Combining the classic vulnerability index and affinity propagation clustering algorithm to assess the intrinsic aquifer vulnerability of coastal aquifers on an integrated scale

Guo, Xu; Yang, Zhaoxian; Li, Chao; Xiong, Hanxiang; Ma, Chuanming

doi:10.1016/j.envres.2022.114877

Cited by 15 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In any case, a detailed comparison of the two algorithms is given in the "Comparison between affinity propagation and K-means" section below. 46 , and its extension to Hierarchical Affinity Propagation 58 , are nowadays becoming extremely popular due to their simplicity, general applicability, and performance and have been succesfully applied to several contexts in research [49][50][51][52] . AP takes as input the measures of similarity between pairs of data points, and simultaneously considers all of them as potential exemplars.…”

Section: Methodsmentioning

confidence: 99%

A multi-modal machine learning approach to detect extreme rainfall events in Sicily

Eleonora

Dimitri

Mocenni

2023

Sci Rep

View full text Add to dashboard Cite

In 2021 almost 300 mm of rain, nearly half of the average annual rainfall, fell near Catania (Sicily Island, Italy). Such events took place in just a few hours, with dramatic consequences on the environmental, social, economic, and health systems of the region. These phenomena are now very common in various countries all around the world: this is the reason why, detecting local extreme rainfall events is a crucial prerequisite for planning actions, able to reverse possibly intensified dramatic future scenarios. In this paper, the Affinity Propagation algorithm, a clustering algorithm grounded on machine learning, was applied, to the best of our knowledge, for the first time, to detect extreme rainfall areas in Sicily. This was possible by using a high-frequency, large dataset we collected, ranging from 2009 to 2021 which we named RSE (the Rainfall Sicily Extreme dataset). Weather indicators were then been employed to validate the results, thus confirming the presence of recent anomalous rainfall events in eastern Sicily. We believe that easy-to-use and multi-modal data science techniques, such as the one proposed in this study, could give rise to significant improvements in policy-making for successfully contrasting climate change.

show abstract

Section: Methodsmentioning

confidence: 99%

A multi-modal machine learning approach to detect extreme rainfall events in Sicily

Eleonora

Dimitri

Mocenni

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Based on the situation of the study area and referring to the relevant literature [28,35,37,38], each evaluation indicator of the DRASTIC model is rated as 1, 3, 5, and 7, corresponding to different categories of indicators. The greater the rating, the greater the contribution to groundwater vulnerability (Table 7).…”

Section: Groundwater Vulnerabilitymentioning

confidence: 99%

Groundwater Function Zoning for Groundwater Management Based on RSF, EEF, and GEF in the Plain of the Central Plains Urban Agglomeration, China

Hu,

Ma,

Guo

et al. 2023

Water

Self Cite

View full text Add to dashboard Cite

Groundwater function zoning is an important means to ensure that groundwater plays its various functions, which can provide a scientific basis for the protection and development of groundwater resources. Water resources are scarce in the Central Plains Urban Agglomeration (CPUA), so it is of great significance to evaluate groundwater vulnerability and to zone groundwater function in this area. In this study, the resource supply function (RSF), eco-environment function (EEF), and geo-environment function (GEF) of groundwater were analyzed using the analytic hierarchy process (AHP), maximum method, and dominant mark method, so as to divide the shallow groundwater function in the plain of the CPUA. The results show that the reservation areas (32.0%) are distributed in the areas from Luoning County to Yanjin County, Changyuan County to Xinzheng County, and the areas near mountainous in the south of the CPUA. The geological-disaster-prone areas (29.5%) are distributed in the areas from Ruyang County to Luohe City, Weihui County to Jiyuan City, Xingyang County to Changge County, Changyuan County to Yuanyang County, and Kaifeng City. The development and utilization areas (6.4%) are distributed near mountainous areas in the CPUA. The ecologically vulnerable areas (7.5%) are distributed in the east of Kaifeng City and the northeast of Xinxiang City. The conservation areas (24.6%) are distributed in the areas from Ruyang County to Wuyang County, Xinzheng County to Xingyang County, the north of Xuchang City, the east of Luohe City, Kaifeng City, and Xinxiang City. In order to better manage the groundwater, this study evaluates the vulnerability of the groundwater using the DRASTIC model and makes a single indicator sensitivity analysis. The results show that the accuracies of indicators D, A, and I are particularly important for this vulnerability evaluation. According to the groundwater vulnerability and the land use types, some suggestions were put forward. The research results can provide a reference for groundwater management and development in the CPUA and other areas.

show abstract

“…The problem with such models is that they are less accurate, omitting the important variables, and therefore they need to be modified and optimized (Bordbar et al 2019). Based on a recent review of groundwater vulnerability index (GVI) methods, four categories can be distinguished: process-based prediction models (Guo et al 2023), overlay analysis and index-based methods (Wu et al 2018), AI-based hybrid methods (Nadiri et al 2022), and statistical frameworks (Omeje et al 2023). As shown in the table 1, there have been a variety of reviews for GVI methods.…”

Section: Introductionmentioning

confidence: 99%

Groundwater vulnerability assessment for drinking water suitability using Fuzzy Shannon Entropy model in a semi-arid river basin

Halder

Roy

et al. 2023

CATENA

View full text Add to dashboard Cite

Combining the classic vulnerability index and affinity propagation clustering algorithm to assess the intrinsic aquifer vulnerability of coastal aquifers on an integrated scale

Cited by 15 publications

References 36 publications

A multi-modal machine learning approach to detect extreme rainfall events in Sicily

A multi-modal machine learning approach to detect extreme rainfall events in Sicily

Groundwater Function Zoning for Groundwater Management Based on RSF, EEF, and GEF in the Plain of the Central Plains Urban Agglomeration, China

Groundwater vulnerability assessment for drinking water suitability using Fuzzy Shannon Entropy model in a semi-arid river basin

Contact Info

Product

Resources

About