No abstract

Groundwater is one of the major valuable water resources for the use of communities, agriculture, and industries. In the present study, we have developed three novel hybrid artificial intelligence (AI) models which is a combination of modified RealAdaBoost (MRAB), bagging (BA), and rotation forest (RF) ensembles with functional tree (FT) base classifier for the groundwater potential mapping (GPM) in the basaltic terrain at DakLak province, Highland Centre, Vietnam. Based on the literature survey, these proposed hybrid AI models are new and have not been used in the GPM of an area. Geospatial techniques were used and geo‐hydrological data of 130 groundwater wells and 12 topographical and geo‐environmental factors were used in the model studies. One‐R Attribute Evaluation feature selection method was used for the selection of relevant input parameters for the development of AI models. The performance of these models was evaluated using various statistical measures including area under the receiver operation curve (AUC). Results indicated that though all the hybrid models developed in this study enhanced the goodness‐of‐fit and prediction accuracy, but MRAB‐FT (AUC = 0.742) model outperformed RF‐FT (AUC = 0.736), BA‐FT (AUC = 0.714), and single FT (AUC = 0.674) models. Therefore, the MRAB‐FT model can be considered as a promising AI hybrid technique for the accurate GPM. Accurate mapping of the groundwater potential zones will help in adequately recharging the aquifer for optimum use of groundwater resources by maintaining the balance between consumption and exploitation.

No abstract

Thanh Hoa province belongs to the southwest part of Northwest Vietnam, which is considered a tectonically active region. In the area of Thanh Hoa province, there are three deep-seated tectonic faults, namely Son La-Bim Son, Song Ma, and Sop Cop. As predicted by scientists, these faults are capable of producing credible earthquakes that might be the strongest in the territory of Vietnam. Besides the three main seismogenic sources, in the province, there are other smaller active faults such as Thuong Xuan-Ba Thuoc and Thuong Xuan-Vinh Loc but the relationship of these faults with seismic activity is still rather blurred. This may due to the sparseness of the Vietnamese National Seismic Network which can not record adequately small earthquakes in the area. This paper presents new results of additional monitoring from a local seismic network using 12 Guralp - 6TD broadband seismometers that have been deployed in Thanh Hoa province since November 2009. We found that the Thanh Hoa area is not seismically quiet. The average number of earthquakes recorded by the network has reached 80 - 90 events per year and some of them have magnitude from ML 3.0 to 4.0.By integration of the earthquake epicenters derived from the local network and distribution of active faults, we can detect several earthquakes locating near the three active faults, not only along the main faults but also along its subsidiary faults. We focused on the active faults of Thuong Xuan-Ba Thuoc and Thuong Xuan-Vinh Loc by using the recent results of the gravity, seismic, and magnetotelluric data analyses. Several recorded earthquakes distribute along the two small faults and some of them reach magnitude 3.0 or greater on the ML scale. In this study, the Thuong Xuan-Vinh Loc is recognized as a seismogenic source. To identify seismic hazard potential caused by earthquakes generated from the active faults, segmentation of the Thuong Xuan - Ba Thuoc fault had been done based on geological and geomorphological indications and seismic activity, and then the peak ground acceleration was determined for each fault segment. Besides, a large number of earthquake epicenters do not have a good correlation with a specific fault, especially in the area of Thanh Hoa coastal plain, which is covered by thick layers of Neogene - Quaternary sediment. This shows that there may be hidden active faults in the area which are needed to study further.

Worldwide literature shows that the potential for electricity generation of every geothermal source is depended on the local condition, so the exploration phase is an important step in the geothermal power development to identify the site, structural feature and temperature parameters of a geothermal system-reservoir. The paper presents some results of the first experiment carried out by using a combination of geological, geochemical, geophysical methods, and temperature measurements in shallow drilling hole (depth 250 m) were applied for investigation in the Bang hot water spring area, Quang Binh province, during the period from 2012 to 2015. The location and structural feature of geothermal reservoir identified by the resistivity model obtained from the magneto-telluric survey and geochemical analysis was a good consistency with the existent reservoirs of a typical hydro-geothermal system of magmatic origin. The temperature gradient and heat flow at the shallow drilling hole are reached 4.1°C/100m and 83.4 mW/m 2 , respectively. The reservoir temperatures estimated by both geochemical thermometer and temperature modeling are varied in a range 167-200°C at the depth >2 km. The obtained results allow to determine the suitable location for test drilling to the reservoir and to propose for the next phase of the Geothermal Program in the area.