Evaluation and Clustering Maps of Groundwater Wells in the Red Beds of Chengdu, Sichuan, China

Zhang, Hai‐Jing; Du, Qingyun; Yao, Min; Ren, Fang

doi:10.3390/su8010087

Cited by 5 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An integral part of big data analytics is data mining (DM) that mine data to trace patterns, relationships between input and output variables, grouping similar data points, or forecasting future outcomes to make informed decisions [6]. Data mining is not limited to big data; it has been in use before the inception of big data, for example, clustering [7], regression [8] and classification [9]. Existing methods seem insufficient in analyzing big data due to multi-dimensional data having different data types and formats.…”

Section: Introductionmentioning

confidence: 99%

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

et al. 2021

View full text Add to dashboard Cite

During the last decade, substantial resources have been invested to exploit massive amounts of boreholes data collected through groundwater extraction. Furthermore, boreholes depth can be considered one of the crucial factors in digging borehole efficiency. Therefore, a new solution is needed to process and analyze boreholes data to monitor digging operations and identify the boreholes shortcomings. This research study presents a boreholes data analysis architecture based on data and predictive analysis models to improve borehole efficiency, underground safety verification, and risk evaluation. The proposed architecture aims to process and analyze borehole data based on different hydrogeological characteristics using data and predictive analytics to enhance underground safety verification and planning of borehole resources. The proposed architecture is developed based on two modules; descriptive data analysis and predictive analysis modules. The descriptive analysis aims to utilize data and clustering analysis techniques to process and extract hidden hydrogeological characteristics from borehole history data. The predictive analysis aims to develop a bi-directional long short-term memory (BD-LSTM) to predict the boreholes depth to minimize the cost and time of the digging operations. Furthermore, different performance measures are utilized to evaluate the performance of the proposed clustering and regression models. Moreover, our proposed BD-LSTM model is evaluated and compared with conventional machine learning (ML) regression models. The R 2 score of the proposed BD-LSTM is 0.989, which indicates that the proposed model accurately and precisely predicts boreholes depth compared to the conventional regression models. The experimental and comparative analysis results reveal the significance and effectiveness of the proposed borehole data analysis architecture. The experimental results will improve underground safety management and the efficiency of boreholes for future wells.

show abstract

Section: Introductionmentioning

confidence: 99%

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

et al. 2021

View full text Add to dashboard Cite

show abstract

Improvement of Dam Management in Terms of WAM Using Machine Learning

Fazli

Abdullah

Zulkifli

et al. 2019

Water Resources Development and Management

View full text Add to dashboard Cite

Alarming Realities of Groundwater Dynamics in Basaltic Region through RS, GIS-Based Retrieval of Historical Data

Chaware

Patil

Patil³

2021

Journal of the Geological Society of India

View full text Add to dashboard Cite

A concept of retrieving and monitoring groundwater dynamics was introduced via metrics derived using Remote Sensing (RS) and Geographic Information Systems (GIS) in the basaltic region, namely the Euclidian distance between neighbouring irrigation wells, area irrigated per well, well density and cluster analysis. In a representative Nagjhari watershed (14823 ha) located in Maharashtra state, India, temporal Google Earth images were interpreted visually to retrieve the periodic (2007, 2013, 2017), historical dugout well related data. During the decade, the number of wells increased by 429 (64%) with a 7% decrease in irrigated area, implying a greater number of competing users, tapping the same aquifer leading to the increased cost of irrigation. In 2007, functional wells (368) outnumbered defunct wells (303). By 2017, the reversal was far greater with 698 defunct wells compared to 399 functional wells. Clusters of 5-10, 10-15, and >15 number of wells respectively with 500 m proximity showed a common trend of a rising number of defunct wells (303 to 698), a decline in the total irrigated area in the watershed (from 517 to 479 ha), and irrigated area per unit well (from 1.41 to 1.23 ha) accompanied by a decrease in inter-well distance from 250 to 110 m. The well density increased from 0.035 to 0.25 units per ha. Neural clustering proved effective in discovering and delineating an aquifer located between 310-330 m contour classes. Three ‘hot spots’ of high well density, lower inter-well distance, and irrigated area per well were mapped. Observation wells monitored by the Central Ground Water Board were located within 460 m from the functional wells raising concerns about their representative character. An alarming trend of the rising number of competing groundwater users, increasing demand but actual use limited by aquifer yield potential was noted with negative influence on well density, and investment of about INR 34.55 million wasted over a decade.

show abstract

Evaluation and Clustering Maps of Groundwater Wells in the Red Beds of Chengdu, Sichuan, China

Cited by 5 publications

References 16 publications

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

Improvement of Dam Management in Terms of WAM Using Machine Learning

Alarming Realities of Groundwater Dynamics in Basaltic Region through RS, GIS-Based Retrieval of Historical Data

Contact Info

Product

Resources

About