The Deccan tholeiite lavas and dykes of Ghatkopar–Powai area,Mumbai, Panvel flexure zone: Geochemistry,stratigraphic status,and tectonic significance

Mumbai City, situated on the western Indian coast, is well known for exposures of late-stage Deccan pillow basalts and spilites, pyroclastic rocks, rhyolite lavas, and trachyte intrusions. These rock units, and a little-studied sequence of tholeiitic flows and dykes in the eastern part of Mumbai City, constitute the west-dipping limb of a regional tectonic structure called the Panvel flexure. Here we present field, petrographic, major and trace element and Sr–Nd isotopic data on these tholeiitic flows and dykes, best exposed in the Ghatkopar–Powai area. The flows closely resemble the Mahabaleshwar Formation of the thick Western Ghats sequence to the east, in Sr–Nd isotopic ratios and multielement patterns, but have other geochemical characteristics (e.g., incompatible trace element ratios) unlike the Mahabaleshwar or any other Formation. The flows may have originated from a nearby eruptive center, possibly offshore of Mumbai. Two dykes resemble the Ambenali Formation of the Western Ghats in all geochemical characteristics, though they may not represent feeders of the Ambenali Formation lavas. Most dykes are distinct from any of the Western Ghats stratigraphic units. Some show partial (e.g., Sr–Nd isotopic) similarities to the Mahabaleshwar Formation, and these include several dykes with unusual, concave-downward REE patterns suggesting residual amphibole and thus a lithospheric source. The flows and dykes are inferred to have undergone little or no contamination, by lower continental crust. Most dykes are almost vertical, suggesting emplacement after the formation of the Panvel flexure, and indicate considerable east–west lithospheric extension during this late but magmatically vigorous stage of Deccan volcanism.     

Multi-hazard susceptibility mapping based on Convolutional Neural Networks

Multi-hazard susceptibility prediction is an important component of disasters risk management plan. An effective multi-hazard risk mitigation strategy includes assessing individual hazards as well as their interactions. However, with the rapid development of artificial intelligence technology, multi-hazard susceptibility prediction techniques based on machine learning has encountered a huge bottleneck. In order to effectively solve this problem, this study proposes a multi-hazard susceptibility mapping framework using the classical deep learning algorithm of Convolutional Neural Networks (CNN). First, we use historical flash flood, debris flow and landslide locations based on Google Earth images, extensive field surveys, topography, hydrology, and environmental data sets to train and validate the proposed CNN method. Next, the proposed CNN method is assessed in comparison to conventional logistic regression and k-nearest neighbor methods using several objective criteria, i.e., coefficient of determination, overall accuracy, mean absolute error and the root mean square error. Experimental results show that the CNN method outperforms the conventional machine learning algorithms in predicting probability of flash floods, debris flows and landslides. Finally, the susceptibility maps of the three hazards based on CNN are combined to create a multi-hazard susceptibility map. It can be observed from the map that 62.43% of the study area are prone to hazards, while 37.57% of the study area are harmless. In hazard-prone areas, 16.14%, 4.94% and 30.66% of the study area are susceptible to flash floods, debris flows and landslides, respectively. In terms of concurrent hazards, 0.28%, 7.11% and 3.13% of the study area are susceptible to the joint occurrence of flash floods and debris flow, debris flow and landslides, and flash floods and landslides, respectively, whereas, 0.18% of the study area is subject to all the three hazards. The results of this study can benefit engineers, disaster managers and local government officials involved in sustainable land management and disaster risk mitigation.