Artificial Intelligence In Source Discrimination of Mine Water: A Deep Learning Algorithm For Water Source Discrimination

With increasing coal mining depth, the source of mine water inrush becomes increasingly complex. The problem of distinguishing the source of mine water in mines and tunnels has been addressed by studying the hydrochemical components of the Pingdingshan Coalfield and applying the artificial intelligence (AI) method to discriminate the source of the mine water. 496 data of mine water have been collected. Six ions of mine water are used as the input data set: Na++K+, Ca2+, Mg2+, Cl-, SO2- 4, and HCO- 3. The type of mine water in the Pingdingshan coalfield is classified into surface water, Quaternary pore water, Carboniderous limestone karst water, Permian sandstone water, and Cambrian limestone karst water. Each type of water is encoded with the number 0 to 4. The one-hot code method is used to encode the numbers, which is the output set. On the basis of hydrochemical data processing, a deep learning model was designed to train the hydrochemical data. Ten new samples of mine water were tested to determine the precision of the model. Nine samples of mine water were predicted correctly. The deep learning model presented here provides significant guidance for the discrimination of mine water.

Combining colour parameters and geochemical tracers to improve sediment source discrimination in a mining catchment (New Caledonia, South Pacific Islands)

Tracing the origin of sediment is needed to improve our knowledge of hydro-sedimentary dynamics at the catchment scale. Several fingerprinting approaches have been developed to provide this crucial information. In particular, spectroscopy provides a rapid, inexpensive and non-destructive alternative technique to the conventional analysis of the geochemical properties. Here, we investigated the performance of four multi-proxy approaches based on (1) colour parameters, (2) geochemical properties, (3) colour parameters coupled with geochemical properties and (4) the entire visible spectrum to discriminate sediment source contributions in a mining catchment of New Caledonia. This French archipelago located in the south-west Pacific Ocean is the world's sixth largest producer of nickel. Open-cast nickel mining increases soil degradation and the downstream transfer of sediments in river systems, leading to the river system siltation. The sediment sources considered in the current research were therefore sediment eroded from mining sub-catchments and non-mining sub-catchments. To this end, sediment deposited during two cyclonic events (i.e. 2015 and 2017) was collected following a tributary design approach in one of the first areas exploited for nickel mining on the archipelago, the Thio River catchment (397 km2). Source (n=24) and river sediment (n=19) samples were analysed by X-ray fluorescence and spectroscopy in the visible spectra (i.e. 365–735 nm). The results demonstrated that the individual sediment tracing methods based on spectroscopy measurements (i.e. (1) and (4)) were not able to discriminate sources. In contrast, the geochemical approach (2) did discriminate sources, with 83.1 % of variance in sources explained. However, it is the inclusion of colour properties in addition to geochemical parameters (3) which provides the strongest discrimination between sources, with 92.6 % of source variance explained. For each of these approaches ((2) and (3)), the associated fingerprinting properties were used in an optimized mixing model. The predictive performance of the models was validated through tests with artificial mixture samples, i.e. where the proportions of the sources were known beforehand. Although with a slightly lower discrimination potential, the “geochemistry” model (2) provided similar predictions of sediment contributions to those obtained with the coupled “colour + geochemistry” model (3). Indeed, the geochemistry model (2) showed that mining tributary contributions dominated the sediments inputs, with a mean contribution of 68 ± 25 % for the 2015 flood event, whereas the colour + geochemistry model (3) estimated that the mining tributaries contributed 65 ± 27 %. In a similar way, the contributions of mining tributaries were evaluated to 83 ± 8 % by the geochemistry model (2) versus 88 ± 8 % by the colour + geochemistry model (3) for the 2017 flood event. Therefore, the use of these approaches based on geochemical properties only (2) or of those coupled to colour parameters (3) was shown to improve source discrimination and to reduce uncertainties associated with sediment source apportionment. These techniques could be extended to other mining catchments of New Caledonia but also to other similar nickel mining areas around the world.

Fingerprinting the Spatial Sources of Fine-grained Sediment Deposited in the Bed of the Mehran River Draining into the Northern Coast of the Persian Gulf using Elemental Geochemistry

Accurate information on the sources of suspended sediment in riverine systems is essential to target mitigation. Accordingly, we applied a generalized likelihood uncertainty estimation (GLUE) framework for quantifying contributions from three sub-basin spatial sediment sources in the Mehran River catchment draining into the Persian Gulf, Hormozgan province, southern Iran. A total of 28 sediment samples were collected from the three sub-basin sources and six from the overall outlet. 43 geochemical elements (e.g., major, trace and rare earth elements) were measured in the samples. Four different combinations of statistical tests comprising: 1) traditional range test (TRT), Kruskal-Wallis (KW) H-test and stepwise discriminant function analysis (DFA) (TRT+KW+DFA); 2) traditional range test using mean values (RTM) and two additional tests (RTM+KW+DFA); 3) TRT+KW+PCA (principle component analysis), and; 4) RTM+KW+PCA, were used to the spatial sediment source discrimination. Tracer bi-plots were used as an additional step to assess the tracers selected in the different final composite signatures for source discrimination. The predictions of spatial source contributions generated by GLUE were assessed using statistical tests and virtual sample mixtures. On this basis, TRT+KW+DFA and RTM+KW+DFA yielded the best source discrimination and the tracers in these composite signatures were shown by the biplots to be broadly conservative during transportation from source to sink. Using these final two composite signatures, the estimated mean contributions for the western, central and eastern sub-basins, respectively, ranged between 10-60% (overall mean contribution 36%), 0.3-16% (overall mean contribution 6%) and 38-77% (overall mean contribution 58%). In comparison, the final tracers selected using TRT+KW+PCA generated respective corresponding contributions of 1-42% (overall mean 20%), 0.5-30% (overall mean 12%) and 55-84% (overall mean 68%) compared with 17-69% (overall mean 41%), 0.2-12% (overall mean 5%) and 29-76% (overall mean 54%) using the final tracers selected by RTM+KW+PCA. Based on the mean absolute fit (MAF; ≥ 95% for all target sediment samples) and goodness-of-fit (GOF; ≥ 99% for all samples), GLUE with the final tracers selected using TRT+KW+PCA performed slightly better than GLUE with the final signatures selected by the three other combinations of statistical tests. Based on the virtual mixture tests, however, predictions provided by GLUE with the final tracers selected using TRT+KW+DFA and RTM+KW+DFA (mean MAE = 11% and mean RMSE = 13%) performed marginally better than GLUE with RTM+KW+PCA (mean MAE = 14% and mean RMSE =16%) and GLUE with TRT+KW+PCA (mean MAE = 17% and mean RMSE = 19%). The estimated source proportions can help watershed engineers plan the targeting of conservation programmes for soil and water resources.

Occurrence of anatase in reworking altered ash beds (K-bentonites and tonsteins) and discrimination of source magmas: a case study of terrestrial Permian–Triassic boundary successions in China

Potential secondary influences on titanium distribution should be evaluated when using ash beds as volcanic source indicators and for correlation purposes. In this study, well-correlated altered ash beds in Permian–Triassic boundary (PTB) successions of various facies in South China were investigated to better understand their use in source discrimination and stratigraphic correlation. The ash beds deposited in lacustrine and paludal facies contain significantly more Ti relative to deposits in marine facies. Neoformed anatase grains nanometres to micrometres in size are associated closely with clay minerals, whereas detrital anatase was observed in the remnants of altered ash beds of terrestrial facies. Extraction of the clay fraction of altered ash beds may exclude significantly detrital accessory minerals such as anatase and rutile added during sediment reworking, and the concentrations of immobile elements in the clay fraction may therefore be used to interpret more effectively their source igneous rocks.