首页 > 最新文献

Stochastic Environmental Research and Risk Assessment最新文献

英文 中文
Traffic flows time series in a flood-prone area: modeling and clustering on extreme values with a spatial constraint 洪水易发地区的交通流时间序列:带有空间约束的极端值建模与聚类
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-06-25 DOI: 10.1007/s00477-024-02735-x
Maurizio Carpita, Giovanni De Luca, Rodolfo Metulini, Paola Zuccolotto

Time series of traffic flows, extracted from mobile phone origin–destination data, are employed for monitoring people crowding and mobility in areas subject to flooding risk. By applying a vector autoregressive model with exogenous covariates combined with dynamic harmonic regression to such time series, we detected the presence of many extreme events in the residuals, which exhibit heavy-tailed distribution. For this reason, we propose a time series clustering procedure based on tail dependence which is suitable for data characterized by a spatial dimension, since objects’ geographical proximity is taken into account. The final aim is to obtain clusters of areas characterized by the common tendency to the manifestation of extreme events, that in this case study are represented by extremely high incoming traffic flows. The proposed method is applied to the Mandolossa, a strongly urbanized area located on the western outskirts of Brescia (northern Italy) which is subject to frequent flooding.

从手机出发地-目的地数据中提取的交通流时间序列被用于监测洪水风险地区的人员拥挤和流动情况。通过将带有外生协变量的矢量自回归模型与动态谐波回归相结合应用于此类时间序列,我们发现残差中存在许多极端事件,它们呈现重尾分布。因此,我们提出了一种基于尾部依赖性的时间序列聚类程序,该程序适用于具有空间维度特征的数据,因为其中考虑到了对象的地理邻近性。最终目的是获得以极端事件的共同趋势为特征的区域聚类,在本案例研究中,极端事件表现为极高的入境交通流量。所提出的方法适用于 Mandolossa 地区,该地区位于布雷西亚(意大利北部)西郊,城市化程度较高,经常遭受洪水侵袭。
{"title":"Traffic flows time series in a flood-prone area: modeling and clustering on extreme values with a spatial constraint","authors":"Maurizio Carpita, Giovanni De Luca, Rodolfo Metulini, Paola Zuccolotto","doi":"10.1007/s00477-024-02735-x","DOIUrl":"https://doi.org/10.1007/s00477-024-02735-x","url":null,"abstract":"<p>Time series of traffic flows, extracted from mobile phone origin–destination data, are employed for monitoring people crowding and mobility in areas subject to flooding risk. By applying a vector autoregressive model with exogenous covariates combined with dynamic harmonic regression to such time series, we detected the presence of many extreme events in the residuals, which exhibit heavy-tailed distribution. For this reason, we propose a time series clustering procedure based on tail dependence which is suitable for data characterized by a spatial dimension, since objects’ geographical proximity is taken into account. The final aim is to obtain clusters of areas characterized by the common tendency to the manifestation of extreme events, that in this case study are represented by extremely high incoming traffic flows. The proposed method is applied to the Mandolossa, a strongly urbanized area located on the western outskirts of Brescia (northern Italy) which is subject to frequent flooding.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"42 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Identification of groundwater pollution sources based on optimal layout of groundwater pollution monitoring network 基于地下水污染监测网络优化布局的地下水污染源识别
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-06-19 DOI: 10.1007/s00477-024-02756-6
Xi Ma, Jiannan Luo, Xueli Li, Zhuo Song

The accuracy of pollution source identification significantly depends on the amount of effective information derived from monitoring data. Currently, most of the comprehensive studies on groundwater contamination source identification and optimal design of monitoring solutions are based on hypothetical cases, whereas relevant studies on actual cases only consider one characteristic of the pollution source (either locations or fluxes). An optimal monitoring network (OMN)-based pollution source characterisation framework that takes source locations and source fluxes into account is presented to enhance the accuracy of pollution source identification. The genetic algorithm (GA) and particle swarm optimization (PSO) were used to solve the optimization model of pollution source characteristics identification. The framework is applied to a landfill for waste located in Baicheng City, China. The results showed that the identification results based on OMN has a smaller mean relative error and higher accuracy, compared with those based on random monitoring network (RMN). This study shows that OMNs can provide more effective information for pollution source identification and effectively enhance the accuracy of the groundwater sources characteristics identification.

污染源识别的准确性在很大程度上取决于从监测数据中获得的有效信息量。目前,有关地下水污染源识别和监测方案优化设计的综合研究大多基于假设案例,而针对实际案例的相关研究只考虑了污染源的一个特征(位置或通量)。为了提高污染源识别的准确性,本文提出了一个基于优化监测网络(OMN)的污染源特征描述框架,将污染源位置和污染源通量都考虑在内。遗传算法(GA)和粒子群优化(PSO)被用于解决污染源特征识别的优化模型。该框架应用于中国白城市的垃圾填埋场。结果表明,与基于随机监测网(RMN)的识别结果相比,基于 OMN 的识别结果具有更小的平均相对误差和更高的精度。该研究表明,OMN 可为污染源识别提供更有效的信息,有效提高地下水源特征识别的准确性。
{"title":"Identification of groundwater pollution sources based on optimal layout of groundwater pollution monitoring network","authors":"Xi Ma, Jiannan Luo, Xueli Li, Zhuo Song","doi":"10.1007/s00477-024-02756-6","DOIUrl":"https://doi.org/10.1007/s00477-024-02756-6","url":null,"abstract":"<p>The accuracy of pollution source identification significantly depends on the amount of effective information derived from monitoring data. Currently, most of the comprehensive studies on groundwater contamination source identification and optimal design of monitoring solutions are based on hypothetical cases, whereas relevant studies on actual cases only consider one characteristic of the pollution source (either locations or fluxes). An optimal monitoring network (OMN)-based pollution source characterisation framework that takes source locations and source fluxes into account is presented to enhance the accuracy of pollution source identification. The genetic algorithm (GA) and particle swarm optimization (PSO) were used to solve the optimization model of pollution source characteristics identification. The framework is applied to a landfill for waste located in Baicheng City, China. The results showed that the identification results based on OMN has a smaller mean relative error and higher accuracy, compared with those based on random monitoring network (RMN). This study shows that OMNs can provide more effective information for pollution source identification and effectively enhance the accuracy of the groundwater sources characteristics identification.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"26 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Improving future drought predictions – a novel multi-method framework based on mutual information for subset selection and spatial aggregation of global climate models of precipitation 改进未来干旱预测--基于互信息的新型多方法框架,用于子集选择和降水量全球气候模型的空间聚合
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-06-04 DOI: 10.1007/s00477-024-02746-8
Muhammad Shakeel, Zulfiqar Ali

Selecting appropriate Global Climate Models (GCMs) presents a significant challenge for accurate climate projections. To address this, a novel framework based on information theory based minimum redundancy and maximum relevancy (MRMR) method identifies top-performing GCMs across the entire study region using multicriteria decision analysis methodology. A subset of the ten best-performing models out of twenty-two GCMs is chosen for multi-model ensemble analysis. Five MME methods are selected to assess the ensemble performance of the ten selected GCMs, categorized into simple, regression-based, geometric-based, and machine learning ensembles. This study evaluates the effectiveness of the MME method based on a comprehensive index called the extended distance between indices of simulation and observation. An Adaptive Multimodel Standardized Drought Index (AMSDI) has been developed based on the optimal MME method. For the application of the framework and the proposed index, historical precipitation data from 1950 to 2014 were utilized from 28 grid points in the Punjab province of Pakistan as the reference dataset. Additionally, simulations from 22 models of the Coupled Model Intercomparison Project phase 6, both past and future, were employed for the estimation procedure. In AMSDI indicator, we used improved multimodel ensemble of precipitation for future drought characterization under various future scenarios. Outcome associated with this research show that AMSDI effectively have ability to effectively identifiy extreme drought events for all three future scenarios. In conclusion, the AMSDI method is shown to be effective and flexible, improving accuracy in monitoring droughts.

选择合适的全球气候模型(GCMs)对准确的气候预测是一项重大挑战。为解决这一问题,基于信息论的最小冗余和最大相关性(MRMR)方法建立了一个新框架,利用多标准决策分析方法确定整个研究区域表现最佳的全球气候模型。从 22 个 GCM 中选出 10 个表现最佳的模型子集进行多模型集合分析。选择了五种 MME 方法来评估所选十个 GCM 的集合性能,分为简单集合、回归集合、几何集合和机器学习集合。本研究根据模拟指数与观测指数之间的扩展距离这一综合指数来评估 MME 方法的有效性。基于最优 MME 方法,开发了自适应多模型标准化干旱指数(AMSDI)。在应用该框架和拟议指数时,使用了巴基斯坦旁遮普省 28 个网格点 1950 年至 2014 年的历史降水数据作为参考数据集。此外,在估算过程中还采用了耦合模式相互比较项目第 6 阶段的 22 个模式的过去和未来模拟。在 AMSDI 指标中,我们使用了改进的多模型降水量集合,用于描述各种未来情景下的未来干旱特征。研究结果表明,AMSDI 能够有效识别三种未来情景下的极端干旱事件。总之,AMSDI 方法有效而灵活,提高了干旱监测的准确性。
{"title":"Improving future drought predictions – a novel multi-method framework based on mutual information for subset selection and spatial aggregation of global climate models of precipitation","authors":"Muhammad Shakeel, Zulfiqar Ali","doi":"10.1007/s00477-024-02746-8","DOIUrl":"https://doi.org/10.1007/s00477-024-02746-8","url":null,"abstract":"<p>Selecting appropriate Global Climate Models (GCMs) presents a significant challenge for accurate climate projections. To address this, a novel framework based on information theory based minimum redundancy and maximum relevancy (MRMR) method identifies top-performing GCMs across the entire study region using multicriteria decision analysis methodology. A subset of the ten best-performing models out of twenty-two GCMs is chosen for multi-model ensemble analysis. Five MME methods are selected to assess the ensemble performance of the ten selected GCMs, categorized into simple, regression-based, geometric-based, and machine learning ensembles. This study evaluates the effectiveness of the MME method based on a comprehensive index called the extended distance between indices of simulation and observation. An Adaptive Multimodel Standardized Drought Index (AMSDI) has been developed based on the optimal MME method. For the application of the framework and the proposed index, historical precipitation data from 1950 to 2014 were utilized from 28 grid points in the Punjab province of Pakistan as the reference dataset. Additionally, simulations from 22 models of the Coupled Model Intercomparison Project phase 6, both past and future, were employed for the estimation procedure. In AMSDI indicator, we used improved multimodel ensemble of precipitation for future drought characterization under various future scenarios. Outcome associated with this research show that AMSDI effectively have ability to effectively identifiy extreme drought events for all three future scenarios. In conclusion, the AMSDI method is shown to be effective and flexible, improving accuracy in monitoring droughts.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"44 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141254449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Temporal and spatial distribution of extreme rainfall from tropical storms in the Gulf of Mexico from 1979 to 2021 1979 年至 2021 年墨西哥湾热带风暴极端降雨量的时空分布情况
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-28 DOI: 10.1007/s00477-024-02742-y
Jae Yeol Song, Eun-Sung Chung

Atlantic tropical cyclones often associate with heavy rainfall, which causes inland- and coastal-flooding in the United States, and the storm-induced rainfall is closely related to its storm scale, movement, and location. For a better performance in flood or risk analysis in a region, understanding the characteristics and distribution of tropical storm (TS) induced extreme rainfall is essential. This study proposes dimensionless rainfall-duration curves for designated four-quartile storms that represents the temporal distribution of TS induced extreme rainfall in the Gulf of Mexico from 1979 to 2021. Our study employs spatiotemporal analysis to compute rainfall while TSs are located overseas and inland from satellite based climate forcing data and hurricane track records, annual maximum approach to define TS induced extreme rainfall events, and designated track types to categorize events based on their trajectories. As a result, extreme rainfall relating to TSs in the Gulf of Mexico are found to be considerably higher in inland than overseas. For inland, majority of the TSs was found to be the 1st- and 2nd-quartile storms. However, the 3rd-quartile storms, which case are rare, were found to have the overall largest amount of rainfall per duration compared to the other quartile storms. As for overseas, more than half of the TSs were found to be the 4th-quartile storm while the 2nd-quartile storm has higher overall rainfall per duration. Spatial analysis shows that Texas, Louisiana, Mississippi, Florida, and South Carolina are determined as high-threatened areas by TS induced extreme rainfall.

大西洋热带气旋经常伴有强降雨,导致美国内陆和沿海地区洪水泛滥,而风暴引起的降雨与其风暴规模、移动和位置密切相关。为了更好地进行区域洪水或风险分析,了解热带风暴(TS)诱发的极端降雨的特征和分布至关重要。本研究为指定的四分位数风暴提出了无量纲降雨持续时间曲线,该曲线代表了 1979 年至 2021 年墨西哥湾由热带风暴引起的极端降雨的时间分布。我们的研究采用了时空分析方法,根据卫星气候强迫数据和飓风路径记录计算 TS 位于海外和内陆时的降雨量,采用年度最大值方法定义 TS 引发的极端降雨事件,并采用指定的路径类型根据其轨迹对事件进行分类。结果发现,与墨西哥湾 TS 有关的极端降雨量,内陆地区要比海外地区高得多。在内陆地区,大部分 TS 都是第 1 和第 2 四分位数风暴。然而,与其他四分位数的暴雨相比,第三四分位数的暴雨虽然罕见,但每次持续时间的降雨量却是最大的。在海外,超过一半的 TS 为第 4 四分位数暴雨,而第 2 四分位数暴雨的单位时间总降雨量更高。空间分析表明,得克萨斯州、路易斯安那州、密西西比州、佛罗里达州和南卡罗来纳州被确定为受 TS 引发的极端降雨威胁较大的地区。
{"title":"Temporal and spatial distribution of extreme rainfall from tropical storms in the Gulf of Mexico from 1979 to 2021","authors":"Jae Yeol Song, Eun-Sung Chung","doi":"10.1007/s00477-024-02742-y","DOIUrl":"https://doi.org/10.1007/s00477-024-02742-y","url":null,"abstract":"<p>Atlantic tropical cyclones often associate with heavy rainfall, which causes inland- and coastal-flooding in the United States, and the storm-induced rainfall is closely related to its storm scale, movement, and location. For a better performance in flood or risk analysis in a region, understanding the characteristics and distribution of tropical storm (TS) induced extreme rainfall is essential. This study proposes dimensionless rainfall-duration curves for designated four-quartile storms that represents the temporal distribution of TS induced extreme rainfall in the Gulf of Mexico from 1979 to 2021. Our study employs spatiotemporal analysis to compute rainfall while TSs are located overseas and inland from satellite based climate forcing data and hurricane track records, annual maximum approach to define TS induced extreme rainfall events, and designated track types to categorize events based on their trajectories. As a result, extreme rainfall relating to TSs in the Gulf of Mexico are found to be considerably higher in inland than overseas. For inland, majority of the TSs was found to be the 1st- and 2nd-quartile storms. However, the 3rd-quartile storms, which case are rare, were found to have the overall largest amount of rainfall per duration compared to the other quartile storms. As for overseas, more than half of the TSs were found to be the 4th-quartile storm while the 2nd-quartile storm has higher overall rainfall per duration. Spatial analysis shows that Texas, Louisiana, Mississippi, Florida, and South Carolina are determined as high-threatened areas by TS induced extreme rainfall.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"35 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141167862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Monte Carlo simulation of source-specific risks of soil at an abandoned lead-acid battery recycling site 废弃铅酸蓄电池回收场土壤特定来源风险的蒙特卡洛模拟
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-27 DOI: 10.1007/s00477-024-02747-7
Andrijana Miletić, Jelena Vesković, Milica Lučić, Antonije Onjia

Anthropogenic activities predominantly affect environmental Pb pollution, especially during waste lead-acid battery (LAB) recycling operations. In this study, the presence of Pb and nine other potentially toxic elements (PTEs) in the soil at an abandoned LAB recycling site was investigated. The focus was on spatial and vertical distributions and potential health issues related to PTEs. Average concentrations of Cd, As, Hg, Pb, Al, Zn, Cu, and Sb were elevated at all investigated soil depths, whereas the concentrations of Zn, Cu, and Sb were significant only on the soil surface. Positive matrix factorization, correlation and cluster analyses, as well as self-organizing maps, identified four primary pollution sources: recycling activities (Cd, Hg, Pb, and Sb), mixed anthropogenic sources (Zn and Cu), the soil parent material (As, Cr, and Ni), and surface runoff combined with sand application (Al and pH). While the non-carcinogenic risk results revealed a negligible risk for adults, the hazard index (HI) values for children were greater than one in 26% of the samples. For adults and children, the total carcinogenic risk (TCR) values were acceptable for 98% and 94% of the samples, respectively. Geospatial analysis identified the main hotspot in the battery disposal area. Source-specific non-carcinogenic and carcinogenic risks were most influenced by recycling activities. Monte Carlo simulation (MCS) of total HI for children showed that the risk value exceeded the threshold level (HI > 1) at the 10th percentile, whereas the maximum value of total HI for adults was 0.2. Regarding carcinogenic risk, the TCR values at the 95th percentile of all four sources for adults and children were below the limit value (1 × 10−4), indicating a low probability of cancer development.

人类活动主要影响环境铅污染,尤其是在废弃铅酸蓄电池(LAB)回收作业期间。本研究调查了铅和其他九种潜在有毒元素(PTEs)在废弃铅酸蓄电池回收场地土壤中的存在情况。重点是空间和垂直分布以及与 PTEs 相关的潜在健康问题。镉、砷、汞、铅、铝、锌、铜和锑的平均浓度在所有调查的土壤深度都有所升高,而锌、铜和锑的浓度仅在土壤表层显著。正矩阵因式分解、相关性和聚类分析以及自组织图确定了四个主要污染源:回收活动(镉、汞、铅和锑)、混合人为污染源(锌和铜)、土壤母质(砷、铬和镍)以及地表径流和施沙(铝和 pH 值)。非致癌风险结果显示,成人的风险可以忽略不计,但在 26% 的样本中,儿童的危害指数 (HI) 值大于 1。对于成人和儿童来说,分别有 98% 和 94% 的样本的总致癌风险 (TCR) 值是可以接受的。地理空间分析确定了电池弃置区的主要热点。特定来源的非致癌风险和致癌风险受回收活动的影响最大。儿童总 HI 的蒙特卡罗模拟(MCS)显示,风险值在第 10 百分位数时超过了阈值水平(HI > 1),而成人总 HI 的最大值为 0.2。在致癌风险方面,成人和儿童所有四个来源的第 95 百分位数的 TCR 值均低于极限值(1 × 10-4),表明癌症发生的概率较低。
{"title":"Monte Carlo simulation of source-specific risks of soil at an abandoned lead-acid battery recycling site","authors":"Andrijana Miletić, Jelena Vesković, Milica Lučić, Antonije Onjia","doi":"10.1007/s00477-024-02747-7","DOIUrl":"https://doi.org/10.1007/s00477-024-02747-7","url":null,"abstract":"<p>Anthropogenic activities predominantly affect environmental Pb pollution, especially during waste lead-acid battery (LAB) recycling operations. In this study, the presence of Pb and nine other potentially toxic elements (PTEs) in the soil at an abandoned LAB recycling site was investigated. The focus was on spatial and vertical distributions and potential health issues related to PTEs. Average concentrations of Cd, As, Hg, Pb, Al, Zn, Cu, and Sb were elevated at all investigated soil depths, whereas the concentrations of Zn, Cu, and Sb were significant only on the soil surface. Positive matrix factorization, correlation and cluster analyses, as well as self-organizing maps, identified four primary pollution sources: recycling activities (Cd, Hg, Pb, and Sb), mixed anthropogenic sources (Zn and Cu), the soil parent material (As, Cr, and Ni), and surface runoff combined with sand application (Al and pH). While the non-carcinogenic risk results revealed a negligible risk for adults, the hazard index (HI) values for children were greater than one in 26% of the samples. For adults and children, the total carcinogenic risk (TCR) values were acceptable for 98% and 94% of the samples, respectively. Geospatial analysis identified the main hotspot in the battery disposal area. Source-specific non-carcinogenic and carcinogenic risks were most influenced by recycling activities. Monte Carlo simulation (MCS) of total HI for children showed that the risk value exceeded the threshold level (HI &gt; 1) at the 10th percentile, whereas the maximum value of total HI for adults was 0.2. Regarding carcinogenic risk, the TCR values at the 95th percentile of all four sources for adults and children were below the limit value (1 × 10<sup>−4</sup>), indicating a low probability of cancer development.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"91 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141173322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Risk assessment of river water quality using long-memory processes subject to divergence or Wasserstein uncertainty 利用受分歧或瓦瑟施泰因不确定性影响的长记忆过程对河流水质进行风险评估
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-18 DOI: 10.1007/s00477-024-02726-y
Hidekazu Yoshioka, Yumi Yoshioka

River water quality often follows a long-memory stochastic process with power-type autocorrelation decay, which can only be reproduced using appropriate mathematical models. The selection of a stochastic process model, particularly its memory structure, is often subject to misspecifications owing to low data quality and quantity. Therefore, environmental risk assessment should account for model misspecification through mathematically rigorous and efficiently implementable approaches; however, such approaches have been still rare. We address this issue by first modeling water quality dynamics through the superposition of an affine diffusion process that is stationary and has a long memory. Second, the worst-case upper deviation of the water quality value from a prescribed threshold value under model misspecifications is evaluated using either the divergence risk or Wasserstein risk measure. The divergence risk measure can consistently deal with the misspecification of the memory structure to the worst-case upper deviation. The Wasserstein risk measure is more flexible but fails in this regard, as it does not directly consider the memory structure information. We theoretically compare both approaches to demonstrate that their assumed uncertainties differed substantially. From the application to the 30-year water quality data of a river in Japan, we categorized the water quality indices to be those with truly long memory (Total nitrogen, NO3-N, NH4-N, and ({{text{SO}}}_{4}^{2-})), those with moderate power-type memory (NO2-N, PO4-P, and Total Organic Carbon), and those with almost exponential memory (Total phosphorus and Chemical Oxygen demand). The risk measures are successfully computed numerically considering the seasonal variations of the water quality indices.

河流水质通常遵循一个具有幂型自相关衰减的长记忆随机过程,只有使用适当的数学模型才能再现这一过程。由于数据的质量和数量较低,随机过程模型的选择,特别是其记忆结构,往往会受到错误规范的影响。因此,环境风险评估应通过数学上严谨且可有效实施的方法来考虑模型的错误指定;然而,这种方法仍然很少见。为了解决这一问题,我们首先通过对静止且具有长记忆的仿射扩散过程进行叠加来建立水质动态模型。其次,我们使用发散风险或瓦瑟施泰因风险度量法来评估在模型失当的情况下水质值与规定阈值的最坏上限偏差。发散风险度量可以持续地处理记忆结构的错误配置,以达到最坏情况下的上限偏差。瓦瑟斯坦风险度量法更为灵活,但在这方面却失效了,因为它没有直接考虑记忆结构信息。我们从理论上对这两种方法进行了比较,以证明其假定的不确定性存在很大差异。通过对日本某河流 30 年水质数据的应用,我们将水质指数分为真正的长记忆指数(总氮、NO3-N、NH4-N 和 ({text{SO}}}_{4}^{2-})、中等幂型记忆指数(NO2-N、PO4-P 和总有机碳)以及几乎指数记忆指数(总磷和化学需氧量)。考虑到水质指数的季节性变化,风险度量成功地进行了数值计算。
{"title":"Risk assessment of river water quality using long-memory processes subject to divergence or Wasserstein uncertainty","authors":"Hidekazu Yoshioka, Yumi Yoshioka","doi":"10.1007/s00477-024-02726-y","DOIUrl":"https://doi.org/10.1007/s00477-024-02726-y","url":null,"abstract":"<p>River water quality often follows a long-memory stochastic process with power-type autocorrelation decay, which can only be reproduced using appropriate mathematical models. The selection of a stochastic process model, particularly its memory structure, is often subject to misspecifications owing to low data quality and quantity. Therefore, environmental risk assessment should account for model misspecification through mathematically rigorous and efficiently implementable approaches; however, such approaches have been still rare. We address this issue by first modeling water quality dynamics through the superposition of an affine diffusion process that is stationary and has a long memory. Second, the worst-case upper deviation of the water quality value from a prescribed threshold value under model misspecifications is evaluated using either the divergence risk or Wasserstein risk measure. The divergence risk measure can consistently deal with the misspecification of the memory structure to the worst-case upper deviation. The Wasserstein risk measure is more flexible but fails in this regard, as it does not directly consider the memory structure information. We theoretically compare both approaches to demonstrate that their assumed uncertainties differed substantially. From the application to the 30-year water quality data of a river in Japan, we categorized the water quality indices to be those with truly long memory (Total nitrogen, NO<sub>3</sub>-N, NH<sub>4</sub>-N, and <span>({{text{SO}}}_{4}^{2-})</span>), those with moderate power-type memory (NO<sub>2</sub>-N, PO<sub>4</sub>-P, and Total Organic Carbon), and those with almost exponential memory (Total phosphorus and Chemical Oxygen demand). The risk measures are successfully computed numerically considering the seasonal variations of the water quality indices.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"25 2 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141061824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Evaluation of eco-environmental quality and analysis of driving forces in the yellow river delta based on improved remote sensing ecological indices 基于改进的遥感生态指数的黄河三角洲生态环境质量评价及驱动力分析
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-13 DOI: 10.1007/s00477-024-02740-0
Dongling Ma, Qingji Huang, Qian Zhang, Qian Wang, Hailong Xu, Yingwei Yan

The ecological environment of the Yellow River Delta is undergoing serious degradation due to the pressures of economic development and population growth. To improve and protect the ecological environment, it is crucial to accurately assess and monitor its eco-environmental quality. With consideration of the characteristics of terrestrial salinization in the region and the need for long-term ecological monitoring, we first utilized Google Earth Engine (GEE) to construct the Improved Remote Sensing Ecological Index (IRSEI). The IRSEI is based on the Remote Sensing Ecological Index (RSEI), which consists of the Normalized Difference Vegetation Index (NDVI), WET, Land Surface Temperature (LST), and Normalized Difference Built-Up and Soil Index (NDBSI), as well as the Net Primary Productivity (NPP) index. The entropy weighting method was employed to construct the IRSEI for assessing the eco-environmental quality of the Yellow River Delta. The validity of the index was verified through image entropy and contrast assessment. We then employed the Hurst exponent, Sen's slope estimation, and Coefficient of Variation (CV) to calculate the range of variation of the IRSEI in the Yellow River Delta over a 20-year period to analyze the spatio-temporal evolution of the ecological quality and its distribution pattern. Furthermore, we conducted a comprehensive analysis combining the Geographically and Temporally Weighted Regression (GTWR) model and Geodetector to understand the influence of drivers such as topography, soil, and climate on the IRSEI, considering both the temporal and spatial dimensions. The results indicate that: (1) The proposed IRSEI demonstrates higher reliability, adaptability, and sensitivity compared to RSEI in monitoring the eco-environmental quality of the Yellow River Delta. (2) From 2000 to 2020, the eco-environmental quality of the Yellow River Delta remained generally stable, with a spatial distribution resembling a "Y" shape, showing significant improvement, particularly in Lijin County and its surrounding areas. However, the middle and eastern estuary exhibited a declining trend in eco-environmental quality. (3) The impact of driving factors on the eco-environmental quality varied across the four subordinate regions of the Yellow River Delta, indicating spatial heterogeneity. Factors such as FVC, Soil, LST, JS, and Srad significantly influenced and explained the spatial differentiation of eco-environmental quality in the region. The proposed IRSEI demonstrates better monitoring capabilities in the Yellow River Delta compared to RSEI, providing a scientific basis for land use planning and ecological protection in the area.

由于经济发展和人口增长的压力,黄河三角洲的生态环境正在严重退化。要改善和保护生态环境,准确评估和监测生态环境质量至关重要。考虑到该地区陆地盐碱化的特点和长期生态监测的需要,我们首先利用谷歌地球引擎(GEE)构建了改进的遥感生态指数(IRSEI)。IRSEI 基于遥感生态指数 (RSEI),后者由归一化差异植被指数 (NDVI)、WET、地表温度 (LST) 和归一化差异堆积和土壤指数 (NDBSI) 以及净初级生产力 (NPP) 指数组成。采用熵权法构建 IRSEI,用于评估黄河三角洲的生态环境质量。通过图像熵和对比度评估验证了该指数的有效性。然后,我们利用赫斯特指数、森氏斜率估计和变异系数(CV)计算了黄河三角洲 20 年间 IRSEI 的变化范围,分析了生态环境质量的时空演变及其分布格局。此外,我们还结合地理和时间加权回归(GTWR)模型和 Geodetector 进行了综合分析,从时间和空间两个维度了解地形、土壤和气候等驱动因素对 IRSEI 的影响。结果表明(1) 与 RSEI 相比,建议的 IRSEI 在监测黄河三角洲生态环境质量方面表现出更高的可靠性、适应性和灵敏度。(2)从 2000 年到 2020 年,黄河三角洲生态环境质量总体保持稳定,空间分布呈 "Y "型,尤其是利津县及周边地区生态环境质量明显改善。但河口中部和东部生态环境质量呈下降趋势。(3) 驱动因子对黄河三角洲四个下属区域生态环境质量的影响存在差异,显示出空间异质性。FVC、Soil、LST、JS 和 Srad 等因子显著影响并解释了该区域生态环境质量的空间差异。与 RSEI 相比,拟议的 IRSEI 在黄河三角洲具有更好的监测能力,为该地区的土地利用规划和生态保护提供了科学依据。
{"title":"Evaluation of eco-environmental quality and analysis of driving forces in the yellow river delta based on improved remote sensing ecological indices","authors":"Dongling Ma, Qingji Huang, Qian Zhang, Qian Wang, Hailong Xu, Yingwei Yan","doi":"10.1007/s00477-024-02740-0","DOIUrl":"https://doi.org/10.1007/s00477-024-02740-0","url":null,"abstract":"<p>The ecological environment of the Yellow River Delta is undergoing serious degradation due to the pressures of economic development and population growth. To improve and protect the ecological environment, it is crucial to accurately assess and monitor its eco-environmental quality. With consideration of the characteristics of terrestrial salinization in the region and the need for long-term ecological monitoring, we first utilized Google Earth Engine (GEE) to construct the Improved Remote Sensing Ecological Index (IRSEI). The IRSEI is based on the Remote Sensing Ecological Index (RSEI), which consists of the Normalized Difference Vegetation Index (NDVI), WET, Land Surface Temperature (LST), and Normalized Difference Built-Up and Soil Index (NDBSI), as well as the Net Primary Productivity (NPP) index. The entropy weighting method was employed to construct the IRSEI for assessing the eco-environmental quality of the Yellow River Delta. The validity of the index was verified through image entropy and contrast assessment. We then employed the Hurst exponent, Sen's slope estimation, and Coefficient of Variation (CV) to calculate the range of variation of the IRSEI in the Yellow River Delta over a 20-year period to analyze the spatio-temporal evolution of the ecological quality and its distribution pattern. Furthermore, we conducted a comprehensive analysis combining the Geographically and Temporally Weighted Regression (GTWR) model and Geodetector to understand the influence of drivers such as topography, soil, and climate on the IRSEI, considering both the temporal and spatial dimensions. The results indicate that: (1) The proposed IRSEI demonstrates higher reliability, adaptability, and sensitivity compared to RSEI in monitoring the eco-environmental quality of the Yellow River Delta. (2) From 2000 to 2020, the eco-environmental quality of the Yellow River Delta remained generally stable, with a spatial distribution resembling a \"Y\" shape, showing significant improvement, particularly in Lijin County and its surrounding areas. However, the middle and eastern estuary exhibited a declining trend in eco-environmental quality. (3) The impact of driving factors on the eco-environmental quality varied across the four subordinate regions of the Yellow River Delta, indicating spatial heterogeneity. Factors such as FVC, Soil, LST, JS, and Srad significantly influenced and explained the spatial differentiation of eco-environmental quality in the region. The proposed IRSEI demonstrates better monitoring capabilities in the Yellow River Delta compared to RSEI, providing a scientific basis for land use planning and ecological protection in the area.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"20 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140941164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Discharge coefficient estimation of modified semi-cylindrical weirs using machine learning approaches 利用机器学习方法估算改良半圆筒形围堰的排流系数
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-13 DOI: 10.1007/s00477-024-02739-7
Reza Fatahi-Alkouhi, Ehsan Afaridegan, Nosratollah Amanian

Based on the principles design of hydrofoil weirs, Modified Semi-Cylindrical Weirs (MSCWs) incorporate an innovative tangential ramp along the downstream crest contour, thereby significantly enhancing their performance compared to conventional semi-cylindrical weirs. A pivotal parameter in the calculation of flow discharge over the weir is the discharge coefficient (Cd). This study involves a comprehensive comparative analysis of various Cd estimation methodologies for MSCWs, employing a range of machine learning-based models, notably including Artificial Neural Network (ANN), Multivariate Adaptive Regression Splines (MARS), M5 tree, Locally Weighted Polynomial Regression (LWPR), and Support Vector Machine (SVM) models. To begin, a feature selection analysis utilizing the Gamma Test (GT) method was conducted to identify the optimal input configuration for modeling the discharge of MSCWs. The results of the feature selection revealed that the Cd of the MSCWs is primarily influenced by the ratio of upstream flow depth (yup) to crest radius (R), while showing negligible sensitivity to the slope of the downstream ramp (θ). The dataset was partitioned into two segments: 70% were assigned to the training stage, while the remaining 30% were allocated to the testing stage. The precision of Cd predictions is evaluated through four key statistical metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Correlation Coefficient (R2), and Nash –Sutcliff Efficiency (NSE). The outcomes reveal that, for the training and testing phases, the R2 values for the ANN, MARS, M5 tree, LWPR and SVM models are respectively 0.967, 0.931, 0.974, 0.937, and 0.933, and 0.925, 0.953, 0.953, 0.980, and 0.954. Notably, the LWPR model outperforms the ANN, MARS, M5 tree, and SVM models, boasting MAE, MSE, RMSE, and NSE values of 0.0167, 0.0005, 0.0217, and 0.942 during training, and 0.0107, 0.0002, 0.0136, and 0.949 during testing. As a result, the LWPR model clearly emerges as the superior model, followed by the M5 model tree.

根据水翼堰的设计原理,改良半圆筒形堰(MSCW)沿下游堰顶轮廓线设计了一个创新的切向斜坡,从而使其性能大大优于传统的半圆筒形堰。计算堰上水流排量的一个关键参数是排量系数(Cd)。本研究采用一系列基于机器学习的模型,主要包括人工神经网络 (ANN)、多元自适应回归样条 (MARS)、M5 树、局部加权多项式回归 (LWPR) 和支持向量机 (SVM) 模型,对用于 MSCW 的各种 Cd 估算方法进行了全面的比较分析。首先,利用伽马测试(GT)方法进行了特征选择分析,以确定中层海洋水体排放建模的最佳输入配置。特征选择的结果表明,中横向水道的 Cd 主要受上游水流深度(yup)与坡顶半径(R)之比的影响,而对下游坡道坡度(θ)的敏感性可忽略不计。数据集被分为两部分:其中 70% 分配给训练阶段,其余 30% 分配给测试阶段。Cd 预测精度通过四个关键统计指标进行评估:平均绝对误差 (MAE)、平均平方误差 (MSE)、均方根误差 (RMSE)、相关系数 (R2) 和 Nash -Sutcliff 效率 (NSE)。结果显示,在训练和测试阶段,ANN、MARS、M5 树、LWPR 和 SVM 模型的 R2 值分别为 0.967、0.931、0.974、0.937 和 0.933,以及 0.925、0.953、0.953、0.980 和 0.954。值得注意的是,LWPR 模型优于 ANN、MARS、M5 树和 SVM 模型,在训练期间的 MAE、MSE、RMSE 和 NSE 值分别为 0.0167、0.0005、0.0217 和 0.942,在测试期间的 MAE、MSE、RMSE 和 NSE 值分别为 0.0107、0.0002、0.0136 和 0.949。因此,LWPR 模型明显优于 M5 模型树。
{"title":"Discharge coefficient estimation of modified semi-cylindrical weirs using machine learning approaches","authors":"Reza Fatahi-Alkouhi, Ehsan Afaridegan, Nosratollah Amanian","doi":"10.1007/s00477-024-02739-7","DOIUrl":"https://doi.org/10.1007/s00477-024-02739-7","url":null,"abstract":"<p>Based on the principles design of hydrofoil weirs, Modified Semi-Cylindrical Weirs (MSCWs) incorporate an innovative tangential ramp along the downstream crest contour, thereby significantly enhancing their performance compared to conventional semi-cylindrical weirs. A pivotal parameter in the calculation of flow discharge over the weir is the discharge coefficient (<i>C</i><sub><i>d</i></sub>). This study involves a comprehensive comparative analysis of various <i>C</i><sub><i>d</i></sub> estimation methodologies for MSCWs, employing a range of machine learning-based models, notably including Artificial Neural Network (ANN), Multivariate Adaptive Regression Splines (MARS), M5 tree, Locally Weighted Polynomial Regression (LWPR), and Support Vector Machine (SVM) models. To begin, a feature selection analysis utilizing the Gamma Test (GT) method was conducted to identify the optimal input configuration for modeling the discharge of MSCWs. The results of the feature selection revealed that the <i>C</i><sub><i>d</i></sub> of the MSCWs is primarily influenced by the ratio of upstream flow depth (<i>y</i><sub><i>up</i></sub>) to crest radius (<i>R</i>), while showing negligible sensitivity to the slope of the downstream ramp (<i>θ</i>). The dataset was partitioned into two segments: 70% were assigned to the training stage, while the remaining 30% were allocated to the testing stage. The precision of <i>C</i><sub><i>d</i></sub> predictions is evaluated through four key statistical metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Correlation Coefficient (<i>R</i><sup>2</sup>), and Nash –Sutcliff Efficiency (NSE). The outcomes reveal that, for the training and testing phases, the <i>R</i><sup>2</sup> values for the ANN, MARS, M5 tree, LWPR and SVM models are respectively 0.967, 0.931, 0.974, 0.937, and 0.933, and 0.925, 0.953, 0.953, 0.980, and 0.954. Notably, the LWPR model outperforms the ANN, MARS, M5 tree, and SVM models, boasting MAE, MSE, RMSE, and NSE values of 0.0167, 0.0005, 0.0217, and 0.942 during training, and 0.0107, 0.0002, 0.0136, and 0.949 during testing. As a result, the LWPR model clearly emerges as the superior model, followed by the M5 model tree.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"12 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140940965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Groundwater salinization risk in coastal regions triggered by earthquake-induced saltwater intrusion 地震引起的盐水入侵引发的沿海地区地下水盐碱化风险
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-09 DOI: 10.1007/s00477-024-02734-y
Alban Kuriqi, Ismail Abd-Elaty

Anthropogenic factors such as over-pumping and natural events such as earthquakes impact coastal aquifers by reducing freshwater recharge, aquifer water budgets, and increasing saltwater intrusion (SWI). This study investigates the impact of hydrodynamic forces induced by earthquakes on SWI in one hypothetical case, namely, the Henry problem, and a real case of the Biscayne aquifer located in Florida, USA. The analysis was carried out using the analytical solution of estimating the earthquake’s induced hydrodynamic pressure and applying the SEAWAT code to investigate the SWI for the base case and three scenarios, namely for the horizontal acceleration (αh) by 0.10 g, 0.20 g, and 0.30 g. The results show that earthquakes might considerably increase the SWI in coastal aquifers. Moreover, the rise in salinity across expansive land areas significantly threatens agricultural productivity and jeopardizes food security. Namely, in the case of Biscayne aquifer, salinity was increased by 12.10%, 21.90%, and 45.70% for the horizontal seismic acceleration of 0.1 g, 0.20 g, and 0.30 g, respectively. Hence, the conclusions drawn from this study underscore the need for carefull consideration of earthquake impacts in future planning and water management strategies for coastal regions. This proactive approach is crucial to preemptively address and mitigate the groundwater salinization hazard associated with SWI fluctuations due to earthquakes.

过度抽水等人为因素和地震等自然事件通过减少淡水补给、含水层水量预算和增 加盐水入侵(SWI)对沿海含水层产生影响。本研究调查了地震诱发的水动力在一种假设情况(即亨利问题)和位于美国佛罗里达州的比斯坎含水层的实际情况下对 SWI 的影响。分析采用了估算地震引起的水动力压力的分析方法,并应用 SEAWAT 代码研究了基 本情况和三种情况下的 SWI,即水平加速度(αh)为 0.10 g、0.20 g 和 0.30 g 时的 SWI。此外,广阔陆地上盐度的升高会严重威胁农业生产力,危及粮食安全。例如,在水平地震加速度为 0.1 g、0.20 g 和 0.30 g 时,比斯开含水层的盐度分别增加了 12.10%、21.90% 和 45.70%。因此,本研究得出的结论强调,在沿海地区未来的规划和水资源管理策略中,需要认真考虑地震的影响。这种未雨绸缪的方法对于预先解决和减轻地震引起的 SWI 波动造成的地下水盐碱化危害至关重要。
{"title":"Groundwater salinization risk in coastal regions triggered by earthquake-induced saltwater intrusion","authors":"Alban Kuriqi, Ismail Abd-Elaty","doi":"10.1007/s00477-024-02734-y","DOIUrl":"https://doi.org/10.1007/s00477-024-02734-y","url":null,"abstract":"<p>Anthropogenic factors such as over-pumping and natural events such as earthquakes impact coastal aquifers by reducing freshwater recharge, aquifer water budgets, and increasing saltwater intrusion (SWI). This study investigates the impact of hydrodynamic forces induced by earthquakes on SWI in one hypothetical case, namely, the Henry problem, and a real case of the Biscayne aquifer located in Florida, USA. The analysis was carried out using the analytical solution of estimating the earthquake’s induced hydrodynamic pressure and applying the SEAWAT code to investigate the SWI for the base case and three scenarios, namely for the horizontal acceleration (α<sub><i>h</i></sub>) by 0.10 g, 0.20 g, and 0.30 g. The results show that earthquakes might considerably increase the SWI in coastal aquifers. Moreover, the rise in salinity across expansive land areas significantly threatens agricultural productivity and jeopardizes food security. Namely, in the case of Biscayne aquifer, salinity was increased by 12.10%, 21.90%, and 45.70% for the horizontal seismic acceleration of 0.1 g, 0.20 g, and 0.30 g, respectively. Hence, the conclusions drawn from this study underscore the need for carefull consideration of earthquake impacts in future planning and water management strategies for coastal regions. This proactive approach is crucial to preemptively address and mitigate the groundwater salinization hazard associated with SWI fluctuations due to earthquakes.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"405 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140941032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Insights into airborne particulate matter: artificial intelligence-driven PM2.5 modelling in Hyderabad district, India 洞察空气中的颗粒物:印度海得拉巴地区人工智能驱动的 PM2.5 模型
IF 4.2 3区 环境科学与生态学 Q1 ENGINEERING, CIVIL Pub Date : 2024-05-09 DOI: 10.1007/s00477-024-02728-w
Nandan A K, Aneesh Mathew

Air pollution is one of the grave concerns of the modern era, claiming millions of lives and adversely impacting the economy. The primary objective of this study was to develop advanced forecast models for PM2.5 levels in the Hyderabad district of India using artificial intelligence techniques. This study presents a novel approach to PM2.5 modelling, leveraging the power of artificial intelligence (AI) and data-driven insights for Hyderabad District. Factor analysis was performed to check for correlations of PM2.5 and aerosol optical depth (AOD) with various meteorological and pollutant variables, based on which it was observed that except temperature and solar radiation, all the variables showed considerable correlations with aerosols. The hybrid deep learning-based CNN – LSTM model was identified as the best-fit model for predicting PM2.5 with an R2 = 0.88, MSE = 68.93 (µg/m3)2, RMSE = 8.30 µg/m3, and MAE = 6.45 µg/m3 as against the MLP – ARIMA and MLP models. A study on feature importance showed that AOD is a significant contributor to PM2.5 prediction with a factor importance of 6.8%, ranking second only to meteorological factors. Wind direction and relative humidity exhibited factor importance values of 10.94% and 8.69%, respectively. The AI-driven PM2.5 modelling approach offers a more comprehensive understanding of pollution patterns and their relationship with meteorological conditions and geographical characteristics. These results highlight the strong predictive power of the CNN – LSTM model and the significant influence of AOD and meteorological factors on PM2.5 levels. These insights can inform policymakers, urban planners, and environmental agencies in formulating effective pollution control strategies and mitigation measures, leading to improved air quality and public health in the Hyderabad district and beyond.

空气污染是现代人严重关切的问题之一,它夺走了数百万人的生命,并对经济产生了不利影响。本研究的主要目的是利用人工智能技术为印度海得拉巴地区的 PM2.5 水平开发先进的预测模型。本研究利用人工智能(AI)的力量和数据驱动的洞察力,为海德拉巴地区的 PM2.5 建模提供了一种新方法。通过因子分析来检查 PM2.5 和气溶胶光学深度(AOD)与各种气象和污染物变量之间的相关性,在此基础上观察到,除温度和太阳辐射外,所有变量都与气溶胶有相当大的相关性。与 MLP - ARIMA 模型和 MLP 模型相比,基于深度学习的混合 CNN - LSTM 模型被确定为预测 PM2.5 的最佳拟合模型,其 R2 = 0.88,MSE = 68.93(微克/立方米)2,RMSE = 8.30 微克/立方米,MAE = 6.45 微克/立方米。对特征重要性的研究表明,AOD 对 PM2.5 预测有重要贡献,其因子重要性为 6.8%,仅次于气象因子。风向和相对湿度的因子重要性分别为 10.94% 和 8.69%。人工智能驱动的 PM2.5 建模方法可以更全面地了解污染模式及其与气象条件和地理特征的关系。这些结果凸显了 CNN - LSTM 模型的强大预测能力,以及 AOD 和气象因素对 PM2.5 水平的显著影响。这些见解可以为政策制定者、城市规划者和环境机构提供信息,帮助他们制定有效的污染控制策略和缓解措施,从而改善海得拉巴地区及周边地区的空气质量和公众健康。
{"title":"Insights into airborne particulate matter: artificial intelligence-driven PM2.5 modelling in Hyderabad district, India","authors":"Nandan A K, Aneesh Mathew","doi":"10.1007/s00477-024-02728-w","DOIUrl":"https://doi.org/10.1007/s00477-024-02728-w","url":null,"abstract":"<p>Air pollution is one of the grave concerns of the modern era, claiming millions of lives and adversely impacting the economy. The primary objective of this study was to develop advanced forecast models for PM<sub>2.5</sub> levels in the Hyderabad district of India using artificial intelligence techniques. This study presents a novel approach to PM<sub>2.5</sub> modelling, leveraging the power of artificial intelligence (AI) and data-driven insights for Hyderabad District. Factor analysis was performed to check for correlations of PM<sub>2.5</sub> and aerosol optical depth (AOD) with various meteorological and pollutant variables, based on which it was observed that except temperature and solar radiation, all the variables showed considerable correlations with aerosols. The hybrid deep learning-based CNN – LSTM model was identified as the best-fit model for predicting PM<sub>2.5</sub> with an R<sup>2</sup> = 0.88, MSE = 68.93 (µg/m<sup>3</sup>)<sup>2</sup>, RMSE = 8.30 µg/m<sup>3</sup>, and MAE = 6.45 µg/m<sup>3</sup> as against the MLP – ARIMA and MLP models. A study on feature importance showed that AOD is a significant contributor to PM<sub>2.5</sub> prediction with a factor importance of 6.8%, ranking second only to meteorological factors. Wind direction and relative humidity exhibited factor importance values of 10.94% and 8.69%, respectively. The AI-driven PM<sub>2.5</sub> modelling approach offers a more comprehensive understanding of pollution patterns and their relationship with meteorological conditions and geographical characteristics. These results highlight the strong predictive power of the CNN – LSTM model and the significant influence of AOD and meteorological factors on PM<sub>2.5</sub> levels. These insights can inform policymakers, urban planners, and environmental agencies in formulating effective pollution control strategies and mitigation measures, leading to improved air quality and public health in the Hyderabad district and beyond.</p>","PeriodicalId":21987,"journal":{"name":"Stochastic Environmental Research and Risk Assessment","volume":"27 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140941016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Stochastic Environmental Research and Risk Assessment
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1