Analysis of self-organizing maps and explainable artificial intelligence to identify hydrochemical factors that drive drinking water quality in Haor region

Currently, there is a contradiction between coal mining and protection of water resources, meaning that there is a need for an effective method for discriminating the source of mine gushing water. Ningtiaota Coal Mine is a typical and representative main coal mine in the Shennan mining area. Taking this coal mine as an example, the self-organizing feature map (SOM) approach was applied to source discrimination of mine gushing water. Fisher discriminant analysis, water temperature, and traditional hydrogeochemical discrimination methods, such as Piper and Gibbs diagrams, were also employed as auxiliary indicators to verify and analyze the results of the SOM approach. The results from the three methods showed that the source of all the gushing water samples was surface water. This study represents the innovative use of an SOM in source discrimination for the first time. This approach has the advantages of high precision, high efficiency, good visualization, and less human interference. It can quantify sources while also comprehensively considering their hydrogeochemical characteristics, and it is especially suitable for case studies with large sample sizes. This research provides a more satisfactory solution for water inrush traceability, water disaster prevention and control, ecological protection, coal mine safety, and policy intervention.

Hydrogeochemical characterization and quality assessment of groundwater using self-organizing maps in the Hangjinqi gasfield area, Ordos Basin, NW China

Water resources are scarce in arid or semiarid areas; groundwater is an important water source to maintain residents’ lives and the social economy; and identifying the hydrogeochemical characteristics of groundwater and its seasonal changes is a prerequisite for sustainable use and protection of groundwater. This study takes the Hongjiannao Basin as an example, and the Piper diagram, the Gibbs diagram, the Gaillardet diagram, the Chlor-alkali index, the saturation index, and the ion ratio were used to analyze the hydrogeochemical characteristics of groundwater. Meanwhile, based on self-organizing maps (SOM), quantification error (QE), topological error (TE), and the K-means algorithm, groundwater chemical data analysis was carried out to explore its seasonal variability. The results show that (1) the formation of groundwater chemistry in the study area was controlled by water–rock interactions and cation exchange, and the hydrochemical facies were HCO3-Ca type, HCO3-Na type, and Cl-Na type. (2) Groundwater chemical composition was mainly controlled by silicate weathering and carbonate dissolution, and the dissolution of halite, gypsum, and fluorite dominated the contribution of ions, while most dolomite and calcite were in a precipitated state or were reactive minerals. (3) All groundwater samples in wet and dry seasons were divided into five clusters, and the hydrochemical facies of clusters 1, 2, and 3 were HCO3-Ca type; cluster 4 was HCO3-Na type; and cluster 5 was Cl-Na type. (4) Thirty samples changed in the same clusters, and the groundwater chemistry characteristics of nine samples showed obvious seasonal variability, while the seasonal changes of groundwater hydrogeochemical characteristics were not significant.

Characterizing regional groundwater chemistry and quality is essential for sustainable water resource management, yet remains challenging due to spatial complexity arising from both natural and anthropogenic factors. In this study, a hybrid Self-Organizing Map (SOM) and Principal Component Analysis (PCA) approach was applied, followed by Hierarchical Cluster Analysis (HCA), to interpret the hydrochemical characteristics of groundwater in the Qorveh-Dehgolan basin, Iran. A total of 112 groundwater samples collected during dry and wet seasons were analyzed. To ensure optimal performance, multiple SOM map sizes and normalization techniques (Z-score, Min-Max, and log(1 + x)) were tested and evaluated using Quantization Error (QE), Topographic Error (TE), and Explained Variance (EV). The 8 × 7 SOM grid (56 neurons) was selected as the final configuration, as it produced the lowest QE and TE and the highest EV. The optimized SOM results were subsequently grouped into four clusters based on the combined evaluation of SOM and HCA outcomes. Hydrogeochemical processes were interpreted using Piper and Gibbs diagrams, as well as cation exchange indices. Results indicated a dominant Ca2⁺-HCO3⁻ water type across all clusters (1-4). Cation concentrations followed the order Ca2⁺ > Mg2⁺ > Na⁺ + K⁺, while the dominant anion sequence was HCO3⁻ > Cl⁻ > SO42⁻. Ionic ratio analyses revealed that elevated NO3⁻ concentrations are largely attributable to agricultural fertilizer use and domestic wastewater infiltration, highlighting anthropogenic impacts on groundwater quality. In contrast, natural geochemical processes, including silicate weathering and carbonate dissolution, were identified as the predominant mechanisms controlling groundwater evolution. Overall, the integrated SOM-PCA-HCA framework effectively captured both natural and human-induced variability in groundwater chemistry, and distinguished seasonal variations in water quality, underscoring its applicability for sustainable groundwater management in complex aquifer systems.

The study was carried out in the Khandbari Municipality, Sankhuwasabha District, Eastern Nepal to document the spring location and assess the water quality of the spring water for drinking and irrigation purposes. A total of 85 springs were mapped, which are located from 274 to 2176 m in altitude. Spring water samples were collected from 33 springs in the pre-monsoon (November, 2021) and 31 springs in the post-monsoon (March, 2022). Correlation matrices, t-test, principal component analysis (PCA), Piper diagram, Gibbs diagram, water quality index (WQI), United States Salinity Laboratory (USSL) diagram, and Wilcox diagram were applied for evaluating the spring water. All the physicochemical parameters were within the Nepalese National Drinking Water Quality Standard (NDWQS) and drinking water quality guidelines of the World Health Organization (WHO) except for pH in the pre-monsoon and iron in the post-monsoon season. The main contributors to the groundwater are Na+, Ca2+, Cl-, total dissolved solids (TDS), and total hardness, which exhibit significant correlations with electrical conductivity (EC) similar to TDS, suggesting their common source of origin. Based on the WQI, spring water is excellent in the post-monsoon and excellent and good in the pre-monsoon season. Furthermore, the spring water is excellent for irrigation purposes except for thepercent sodium in the post-monsoon and the magnesium ratio in the pre-monsoon season. Gibbs diagram illustrates that spring water is mainly governed by rock and precipitation dominance in some springs. The PCA indicates that anthropogenic activities (mixing of human waste and agricultural run-off in the spring water) are the main causes of contamination. Piper trilinear diagram demonstrates carbonate dissolution and silicate weathering as major processes for controlling the spring water chemistry. The study reveals that 62.5% of spring water was contaminated with microbes. For benthic macroinvertebrates, 18 springs were sampled, where nine orders and 17 families were recorded in the pre-monsoon and six orders and ten families in the post-monsoon season. The main influencing variables for macroinvertebrate assemblages are elevation, discharge, NO3-, and NH3.

Efficient and relevant classification of clinical findings, i.e. diagnostic decision making, poses a major challenge in medicine. In relation to biomedical NMR spectroscopy the problem of classification is often accompanied by complex, heavily overlapping information. Self-organizing map (SOM) analysis has been successfully applied in many areas of research and was thus also considered as a potential tool for NMR data analysis. In this paper we demonstrate how SOM analysis can be used for automated NMR data classification. Our goal was analysis of plasma lipoprotein lipids, a complex but biochemically well understood and specified system. The results illustrate that clinically relevant lipid classifications can be obtained from the SOM analysis of 1H NMR spectral information alone. The resulting maps were calibrated using independent biochemical lipid analyses and were found to produce excellent clustering of the plasma samples into clinically useful groups: normal, type IIa, IIb and IV hyperlipidaemias. In addition to this traditional classification, we also present results from SOM analysis in which the reference vectors of the map were calibrated for plasma total cholesterol and triglycerides and high and low density lipoprotein C; the plasma lipid parameters that are currently considered as the most useful indicators of coronary heart disease risk. In all, the present results indicate that SOM analysis can cope well with complex NMR spectral information and is thus likely to have an independent role in the area of biomedical NMR data analysis.

(1)H NMR spectra of plasma are known to provide specific information on lipoprotein subclasses in the form of complex overlapping resonances. A combination of (1)H NMR and self-organising map (SOM) analysis was applied to investigate if automated characterisation of subclass-related metabolic interactions can be achieved. To reliably assess the intrinsic capability of (1)H NMR for resolving lipoprotein subclass profiles, sum spectra representing the pure lipoprotein subclass part of actual plasma were simulated with the aid of experimentally derived model signals for 11 distinct lipoprotein subclasses. Two biochemically characteristic categories of spectra, representing normolipidaemic and metabolic syndrome status, were generated with corresponding lipoprotein subclass profiles. A set of spectra representing a metabolic pathway between the two categories was also generated. The SOM analysis, based solely on the aliphatic resonances of these simulated spectra, clearly revealed the lipoprotein subclass profiles and their changes. Comparable SOM analysis in a group of 69 experimental (1)H NMR spectra of serum samples, which according to biochemical analyses represented a wide range of lipoprotein lipid concentrations, corroborated the findings based on the simulated data. Interestingly, the choline-N(CH(3))(3) region seems to provide more resolved clustering of lipoprotein subclasses in the SOM analyses than the methyl-CH(3) region commonly used for subclass quantification. The results illustrate the inherent suitability of (1)H NMR metabonomics for automated studies of lipoprotein subclass-related metabolism and demonstrate the power of SOM analysis in an extensive and representative case of (1)H NMR metabonomics.

Groundwater quality in high-sulfur coal mining region of India: Spatial distribution, source control, and health risk assessment

[1] A network of high-frequency (HF) radars was installed in the northern Adriatic in the second half of 2007, aimed to measure surface currents in the framework of the North Adriatic Surface Current Mapping (NASCUM) project. This study includes a detailed analysis of current measurements from February to August 2008, a period in which three radars were simultaneously operational. Current patterns and temporal evolutions of different physical processes were extracted by using self-organizing map (SOM) analysis. The analysis focused on subtidal frequency band and extracted 12 different circulation patterns on a 4 × 3 rectangular SOM grid. The SOM was also applied on a joint data set that included contemporaneous surface wind data obtained from the operational hydrostatic mesoscale meteorological model ALADIN/HR. The strongest currents were recorded during energetic bora episodes, being recognized by several current patterns and having the characteristic downwind flow with magnitudes exceeding 35 cm/s at some grid points. Another characteristic wind, the sirocco, was represented by three current patterns, while the remaining current structures were attributed to weak winds and the residual thermohaline circulation. A strong resemblance has been found between SOM patterns extracted from HF radar data only and from combined HF radar and wind data sets, revealing the predominant wind influence to the surface circulation structures and their temporal changes in the northern Adriatic. These results show the SOM analysis being a valuable tool for extracting characteristic surface current patterns and forcing functions.

Clustering of ant communities and indicator species analysis using self-organizing maps

Identifying which biodiversity species are more dominant than others in any area is a very challenging task. This is because of the abundant of biodiversity species that may become the majority species in any particular region. This situation create a large dataset with a complex variables to be analysed. Moreover, the responds of organisms and environmental factors are occurred in a non-linear correlation. The effort to do so is really important in order to conserve the biodiversity of nature. To understand the complex relationships that exist between species distribution and their habitat, we analysed the interactions among bird diversity, spatial distribution and land use types at Kenyir landscape in Terengganu, Malaysia by using artificial neural network (ANN) method of self-organizing map (SOM) analysis. SOM performs an unsupervised and non-linear analysis on a complex and large dataset. It is capable to handle the non-linear correlation between organism and environmental factors because SOM identifies clusters and relationships between variables without the fixed assumptions of linearity or normality. The result suggested that SOM analysis was suited for understanding the relationships between bird species assemblages and habitat characteristics.

Community recovery of benthic macroinvertebrates in a stream influenced by mining activity: Importance of microhabitat monitoring

Identification of DNA copy number aberrations associated with metastases of colorectal cancer using array CGH profiles

Classification of surface current maps

Urbanization and land use/land cover (LULC) patterns significantly affect groundwater quality. This study investigated groundwater quality and LULC conversion of Xi’an City in Guanzhong Basin over ten years, from 2005 to 2015. The relationship between groundwater quality and LULC patterns were also explored. Piper diagram, Gibbs diagram, and self-organizing map (SOM) were used to investigate the hydrogeochemistry and groundwater quality in the city. Remote sensing image data generated by Landsat 5 and Landsat 8 satellites in 2005, 2010, and 2015 were used to extract the LULC patterns of Xi’an City in those three years. These data were used to determine the LULC conversion between 2005 and 2010, and between 2010 and 2015. Entropy weighted water quality index (EWQI), curved streamline searchlight model (CS-SLM), and multiple linear regression analysis were used to relate groundwater quality to the LULC patterns of Xi’an City in the three years. The Piper diagram indicated that groundwater in Xi’an City was mainly characterized as HCO3-Na type and/or HCO3-Ca·Mg type. The Gibbs diagram indicated that the dominant evolution of hydrogeochemistry was through rock weathering and water-rock interactions. SOM classified the groundwater into eight clusters, and revealed different spatiotemporal patterns of water quality parameters. The LULC classification indicated that the urban land in Xi’an City has expanded by more than 160%, while forest and agricultural land areas have reduced by 52.54% and 83.08%, respectively, from 2005 to 2015. Indicated by the coefficient of multiple linear regression of EWQI and the percentages of LULC types in CS-SLM for the wells, urban land, agricultural land, and industrial land had negative effects on groundwater quality, while the forest positively impacted the groundwater quality in the same period. This study is meaningful and significant because it supports sustainable urban development and groundwater management in Xi’an City.