Seawater intrusion pattern recognition supported by unsupervised learning: A systematic review and application

Narvaez-Montoya, Christian; Mahlknecht, Jürgen; Torres-Martínez, Juan Antonio; Mora, Abrahan; Bertrand, Guillaume

doi:10.1016/j.scitotenv.2022.160933

Cited by 13 publications

(3 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the WOS database also contains the Chinese Science Citation Database (relevant Chinese literature will have corresponding English titles and abstracts), which is very useful for accessing scientific research in different language type. The quality of outcome produced by a bibliometric analysis heavily depends on the quality of the paper we choose [56][57][58]. The core database of the WOS is comprised of three main indexes: SCI-EXPANDED, SSCI and the AHCI.…”

Section: Data Collection and Search Strategymentioning

confidence: 99%

Bibliometric Analysis of Spatial Technology for World Heritage: Application, Trend and Potential Paths

Chen,

Yang,

Zhao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

World heritage sites are monuments and natural landscapes recognised by all humanity as being of outstanding significance and universal value. Spatial technology provides new ideas for the conservation and sustainable development of world heritage sites. Using a bibliometric analysis, this study extracted 401 relevant documents from the Web of Science database from 1990–2022. Meta information, such as abstracts, keywords of the papers were extracted and cleaned using bibliometric package and analysed the applications, partnerships and development trends of existing spatial technologies for world heritage sites. The results of the study show the “4D” characteristics of space technology in world heritage sites: (1) Development: Spatial applications in world heritage sites have gradually developed with an annual growth rate of 10.22% during the period 1990–2022. (2) Discrepancy: More than 70 per cent of countries have not been able to fully apply space technology on the ground at world heritage sites. (3) Desirability: Shared exchanges between research institutions are rare, and more cooperation and exchanges are expected, especially between transnationals. (4) Diversity: The future outlook for technology will be multidisciplinary, multi-method integrated research.

show abstract

Section: Data Collection and Search Strategymentioning

confidence: 99%

Bibliometric Analysis of Spatial Technology for World Heritage: Application, Trend and Potential Paths

Chen,

Yang,

Zhao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…High-resolution time series are, for example, required for analyzing the interaction of groundwater with the sea (Haehnel et al, 2023). Accounting for SWI in GWL dynamics pattern analysis is best supported by pattern recognition or correction with groundwater chemistry data (Narvaez-Montoya et al, 2023;Rau et al, 2020). However, the lack of GWL time series with high temporal resolution and long time series length currently hinders the expansion of such studies.…”

Section: Hydrogeological Similarity and Scaling Effectmentioning

confidence: 99%

Disentangling coastal groundwater level dynamics on a global data set

Nolte,

Haaf,

Heudorfer

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. This study aims to identify common hydrogeological patterns and to gain a deeper understanding of the underlying similarities and their link to physiographic, climatic, and anthropogenic controls of coastal groundwater. The most striking aspects of GWL dynamics and their controls were identified through a combination of statistical metrics, calculated from about 8,000 groundwater hydrographs, and pattern recognition, classification, and explanation using machine learning techniques and SHapley Additive exPlanations (SHAP). Overall, four different GWL dynamics patterns emerge, independent of the different seasons, time series lengths, and periods. We show in this study that similar GWL dynamics can be observed around the world with different combinations of site characteristics, but also that the main factors differentiating these patterns can be identified. Three of the identified patterns exhibit high short-term and interannual variability and are most common in regions with low terrain elevation and shallow groundwater depth. Climate and soil characteristics are most important in differentiating these patterns. This study provides new insights into the hydrogeological behavior of groundwater in coastal regions and guides systematic and holistic groundwater monitoring and modelling, motivating to consider various aspects of GWL dynamics when, for example, estimating climate-driven GWL changes – especially when information on potential controls is limited.

show abstract

“…Numerical modeling required a large amount of basic data, which was difficult to use in areas where data were lacking. With the rise of computer technology, machine learning has been employed for multivariate analysis of nutrient distribution in water environments across temporal and spatial scales in recent decades, and the number of such studies has grown exponentially in recent years [ 30 ]. Compared with traditional algorithms, machine learning can effectively reduce the computational dimension while maintaining prediction accuracy and high stability [ 31 ].…”

Section: Introductionmentioning

confidence: 99%

Research on Seawater Intrusion Suppression Scheme of Minjiang River Estuary

Wang

Guan

Zhang

et al. 2023

IJERPH

View full text Add to dashboard Cite

Seawater intrusion in the Minjiang River estuary has gravely endangered the water security of the surrounding area in recent years. Previous studies mainly focused on exploring the mechanism of intrusion, but failed to provide a scheme for suppressing seawater intrusion. The three most relevant determinants to chlorine level, which represented the strength of seawater intrusion, were determined using Pearson correlation analysis as being the daily average discharge, daily maximum tidal range, and daily minimum tidal level. Considering the lower requirement of sample data and the ability to handle high-dimensional data, the random forest algorithm was used to construct a seawater intrusion suppression model and was combined with a genetic algorithm. The critical river discharge for suppressing estuary seawater intrusion determined using this model. The critical river discharge was found to gradually increase with the maximum tidal range, which in three different tide scenarios was 487 m3/s, 493 m3/s, and 531 m3/s. The practicable seawater intrusion suppression scheme was built up with three phases to make it easier to regulate upstream reservoirs. In the scheme, the initial reading of river discharge was 490 m3/s, and it rose to 650 m3/s over six days, from four days before the high tide’s arrival to two days following it, and before falling down to 490 m3/s at the end. Verified with the 16 seawater intrusion events in the five dry years, this scheme could eliminate 75% of the seawater intrusion risk and effectively reduce the chlorine level for the remaining 25% of events.

show abstract

Seawater intrusion pattern recognition supported by unsupervised learning: A systematic review and application

Cited by 13 publications

References 113 publications

Bibliometric Analysis of Spatial Technology for World Heritage: Application, Trend and Potential Paths

Bibliometric Analysis of Spatial Technology for World Heritage: Application, Trend and Potential Paths

Disentangling coastal groundwater level dynamics on a global data set

Research on Seawater Intrusion Suppression Scheme of Minjiang River Estuary

Contact Info

Product

Resources

About