Geoscientists have extensively used machine learning for geological mapping and exploring the mineral prospect of a province. However, the interpretation of results becomes challenging due to the complexity of machine learning models. This study uses a convolutional neural network (CNN) and Shapley additive explanation (SHAP) to estimate potential locations for gold mineralisation in Rengali Province, a tectonised mosaic of volcano-sedimentary sequences juxtaposed at the interface of the Archaean cratonic segment in the north and the Proterozoic granulite provinces of the Eastern Ghats Belt in Eastern India. The objective is to integrate multi-thematic data involving geological, geophysical, mineralogical and geochemical surveys on a 1:50 K scale with the aim of prognosticating gold mineralisation. The available data utilised during the integration include aero-geophysical (aeromagnetic and aerospectrometric), geochemical (national geochemical mapping), ground geophysical (gravity), satellite gravity, remote sensing (multispectral) and National Geomorphology and Lineament Project structural lineament maps obtained from the Geological Survey of India Database. The CNN model has an overall accuracy of 90%. The SHAP values demonstrate that the major contributing factors are, in sequential order, antimony, clay, lead, arsenic content and a magnetic anomaly in CNN modelling. Geochemical pathfinders, including geophysical factors, have high importance, followed by the shear zones in mineralisation mapping. According to the results, the central parts of the study area, including the river valley, have higher gold prospects than the surrounding areas. Gold mineralisation is possibly associated with intermediate metavolcanics along the shear zone, which is later intruded by quartz veins in the northern part of the Rengali Province. This work intends to model known occurrences with respect to multiple themes so that the results can be replicated in surrounding areas.

Integrated geoelectric and geochemical investigation were carried out in the Canning and adjoining areas to assess the prevailing groundwater conditions and chemical quality of groundwater. Geologically, the area is constituted of alluvial sediments of Quaternary age. Vertical electrical soundings (VES) in the area of investigation mostly show six layers consisting of top soil, saline water, clay layer, brackish water, clay layer and fresh-water bearing zone of appreciable thicknesses at depths of 137 to 182 meter at six locations and from 370 to 430 meter for other two locations under confined conditions. The result of VES studies significantly correspond with the borehole litholog and well log data. A litho-resistivity relationship is established for this area of investigation A Fence diagram is constructed to show the spatial variation of the sub-surface lithology and hydrological characteristics. Chemically the ground water is fresh and mixed cation and anion type as revealed from Piper-Trilinear diagram with TDS ranging from 699 to 1547 mg/l. The geochemical parameters like Total hardness (TH), Sodium absorption ratio (SAR), Soluble sodium percentage (SSP), Percentage of sodium (PS), Kelley’s ratio (KR), Residual sodium carbonate (RSC), Corrosivity ratio (CR), Gibbs ratios (GR), Chloro alkaline indices (CAI), Sea water contamination (SWC) are also calculated for examining the quality of groundwater in the area. The depth of occurrences of freshwater bearing ground water zones for drinking and irrigation purposes are occurring at depths from 137 meter to 430 meter in this area.