型中未明确表示的隐藏模式。过程模型与机器学习的集成可以实现过程模型既遵循物理定律，具有概念化和可解释性，同时又受益于机器学习强大的数据分析和高性能计算能力，有助于提高对跨学科和跨尺度环境过程的理解和对复杂环境行为的预测能力。基于此，本文提出了一个机器学习与过程模型相结合的通用计算方法，将过程模型与基于数据驱动的机器学习的多功能性耦合起来。首先，通过文献调研、数据收集，构建过程模型产生数据集。然后通过机器学习模型对数据集进行学习和训练，进而耦合 SCE-UA（Shuffled complex evolution method developed at The University of Arizona）优化算法分别对水环境容量和土壤修复开展了优化研究。具体工作如下：提出了一个基于机器学习与过程模型的流域水环境容量估算与优化方法。该方法将反向传播（Back Propagation，BP）神经网络模型作为一种高效的工具与MIKE11 过程模型以及 SCE-UA 优化算法相结合，以氨氮为关注污染物，开展了茅洲河流域氨氮环境容量的定量估算与优化。为了验证方法的有效性，本文考虑了固定氨氮输入通量比例的情景和变氨氮输入通量比例的情景，并对两种情景下的水环境容量进行了估算和比较。结果表明，固定氨氮输入通量比例的情景下，水环境容量随着水质目标的降低而增加。变氨氮输入通量比例的情景下，水环境容量随水质目标和氨氮输入分布的不同而变化。此外，与仅用过程模型进行模拟相比，BP 神经网络模型的结合可以显著降低计算成本。研究结果为流域尺度水质管理提供一种有效的优化设计方法。建立了一个基于机器学习与过程模型的土壤原位热脱附技术优化方法，旨在解决土壤原位热脱附技术修复过程中能源利用率低和能量损耗高等问题。在该方法中，BP 神经网络模型与 COMSOL Multiphysics 过程模型以及 SCE-UA 优化算法相结合，通过对热脱附加热过程的有效预测，优化了最佳的加热功率组合分布，节省了总能耗。本文考虑了恒定加热功率情景和变加热功率情景两种情景，并比较了两种情景下的温度场变化和不同修复目标下的总能耗。结果表明，变加热功率情景下的总能耗比恒定加热功率情景下的总能耗小，能耗节省率可达到 35.93-45.04%。在实际工程修复中需要关注加热棒的深度、冷点温度的变化和加热功率的大小。研究结果可为推动原位热脱附技术在工程实践中的实施发展以及修复方案的深化设计提供技术支撑。针对场地修复中存在的过度修复和高成本问题，以广州市华侨糖厂为研究区域，砷为关注污染物，提出了一个基于机器学习与过程模型的土壤修复技术集成优化方法。该方法将随机森林与 PFLOTRAN 过程模型以及 SCE-UA 优化算法相结合，对场地修复技术组合方案进行了优化设计。本文考虑了自然修复情景和异位开挖修复情景，并对两种情景下的砷的时空变化趋势和不同修复目标下的土方开挖量进行了预测和比较。结果表明，在长期的自然修复条件下，由于研究区地下水流动性较差，砷的迁移过程非常缓慢，污染区和附近地下水存在污染风险，但砷向河流扩散的迁移通量很小，地表水暴露途径的风险低。通过模拟优化，异位开挖辅以自然修复的方式适用于华侨糖厂，该方法已在场地修复中采用。优化方法的建立可以为场地修复治理提供灵活的优化方案。
其他摘要	As a crucial area of research in the construction of an ecological civilization, the prevention and remediation of water and soil pollution serves as an essential pillar for ensuring national ecological security and achieving the goal of building a beautiful China. In order to better understand the complex environmental processes and the internal mechanisms in water and soil systems, process-based models are often used to simulate various hydrological, biological and geochemical processes. Due to the problems of multi-sources and scarcity of monitoring data, high cost of model simulations, and spatiotemporal heterogeneity, process-based models often have limitations in describing the processes and their interaction in water and soil environments. As a powerful data analysis tool, machine learning (ML) is highly flexible in handling data. ML can identify hidden patterns that are not explicitly represented in process-based models. The integration of process-based models with ML can integrate whether process-based models follow the laws of physics in both conceptualization and interpretability. It also benefits from the powerful data analysis and high performance of massive computing capabilities of ML, which helps to improve the understanding of the coupling of cross-scale environmental processes with the ability to predict complex environmental behavior. This dissertation proposed a general computational method for coupling machine learning with process-based models that takes advantages of process-based models with the versatility of data-driven ML in simulations. In this method, firstly, through literature research and data collection, the process-based model was constructed to generate a dataset. The dataset was then used to train a ML-based model, which was used by a SCE-UA (Shuffled complex evolution method developed at The University of Arizona) optimization algorithm to estimate and optimize the water environmental capacity and site remediation technology. The specific work is as follows: A watershed water environmental capacity estimation and optimization method coupled with ML and process-based model was successfully developed. In this method, the BP neural network model as an efficient tool was coupled with the MIKE11 process-based model and SCE-UA optimization algorithm to quantitatively estimate and optimize the ammonia nitrogen environmental capacity in the Maozhou River Watershed. To demonstrate the effectiveness of the method, this dissertation considered two scenarios, fixed ammonia nitrogen input flux ratio and scenarios with variable ammonia nitrogen input flux ratio, and the estimated water environmental capacities under the two scenarios were compared. The results indicated that under fixed ammonia nitrogen input flux ratio scenario, the water environmental capacity increased with the decrease of water quality targets. In variable ammonia nitrogen input flux ratio scenario, the water environmental capacity varied with the water quality target and the ammonia input distribution. In addition, the coupling of BP neural network model could significantly reducecomputational costs compared to the simulations using process-based model alone. Theresearch results provided an effective optimization method for watershed-scale water quality management. An optimization method for soil in-situ thermal desorption technology based on ML and process-based model was investigated, aiming to address the issues of low energy utilization and high energy loss in the soil in-situ thermal desorption remediation process. In this method, the BP neural network model was coupled with the COMSOL Multiphysics 5.6 process-based model and the SCE-UA optimization algorithm to optimize the optimal heating power distribution and reduce total energy consumption by effectively predicting the thermal process of thermal decoupling. This research considered two scenarios: the constant power scenario and the variable power scenario. The simulated temperature field change and the total energy consumption under different restoration goals in the two scenarios were compared. The results showed that the total energy consumption under the variable power scenario was smaller than those under the constant power scenario, and the energy consumption saving rate could reach 35.93-45.04%. In the actual engineering remediation, it is necessary to pay attention to the depth of the heating well, the change of cold spot temperature and the magnitude of the heating power. The research results can provide technical support for promoting the development and application of in-situ thermal desorption technology in engineering practice and the optimal design of remediation schemes. Aiming at the problems of excessive remediation and high cost in site soil remediation, an optimization method in coupling with ML and process-based model was proposed and developed to integrate and optimize multiple remediation technologies. The method was demonstrated at Guangzhou Huaqiao Sugar Factory where arsenic is a pollutant. In this method, random forest was coupled with PFLOTRAN process-based model and the SCE-UA optimization algorithm to integrate and optimize the combination of site remediation technologies. In this research, the natural attenuation remediation scenario and the ex-situ remediation scenario were considered. The temporal and spatial variations of arsenic, and the excavation volume under different remediation targets in the two scenarios were predicted and compared. The results showed that the groundwater flow condition in the study area was poor, and the migration process of arsenic was slow. Under long-term natural attenuation remediation conditions, there has a risk of contamination in contaminated areas and nearby groundwater. The migration flux of arsenic transport to the river is small, so the risk of surface water exposure pathways is low. Through simulation optimization, the combined remediation method of excavation supplemented with natural attenuation is suitable for Huaqiao sugar factory, which has been adopted in site remediation. The result demonstrated that the method developed in this study can provide flexible optimization schemes for site remediation.
关键词	机器学习过程模型优化算法水环境容量原位热脱附场地修复
其他关键词	Machine Learning Process-based Model Optimization Algorithm Water Environmental Capacity In-situ Thermal Desorption Site Remediation
语种	中文
培养类别	联合培养
入学年份	2018
学位授予年份	2023-06
参考文献列表	[1] LI L, MAHER K, NAVARRE-SITCHLER A, et al. Expanding the role of reactive transport models in critical zone processes[J]. Earth-Science Reviews, 2017, 165: 280-301. [2] STEEFEL C I, DEPAOLO D J, LICHTNER P C. Reactive transport modeling: An essential tool and a new research approach for the Earth sciences[J]. Earth and Planetary Science Letters, 2005, 240(3): 539-358. [3] CLARK J S, GELFAND A E. A future for models and data in environmental science[J]. Trends in Ecology & Evolution, 2006, 21(7): 375-380. [4] ALOUI S, MAZZONI A, ELOMRI A, et al. A review of soil and water assessment tool (SWAT) studies of mediterranean catchments: applications, feasibility, and future directions[J]. Journal of Environmental Management, 2023, 326: 116799. [5] NING Z, LI R, LIAN H, et al. Effects of flow-interruption on the bacteria transport behavior in porous media[J]. Journal of Hydrology, 2021, 595: 125677. [6] WASHINGTON W M, BUJA L, CRAIG A. The computational future for climate and earth system models: on the path to petaflop and beyond[J]. Philosophical transactions Series A, Mathematical, physical, and engineering sciences, 2009, 367(1890): 833-846. [7] MOHAMMED S A, ATTARNEJAD R, HAMAMIN D F. Aquifer feature estimation in Basara basin using a groundwater modeling system for smart agriculture[J]. Computers and Electrical Engineering, 2022, 103: 108354. [8] 李佳. 基于机器学习的多孔介质渗透率预测研究[D]. 杭州: 浙江大学, 2019: 8-10. [9] NAGHIBI S A, MOGHADDAM D D, KALANTAR B, et al. A comparative assessment of GIS-based data mining models and a novel ensemble model in groundwater well potential mapping[J]. Journal of Hydrology, 2017, 548: 471-483. [10] LI P, ZHA Y, SHI L, et al. Comparison of the use of a physical-based model with data assimilation and machine learning methods for simulating soil water dynamics[J]. Journal of Hydrology, 2020, 584: 124692. [11] LI W, FANG H, QIN G, et al. Concentration estimation of dissolved oxygen in Pearl river basin using input variable selection and machine learning techniques[J]. Science of The Total Environment, 2020, 731: 139099. [12] SUSHANTH K, MISHRA A, MUKHOPADHYAY P, et al. Real-time streamflow forecasting in a reservoir-regulated river basin using explainable machine learning and conceptual reservoir module[J]. Science of The Total Environment, 2023, 861: 160680. [13] CHEN C C, WANG Y R, YEH H Y, et al. Estimating monthly PM2.5 concentrations from satellite remote sensing data, meteorological variables, and land use data using ensemble statistical modeling and a random forest approach[J]. Environmental Pollution, 2021, 291: 118159. [14] REICHSTEIN M, CAMPS-VALLS G, STEVENS B, et al. Deep learning and process understanding for data-driven earth system science[J]. Nature, 2019, 566(7743): 195-204. [15] CUDDINGTON K, FORTIN M-J, GERBER L R, et al. Process-based models are required to manage ecological systems in a changing world[J]. Ecosphere, 2013, 4(2): 1-20. [16] 何用, 李义天. 重金属迁移转化模型研究[J]. 水科学进展, 2004, (5): 576-583. [17] 应珊珊. 基于贝叶斯方法的土壤溶质迁移转化反演研究[D]. 杭州: 浙江大学, 2018: 2-3. [18] DOULGERIS C, GEORGIOU P, PAPADIMOS D, et al. Ecosystem approach to water resources management using the MIKE 11 modeling system in the Strymonas river and lake Kerkini[J]. Journal of Environmental Management, 2012, 94(1): 132-143. [19] WANG Y, ZHOU X, ENGEL B. Water environment carrying capacity in Bosten Lake basin[J]. Journal of Cleaner Production, 2018, 199: 574-583. [20] YIRA Y, DIEKKRüGER B, STEUP G, et al. Modeling land use change impacts on water resources in a tropical west African catchment (Dano, Burkina Faso)[J]. Journal of Hydrology, 2016, 537: 187-199. [21] WARBURTON M L, SCHULZE R E, JEWITT G P W. Hydrological impacts of land use change in three diverse south African catchments[J]. Journal of Hydrology, 2012, 414-415: 118-135. [22] BAKER T J, MILLER S N. Using the soil and water assessment tool (SWAT) to assess land use impact on water resources in an east African watershed[J]. Journal of Hydrology, 2013, 486: 100-111. [23] DEVIA G K, GANASRI B P, DWARAKISH G S. A review on hydrological models[J]. Aquatic Procedia, 2015, 4: 1001-1007. [24] SHIH S-S, HSU Y-W. Unit hydrographs for estimating surface runoff and refining the water budget model of a mountain wetland[J]. Ecological Engineering, 2021, 173: 106435. [25] NOVOTNY V. Encyclopedia of ecology (second edition)-watershed models[M]. Oxford; Elsevier. 2019: 221-232. [26] ABBOTT M B, BATHURST J C, CUNGE J A, et al. An introduction to the european hydrological system-systeme hydrologique europeen, “SHE”, 2: structure of a physically-based, distributed modelling system[J]. Journal of Hydrology, 1986, 87(1): 61-77. [27] PANDI D, KOTHANDARAMAN S, KUPPUSAMY M. Hydrological models: a review[J]. International Journal of Hydrology Science and Technology, 2021, 12(3): 223-242. [28] SONG X, ZHANG J, ZHAN C, et al. Global sensitivity analysis in hydrological modeling: review of concepts, methods, theoretical framework, and applications[J]. Journal of Hydrology, 2015, 523: 739-757. [29] KELLER A A, GARNER K, RAO N, et al. Hydrological models for climate-based assessments at the watershed scale: a critical review of existing hydrologic and water quality models[J]. Science of The Total Environment, 2023, 867: 161209. [30] WANG S, XU L, YANG F L, et al. Assessment of water ecological carrying capacity under the two policies in Tieling City on the basis of the integrated system dynamics model[J]. Science of The Total Environment, 2014, 472: 1070-1081. [31] YU W, MIN Q, LI X. Some progresses and perspectives in study on the carrying capability of water resources[J]. Arid Zone Research, 2003, 20(1): 60-66. [32] ZHANG Y J, HAO J F. The evaluation of environmental capacity: evidence in hunan province of China[J]. Ecological Indicators, 2016, 60: 514-523. [33] XIE R, PANG Y, BAO K. Spatiotemporal distribution of water environmental capacity-a case study on the western areas of Taihu lake in Jiangsu province, China[J]. Environmental science and pollution research international, 2014, 21(8): 5465-5473. [34] LI K, ZHANG L, LI Y, et al. A three-dimensional water quality model to evaluate the environmental capacity of nitrogen and phosphorus in Jiaozhou Bay, China[J]. Marine Pollution Bulletin, 2015, 91(1): 306-316. [35] ZHAO C S, YANG S T, SUN Y, et al. Estimating river accommodation capacity for organic pollutants in data-scarce areas [J]. Journal of Hydrology, 2018, 564: 442-451. [36] CHEN Q, WANG Q, LI Z, et al. Uncertainty analyses on the calculation of water environmental capacity by an innovative holistic method and its application to the Dongjiang River[J]. Journal of Environmental Sciences, 2014, 26(9): 1783-1790. [37] FAN C, CHEN K H, HUANG Y Z. Model-based carrying capacity investigation and its application to total maximum daily load (TMDL) establishment for river water quality management: a case study in Taiwan[J]. Journal of Cleaner Production, 2021, 291: 125251. [38] ZHANG X, LUO J G, ZHANG X, et al. Dynamic simulation of river water environmental capacity based on the subsection summation model[J]. Water Environment Research, 2020, 92(2): 278-290. [39] HUGHES D A, LOUW D. Integrating hydrology, hydraulics and ecological response into a flexible approach to the determination of environmental water requirements for rivers[J]. Environmental Modelling & Software, 2010, 25(8): 910-918. [40] LIU R M, SUN C C, HAN Z X, et al. Water environmental capacity calculation based on uncertainty analysis: a case study in the Baixi watershed area, China[J]. Procedia Environmental Sciences, 2012, 13: 1728-1738. [41] BETHKE C M. Geochemical and biogeochemical reaction modeling (third edition)[M]. Cambridge: Cambridge University Press, 2022. [42] HELGESON H C. Evaluation of irreversible reactions in geochemical processes involving minerals and aqueous solutions .I. thermodynamic relations[J]. Geochimica et Cosmochimica Acta, 1968, 32(8): 853-877. [43] LI L, MAHER K, NAVARRE-SITCHLER A, et al. Expanding the role of reactive transport models in critical zone processes[J]. Earth-Science Reviews, 2017, 165: 280-301. [44] XIE X J, PENG K, WANG Y X, et al. In situ arsenic immobilization by chemical oxidation: field trial and reactive transport modelling[J]. Journal of Hydrology, 2020, 583: 124645. [45] 黄小鱼. 基于数据同化的卫星遥感监测土壤盐渍化方法研究[D]. 咸阳: 西北农林科技大学, 2022: 8-9. [46] JIA M, BLUME O, AMOS R T, et al. Assessing GHG cycling in agricultural and riparian soils using a uniform reactive transport modeling approach[J]. Geoderma, 2022, 425: 116078. [47] JEMISON N E, BIZJACK M T, JOHNSON T M, et al. Influence of physical and chemical hydrology on bioremediation of a U-contaminated aquifer informed by reactive transport modeling incorporating 238U/235U ratios[J]. Geochimica et Cosmochimica Acta, 2020, 269: 303-328. [48] SUN Y, GLASCOE L G. Modeling biodegradation and reactive transport: analytical and numerical models[C], Biology, 2005. [49] DOMINIQUE G, BRUYELLE J. Geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation[J]. Computational Geosciences, 2018, 24: 697-707. [50] WANG X, LI R, TIAN Y, et al. Watershed-scale water environmental capacity estimation assisted by machine learning[J]. Journal of Hydrology, 2021, 597: 126310. [51] GANI R, BAŁDYGA J, BISCANS B, et al. A multi-layered view of chemical and biochemical engineering[J]. Chemical Engineering Research and Design, 2020, 155: A133-A145. [52] MORADI A, ABBASPOUR K C, AFYUNI M. Modelling field-scale cadmium transport below the root zone of a sewage sludge amended soil in an arid region in Central Iran[J]. Journal of Contaminant Hydrology, 2005, 79(3): 187-206. [53] PENG S, WANG N, CHEN J. Steam and air co-injection in removing residual TCE in unsaturated layered sandy porous media[J]. Journal of Contaminant Hydrology, 2013, 153: 24-36. [54] XU D, ZHU Q, ROS G H, et al. Model-based optimal management strategies to mitigate soil acidification and minimize nutrient losses for croplands[J]. Field Crops Research, 2023, 292: 108827. [55] WANG W S, LI C, LI Y Z, et al. Numerical analysis of heat transfer performance of in-situ thermal remediation of large polluted soil areas[J]. Energies, 2019, 12(24):4622. [56] BEBELIS S, BOUZEK K, CORNELL A, et al. Highlights during the development of electrochemical engineering[J]. Chemical Engineering Research and Design, 2013, 91(10): 1998-2020. [57] DOUAY F, ROUSSEL H, PRUVOT C, et al. Assessment of a remediation technique using the replacement of contaminated soils in kitchen gardens nearby a former lead smelter in Northern France[J]. Science of The Total Environment, 2008, 401(1-3): 29-38. [58] GIANNIS A, NIKOLAOU A, PENTARI D, et al. Chelating agent-assisted electrokinetic removal of cadmium, lead and copper from contaminated soils [J]. Environmental Pollution, 2009, 157(12): 3379-3386. [59] BUSTO Y, CABRERA X, TACK F M G, et al. Potential of thermal treatment for decontamination of mercury containing wastes from chlor-alkali industry[J]. Journal of Hazardous Materials, 2011, 186(1): 114-118. [60] HU W, NIU Y L, ZHU H, et al. Remediation of zinc-contaminated soils by using the two-step washing with citric acid and water-soluble chitosan[J]. Chemosphere, 2021, 282:131092. [61] MOON D H, GRUBB D G, REILLY T L. Stabilization/solidification of selenium-impacted soils using portland cement and cement kiln dust[J]. Journal of Hazardous Materials, 2009, 168(2-3): 944-951. [62] GONG Y Y, ZHAO D Y, WANG Q L. An overview of field-scale studies on remediation of soil contaminated with heavy metals and metalloids: technical progress over the last decade[J]. Water Research, 2018, 147: 440-460. [63] NEJAD Z D, JUNG M C, KIM K H. Remediation of soils contaminated with heavy metals with an emphasis on immobilization technology[J]. Environmental Geochemistry and Health, 2018, 40(3): 927-953. [64] MAHAR A, WANG P, ALI A, et al. Challenges and opportunities in the phytoremediation of heavy metals contaminated soils: a review[J]. Ecotoxicology and Environmental Safety, 2016, 126: 111-121. [65] O'BRIEN P L, DESUTTER T M, CASEY F X M, et al. Thermal remediation alters soil properties-a review[J]. Journal of Environmental Management, 2018, 206: 826-835. [66] 冉雨灵. 基于共沸共溶的土壤低温热脱附修复技术研究[D]. 上海: 华东理工大学, 2020: 5-7. [67] YE S J, ZENG G M, WU H P, et al. Co-occurrence and interactions of pollutants, and their impacts on soil remediation-a review[J]. Critical Reviews in Environmental Science and Technology, 2017, 47(16): 1528-1553. [68] MOKHTARI H A, BAGHERI M, MIRBAGHERI S A, et al. Performance evaluation and modelling of an integrated municipal wastewater treatment system using neural networks[J]. Water and Environment Journal, 2020, 34(S1): 622-634. [69] WANG Z, MAN Y, HU Y, LI A G, et al. A deep learning based dynamic COD prediction model for urban sewage[J]. Environmental Science: Water Research & Technology, 2019, 5(12): 2210-2218. [70] ZHU J J, ANDERSON P R. Performance evaluation of the ISMLR package for predicting the next day's influent wastewater flowrate at Kirie WRP[J]. Water Science and Technology, 2019, 80(4): 695-706. [71] WAI K P, CHIA M Y, KOO C H, et al. Applications of deep learning in water quality management: a state-of-the-art review[J]. Journal of Hydrology, 2022, 613: 128332. [72] ZHONG S, ZHANG K, BAGHERI M, et al. Machine learning: new ideas and tools in environmental science and engineering[J]. Environmental Science & Technology, 2021, 55(19): 12741-12754. [73] BZDOK D, ALTMAN N, KRZYWINSKI M. Statistics versus machine learning[J]. Nature Methods, 2018, 15(4): 233-234. [74] CERVANTES J, GARCIA-LAMONT F, RODRIGUEZ-MAZAHUA L, et al. A comprehensive survey on support vector machine classification: Applications, challenges and trends[J]. Neurocomputing, 2020, 408: 189-215. [75] SCHMIDHUBER J. Deep learning in neural networks: an overview [J]. Neural Networks, 2015, 61: 85-117. [76] AMORIM W P, ROSA G H, THOMAZELLA R, et al. Semi-supervised learning with connectivity-driven convolutional neural networks[J]. Pattern Recognition Letters, 2019, 128: 16-22. [77] REN L, NING X, WANG Z. A competitive Markov decision process model and a recursive reinforcement-learning algorithm for fairness scheduling of agile satellites[J]. Computers & Industrial Engineering, 2022, 169: 108242. [78] ZAIDI S M A, CHANDOLA V, ALLEN M R, et al. Machine learning for energy-water nexus: challenges and opportunities[J]. Big Earth Data, 2018, 2(3): 228-267. [79] WANG J, SONG G. A deep spatial-temporal ensemble model for air quality prediction[J]. Neurocomputing, 2018, 314: 198-206. [80] BAGHERI M, AKBARI A, MIRBAGHERI S A. Advanced control of membrane fouling in filtration systems using artificial intelligence and machine learning techniques: a critical review[J]. Process Safety and Environmental Protection, 2019, 123: 229-252. [81] SHI B, WANG P, JIANG J, et al. Applying high-frequency surrogate measurements and a wavelet-ANN model to provide early warnings of rapid surface water quality anomalies[J]. Science of The Total Environment, 2018, 610-611: 1390-1399. [82] CHEN X, WANG S, GAO H, et al. Comparison of deep learning models and a typical process-based model in glacio-hydrology simulation[J]. Journal of Hydrology, 2022, 615: 128562. [83] YASEEN Z M, SULAIMAN S O, DEO R C, DEO R C, et al. An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction[J]. Journal of Hydrology, 2019, 569: 387-408. [84] TARTAKOVSKY A M, MARRERO C O, PERDIKARIS P, et al. Physics-informed deep neural networks for learning parameters and constitutive relationships in subsurface flow problems[J]. Water Resources Research, 2020, 56(5): e2019WR026731. [85] GUO H, JEONG K, LIM J, et al. Prediction of effluent concentration in a wastewater treatment plant using machine learning models[J]. Journal of Environmental Sciences, 2015, 32: 90-101. [86] BOLSTER D, ROCHE K R, MORALES V L. Recent advances in anomalous transport models for predicting contaminants in natural groundwater systems[J]. Current Opinion in Chemical Engineering, 2019, 26: 72-80. [87] 王策. 松花江典型有机污染物动态数值模型构建与模拟[D]. 哈尔滨: 哈尔滨工业大学, 2013: 5-11. [88] PETERS-LIDARD C D, CLARK M, SAMANIEGO L, et al. Scaling, similarity, and the fourth paradigm for hydrology[J]. Hydrology and earth system sciences, 2017, 21(7): 3701-3713. [89] CHEN M, MAO S, LIU Y. Big data: a Survey[J]. Mobile networks and applications, 2014, 19(2): 171-209. [90] WEICHERT D, LINK P, STOLL A, et al. A review of machine learning for the optimization of production processes[J]. The International Journal of Advanced Manufacturing Technology, 2019, 104(5): 1889-1902. [91] WANG J J, IEEE. Comprehensive evaluation and analysis method for carrying capacity of water resource based on neural network[Z]. Proceedings of 8th International Conference on Intelligent Computation Technology and Automation, Nanchang, China, 2015: 305-308. [92] KAI X L, QIU X C, WANG Y, et al. The water environment carrying capacity of the Aiyi river based on artificial neural networks[J]. Polish Journal of Environmental Studies, 2020, 29(1): 131-139. [93] MAZZOCCHI F. Could big data be the end of theory in science?[J]. EMBO Reports, 2015, 16(10): 1250-1255. [94] REZAEE M, MAHDIANPARI M, ZHANG Y, et al. Deep convolutional neural network for complex wetland classification using optical remote sensing imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(9): 3030-3039. [95] SARAILIDIS G, WAGENER T, PIANOSI F. Integrating scientific knowledge into machine learning using interactive decision trees[J]. Computers & Geosciences, 2023, 170: 105248. [96] MA Y, LI L, YIN Z, et al. Research and application of network status prediction based on BP neural network for intelligent production line[J]. Procedia Computer Science, 2021, 183: 189-196. [97] WADOUX A M J C, MINASNY B, MCBRATNEY A B. Machine learning for digital soil mapping: applications, challenges and suggested solutions[J]. Earth-Science Reviews, 2020, 210: 103359. [98] DIAZ-GONZALEZ F A, VUELVAS J, CORREA C A, et al. Machine learning and remote sensing techniques applied to estimate soil indicators-review[J]. Ecological Indicators, 2022, 135: 108517. [99] KANG X, KOKKINAKI A, POWER C, et al. Integrating deep learning-based data assimilation and hydrogeophysical data for improved monitoring of DNAPL source zones during remediation[J]. Journal of Hydrology, 2021, 601: 126655. [100] CUI K, JING X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing and Applications, 2019, 31(12): 8205-8215. [101] 王勇. 松嫩平原北部农作物土壤水分有效性模拟及干旱评估研究[D]. 哈尔滨: 哈尔滨师范大学, 2021: 12-15. [102] TAN Y, ZHANG P, CHEN J, et al. Predicting the hydraulic conductivity of compacted soil barriers in landfills using machine learning techniques[J]. Waste Management, 2023, 157: 357-366. [103] ODEBIRI O, MUTANGA O, ODINDI J, et al. Mapping soil organic carbon distribution across South Africa's major biomes using remote sensing-topo-climatic covariates and concrete autoencoder-deep neural networks[J]. Science of The Total Environment, 2023, 865: 161150. [104] XIAO C, JI Q, CHEN J, et al. Prediction of soil salinity parameters using machine learning models in an arid region of northwest China[J]. Computers and Electronics in Agriculture, 2023, 204: 107512. [105] HOU D, AL-TABBAA A. Sustainability: A new imperative in contaminated land remediation[J]. Environmental Science & Policy, 2014, 39: 25-34. [106] FORTUNA M E, SIMION I M, GAVRILESCU M. Sustainability in environmental remediation[J]. Environmental Engineering and Management Journal, 2011, 10(12): 1987-1996. [107] HALEY J L, LANG D J, HERRINTON L J J G W M, et al. EPA's approach to evaluating and cleaning up ground water contamination at superfund sites[J]. 1989, 9: 177-183. [108] KONTOS Y N, KATSIFARAKIS K L. Optimal management of a theoretical coastal aquifer with combined pollution and salinization problems, using genetic algorithms[J]. Energy, 2017, 136: 32-44. [109] CARDIFF M, LIU X, KITANIDIS P K, et al. Cost optimization of DNAPL source and plume remediation under uncertainty using a semi-analytic model[J]. Journal of Contaminant Hydrology, 2010, 113(1): 25-43. [110] FINSTERLE S, ZHANG Y. Solving iTOUGH2 simulation and optimization problems using the PEST protocol[J]. Environmental Modelling & Software, 2011, 26(7): 959-968. [111] HAMMOND G E, LICHTNER P C. Field-scale model for the natural attenuation of uranium at the Hanford 300 area using high-performance computing[J]. Water Resources Research, 2010, 46(9): W09527. [112] NEVILLE C, TONKIN M J. Modeling multiaquifer wells with MODFLOW[J]. Groundwater, 2004, 42(6): 910-919. [113] STEEFEL C I, APPELO C A J, ARORA B, et al. Reactive transport codes for subsurface environmental simulation[J]. Computational Geosciences, 2015, 19(3): 445-478. [114] YADAV B, MATHUR S, CH S, et al. Data-based modelling approach for variable density flow and solute transport simulation in a coastal aquifer[J]. Hydrological Sciences Journal, 2018, 63(2): 210-226. [115] MO S, ZABARAS N, SHI X, et al. Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification[J]. Water Resources Research, 2019, 55(5): 3856-3881. [116] RIDSDALE D R, NOBLE B F. Assessing sustainable remediation frameworks using sustainability principles[J]. Journal of Environmental Management, 2016, 184: 36-44. [117] RODRIGUEZ-GALIANO V, MENDES M P, GARCIA-SOLDADO M J, et al. Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (southern Spain) [J]. Science of The Total Environment, 2014, 476-477: 189-206. [118] JIA X, HOU D. Mapping soil arsenic pollution at a brownfield site using satellite hyperspectral imagery and machine learning[J]. Science of The Total Environment, 2023, 857: 159387. [119] SONG X, REN H, HOU Z, et al. Predicting future well performance for environmental remediation design using deep learning[J]. Journal of Hydrology, 2023, 617: 129110. [120] LI X, YI S, CUNDY A B, et al. Sustainable decision-making for contaminated site risk management: a decision tree model using machine learning algorithms[J]. Journal of Cleaner Production, 2022, 371: 133612. [121] NAYAK P C, VENKATESH B, KRISHNA B, et al. Rainfall-runoff modeling using conceptual, data driven, and wavelet based computing approach[J]. Journal of Hydrology, 2013, 493: 57-67. [122] REN J, LIU Y, CAO W, et al. A process-based model for describing redox kinetics of Cr(VI) in natural sediments containing variable reactive Fe(II) species[J]. Water Research, 2022, 225: 119126. [123] 曹引. 湖库水质遥感和水动力水质模型数据同化理论方法研究[D]. 上海: 东华大学, 2019: 2-7. [124] KERKEZ B, GLASER S D, BALES R C, et al. Design and performance of a wireless sensor network for catchment-scale snow and soil moisture measurements[J]. Water Resources Research, 2012, 48(9): W09515. [125] GASPERIKOVA E, HUBBARD S S, WATSON D B, et al. Long-term electrical resistivity monitoring of recharge-induced contaminant plume behavior[J]. Journal of Contaminant Hydrology, 2012, 142: 33-49. [126] YASEEN Z M, JAAFAR O, DEO R C, et al. Stream-flow forecasting using extreme learning machines: a case study in a semi-arid region in Iraq[J]. Journal of Hydrology, 2016, 542: 603-614. [127] SHEN L Q, AMATULLI G, SETHI T, et al. Estimating nitrogen and phosphorus concentrations in streams and rivers, within a machine learning framework[J]. Science Data, 2020, 7(1): 161. [128] JIA X, O’CONNOR D, SHI Z, et al. VIRS based detection in combination with machine learning for mapping soil pollution[J]. Environmental Pollution, 2021, 268: 115845. [129] BU J, LI C, WANG X, et al. Assessment and prediction of the water ecological carrying capacity in Changzhou city, China[J]. Journal of Cleaner Production, 2020, 277: 123988. [130] DAS D, SINGAPURI C, DWIVEDI A. Experimental determination of buoyancy induced convection heat transfer characteristics in a rectangular cavity with cylindrical porous medium fixed between pin fins[J]. Heat Mass Transfer, 2020, 56(4): 1293-1306. [131] TSILINGIRIS P T. Thermophysical and transport properties of humid air at temperature range between 0 and 100°C[J]. Energy Conversion and Management, 2008, 49(5): 1098-1110. [132] WU R, CHEN X, HAMMOND G, et al. Coupling surface flow with high-performance subsurface reactive flow and transport code PFLOTRAN[J]. Environmental Modelling & Software, 2021, 137: 104959. [133] MILLS R T, LU C, LICHTNER P C, et al. Simulating subsurface flow and transport on ultrascale computers using PFLOTRAN[J]. Journal of Physics: Conference Series, 2007, 78: 012051. [134] HUANG K, LIU Y Y, YANG C, et al. Identification of hydrobiogeochemical processes controlling seasonal variations in arsenic concentrations within a riverbank aquifer at Jianghan Plain, China[J]. Water Resources Research, 2018, 54(7): 4294-4308. [135] YANG C, ZHANG Y K, LIU Y Y, et al. Model-based analysis of the effects of dam-induced river water and groundwater interactions on hydro-biogeochemical transformation of redox sensitive contaminants in a hyporheic zone[J]. Water Resources Research, 2018, 54(9): 5973-5985. [136] SUN A Y, SCANLON B R. How can big data and machine learning benefit environment and water management: a survey of methods, applications, and future directions[J]. Environmental Research Letters, 2019, 14(7): 073001. [137] LI P J, ZHA Y Y, SHI L S, et al. Comparison of the use of a physical-based model with data assimilation and machine learning methods for simulating soil water dynamics[J]. Journal of Hydrology, 2020, 584: 124692. [138] TIKHAMARINE Y, SOUAG-GAMANE D, NAJAH AHMED A, et al. Improving artificial intelligence models accuracy for monthly streamflow forecasting using grey wolf optimization (GWO) algorithm[J]. Journal of Hydrology, 2020, 582: 124435. [139] CHEN G, LI S, KNIBBS L D, et al. A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information[J]. Science of The Total Environment, 2018, 636: 52-60. [140] YASEEN Z M, EL-SHAFIE A, JAAFAR O, et al. Artificial intelligence based models for stream-flow forecasting: 2000-2015[J]. Journal of Hydrology, 2015, 530: 829-844. [141] PINEDA F J. Generalization of back-propagation to recurrent neural networks[J]. Physical review letters, 1987, 59(19): 2229-2232. [142] PALANI S, LIONG S Y, TKALICH P. An ANN application for water quality forecasting[J]. Marine Pollution Bulletin, 2008, 56(9): 1586-1597. [143] KARSOLIYA S, AZAD M A K. Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture[C]. International Journal of Engineering Trends and Technology, 2012, 3(6):714-717. [144] SACHANIYA B K, GOSAI H B, PANSERIYA H Z, et al. Bioengineering for multiple PAHs degradation for contaminated sediments: response surface methodology (RSM) and artificial neural network (ANN)[J]. Chemometrics and Intelligent Laboratory Systems, 2020, 202: 104033. [145] 周志华. 机器学习[M]. 北京：清华大学出版社, 2016. [146] NAGHIBI S A, AHMADI K, DANESHI A. Application of support vector machine, random forest, and genetic algorithm optimized random forest models in groundwater potential mapping [J]. Water Resources Management, 2017, 31(9): 2761-2775. [147] CATTANI G. Combining data envelopment analysis and random forest for selecting optimal locations of solar PV plants[J]. Energy and AI, 2023, 11: 100222. [148] DAI L, GE J, WANG L, et al. Influence of soil properties, topography, and land cover on soil organic carbon and total nitrogen concentration: a case study in Qinghai-Tibet plateau based on random forest regression and structural equation modeling[J]. Science of The Total Environment, 2022, 821: 153440. [149] HARRISON J W, LUCIUS M A, FARRELL J L, et al. Prediction of stream nitrogen and phosphorus concentrations from high-frequency sensors using random forests regression[J]. Science of The Total Environment, 2021, 763: 143005. [150] LI B, YANG G, WAN R, et al. Combining multivariate statistical techniques and random forests model to assess and diagnose the trophic status of Poyang lake in China[J]. Ecological Indicators, 2017, 83: 74-83. [151] HE S, WU J, WANG D, et al. Predictive modeling of groundwater nitrate pollution and evaluating its main impact factors using random forest[J]. Chemosphere, 2022, 290: 133388. [152] GUO B, ZHANG D, PEI L, et al. Estimating PM2.5 concentrations via random forest method using satellite, auxiliary, and ground-level station dataset at multiple temporal scales across China in 2017[J]. Science of The Total Environment, 2021, 778: 146288. [153] SUTTON C D. 11-Classification and regression trees, bagging, and boosting[M]. Handbook of Statistics. Elsevier. 2005: 303-329. [154] WERE K, BUI D T, DICK Ø B, et al. A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an afromontane landscape[J]. Ecological Indicators, 2015, 52: 394-403. [155] KRUPPA J, SCHWARZ A, ARMINGER G, et al. Consumer credit risk: Individual probability estimates using machine learning[J]. Expert Systems with Applications, 2013, 40(13): 5125-5131. [156] 吴浩楠. 超参数自动调优算法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020: 6-13. [157] KARUNASINGHA D S K. Root mean square error or mean absolute error? use their ratio as well[J]. Information Sciences, 2022, 585: 609-629. [158] COLIN CAMERON A, WINDMEIJER F A G. An R-squared measure of goodness of fit for some common nonlinear regression models[J]. Journal of Econometrics, 1997, 77(2): 329-342. [159] NASH J E, SUTCLIFFE J V. River flow forecasting through conceptual models part I-a discussion of principles[J]. Journal of Hydrology, 1970, 10(3): 282-290. [160] PRADHAN P, TINGSANCHALI T, SHRESTHA S. Evaluation of soil and water assessment tool and artificial neural network models for hydrologic simulation in different climatic regions of Asia[J]. Science of The Total Environment, 2020, 701: 134308. [161] BEHRANGI A, KHAKBAZ B, VRUGT J A, et al. Comment on "dynamically dimensioned search algorithm for computationally efficient watershed model calibration" by Bryan A. Tolson and Christine A. Shoemaker[J]. Water Resources Research, 2008, 44(12): W12603. [162] DUAN Q, SOROOSHIAN S, GUPTA V. Effective and efficient global optimization for conceptual rainfall-runoff models[J]. 1992, 28(4): 1015-1031. [163] NELDER J A, MEAD R J C J. A simplex method for function minimization[J]. 1965, 7: 308-313. [164] DUAN Q Y, SOROOSHIAN S, GUPTA V K. Optimal use of the SCE-UA global optimization method for calibrating watershed models[J]. Journal of Hydrology, 1994, 158(3-4): 265-284. [165] VRUGT J A, GUPTA H V, BOUTEN W, et al. A shuffled complex evolution metropolis algorithm for optimization and uncertainty assessment of hydrologic model parameters[J]. Water Resources Research, 2003, 39(8):1201. [166] QI W, ZHANG C, FU G T, et al. Quantifying dynamic sensitivity of optimization algorithm parameters to improve hydrological model calibration[J]. Journal of Hydrology, 2016, 533: 213-223. [167] 邓元倩, 李致家, 刘甲奇, 等. 基于SCE-UA算法新安江模型在沣河流域的应用[J]. 水资源与水工程学报, 2017, 28: 27-31. [168] YU K, DUAN Y, LIAO P, et al. Watershed-scale distributions of heavy metals in the hyporheic zones of a heavily polluted Maozhou River watershed, southern China[J]. Chemosphere, 2020, 239: 124773. [169] 赵迪. 茅洲河水质评价与水体污染防治综合措施研究[D]. 邯郸: 河北工程大学, 2017: 30-38. [170] 中华人民共和国生态环境部. 地表水环境质量标准（GB3838-2002）[S]. 北京: 生态环境部, 2002. [171] AKAN A O. Open channel hydraulics (second edition) [M]. Butterworth-Heinemann. Elsevier, 2021: 1-25. [172] ZHANG D, WANG J J, NI H G, et al. Spatial-temporal and multi-media variations of polycyclic aromatic hydrocarbons in a highly urbanized river from South China [J]. Science of The Total Environment, 2017, 581-582: 621-628. [173] 陈世勇. 基于控制单元划分的茅洲河流域水环境现状分析与水质预测研究 [D]. 深圳: 深圳大学, 2016: 19-23. [174] DHI, MIKE 11: A modeling system for rivers and channels, user guide[Z]. Danish Hydraulic Institute, Denmark, 2012. [175] CAMPS-VALLS G, MARTINO L, SVENDSEN D H, et al. Physics-aware gaussian processes in remote sensing[J]. Applied Soft Computing, 2018, 68: 69-82. [176] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. [177] CUI K, JING X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing and Applications, 2019, 31(12): 8205-8215. [178] KRAUSE P, BOYLE D P, BäSE F. Comparison of different efficiency criteria for hydrological model assessment[J]. Advances in Geosciences, 2005, 5: 89-97. [179] MORIASI D N, ARNOLD J G, VAN LIEW M W, et al. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations[J]. Transactions of the ASABE (American Society of Agricultural and Biological Engineers), 2007, 50(3): 885-900. [180] ZHANG W, KUMAR M, LIU J. Multi-parameter online measurement IoT system based on BP neural network algorithm[J]. Neural Computing and Applications, 2019, 31(12): 8147-8155. [181] ZHANG Y, SHAO Q. Uncertainty and its propagation estimation for an integrated water system model: an experiment from water quantity to quality simulations[J]. Journal of Hydrology, 2018, 565: 623-635. [182] YAN R, GAO Y, LI L, et al. Estimation of water environmental capacity and pollution load reduction for urban lakeside of lake Taihu, eastern China[J]. Ecological Engineering, 2019, 139: 105587. [183] LI Y, QIU R, YANG Z, et al. Parameter determination to calculate water environmental capacity in Zhangweinan canal sub-basin in China[J]. Journal of Environmental Sciences, 2010, 22(6): 904-907. [184] CHEN R, TENG Y, CHEN H, et al. A coupled optimization of groundwater remediation alternatives screening under health risk assessment: an application to a petroleum-contaminated site in a typical cold industrial region in northeastern China[J]. Journal of Hazardous Materials, 2021, 407: 124796. [185] LI X, JIAO W, XIAO R, et al. Contaminated sites in China: countermeasures of provincial governments[J]. Journal of Cleaner Production, 2017, 147: 485-496. [186] 李书鹏, 焦文涛, 李鸿炫, 等. 燃气热脱附技术修复有机污染场地研究与应用进展[J]. 环境工程学报, 2019, 13: 2037-2048. [187] 刘家巍. 原位热传导修复有机污染土壤温度场模拟研究[D]. 杭州: 浙江大学, 2021: 20-21. [188] ZHAO C, MUMFORD K G, KUEPER B H. Laboratory study of non-aqueous phase liquid and water co-boiling during thermal treatment[J]. Journal of Contaminant Hydrology, 2014, 164: 49-58. [189] HERON G, PARKER K, FOURNIER S, et al. World's largest in situ thermal desorption project: challenges and solutions[J]. Groundwater Monitoring & Remediation, 2015, 35(3): 89-100. [190] TAN J W, DUAN Q Y, GONG W, et al. Differences in parameter estimates derived from various methods for the ORYZA (v3) Model[J]. Journal of Integrative Agriculture, 2022, 21(2): 375-388. [191] JOSEPH T, DUBEY B, MCBEAN E A. Human health risk assessment from arsenic exposures in Bangladesh[J]. Science of The Total Environment, 2015, 527: 552-560. [192] COZZARELLI I M, SCHREIBER M E, ERICKSON M L, et al. Arsenic cycling in hydrocarbon plumes: secondary effects of natural attenuation[J]. Groundwater, 2016, 54(1): 35-45. [193] LIU Y Y, XU F, LIU C X. Coupled hydro-biogeochemical processes controlling Cr reductive immobilization in Columbia river hyporheic zone[J]. Environmental Science & Technology, 2017, 51(3): 1508-1517. [194] HE J, YANG K, TANG W J, et al. The first high-resolution meteorological forcing dataset for land process studies over China[J]. Science Data, 2020, 7: 25. [195] 张怡然, 李晨, 张建柱, 等. 《生活饮用水卫生标准》（GB 5749-2022）解析[J] 供水技术. 2022, 16(05): 38-43. [196] 中华人民共和国生态环境部. 土壤环境质量建设用地土壤污染风险管控标准（试行）（GB36600-2018）[S]. 北京: 生态环境部, 2018. [197] RAHMATI O, CHOUBIN B, FATHABADI A, et al. Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods[J]. Science of The Total Environment, 2019, 688: 855-866. [198] HUAN J, LI H, LI M B, et al. Prediction of dissolved oxygen in aquaculture based on gradient boosting decision tree and long short-term memory network: A study of Chang Zhou fishery demonstration base, China[J]. Computers and Electronics in Agriculture, 2020, 175: 105530. [199] ZHANG L, REN T, YU Y, et al. Optimization of environmental variable functions of GPP quantitative model based on SCE-UA and minimum loss screening method[J]. Ecological Informatics, 2021, 66: 101479.
所在学位评定分委会	资源与环境
国内图书分类号	X52/X53
来源库	人工提交
成果类型	学位论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/543799
专题	工学院_环境科学与工程学院
推荐引用方式 GB/T 7714	王欣. 基于机器学习与过程模型的水环境容量估算与土壤修复研究[D]. 哈尔滨. 哈尔滨工业大学,2023.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可	操作
11849583-王欣-环境科学与工程学（6782KB）	--	--	限制开放	--	请求全文