Deep learning models have been widely used in various applications, such as image and speech recognition, natural language processing, and recently, in the field of drought forecasting/prediction. These models have proven to be effective in handling large and complex datasets, and in automatically extracting relevant features for forecasting. The use of deep learning models in drought forecasting can provide more accurate and timely predictions, which are crucial for the mitigation of drought-related impacts such as crop failure, water shortages, and economic losses. This review provides information on the type of droughts and their information systems. A comparative analysis of deep learning models, related technology, and research tabulation is provided. The review has identified algorithms that are more pertinent than others in the current scenario, such as the Deep Neural Network, Multi-Layer Perceptron, Convolutional Neural Networks, and combination of hybrid models. The paper also discusses the common issues for deep learning models for drought forecasting and the current open challenges. In conclusion, deep learning models offer a powerful tool for drought forecasting, which can significantly improve our understanding of drought dynamics and our ability to predict and mitigate its impacts. However, it is important to note that the success of these models is highly dependent on the availability and quality of data, as well as the specific characteristics of the drought event.

The tannery industry is characterized by the consumption of a large quantity of water, around 30–40 m³ for processing 1000 kg of hide or skin. This amount becomes wastewater, containing about 300 kg of different chemicals, mainly refractory organic compounds, with high chemical oxygen demand (COD), total dissolved salts (TDS), chromium, and evolution of toxic gases, such as ammonia and sulfides, etc. The remaining tanning chemicals are released as effluent having high resistance against biological degradation, becoming a serious environmental issue. Usually, end-of-pipe treatment is not sufficient to meet the concerns of environmental issues. In terms of cleaner production options, the redesigning of the existing effluent treatment procedures with alternate or additional treatment techniques, which “supports resource recovery with no added chemicals”, is expected to give a sustainable solution for the management of toxic effluent. The Zero Liquid Discharge (ZLD) system serves to ensure zero water emission, as well as treatment facilities by recycling, recovery, and reuse of the treated wastewater using advanced cleanup technology. The international scenario shows the implementation of ZLD thanks to pressure from regulatory agencies. The ZLD system consists of a pre-treatment system with conventional physicochemical treatment, tertiary treatment, softening of the treated effluent, reverse osmosis (RO) treatment for desalination, and thermal evaporation of the saline reject from RO to separate the salts. By adopting this system, water consumption is reduced. Moreover, ZLD also becomes effective in disaster mitigation in areas where the tannery industry is a strong economic actor. With this review, we aim to give an outlook of the current framework.

Chennai city is the fourth largest metropolis in India, is the focus of economic, social and cultural development and it is the capital of the State of Tamil Nadu. The city has a multi-dimensional growth in development of its infrastructures and population. The area of Chennai has experienced moderate earthquakes in the historical past. Also the Bureau of Indian Standard upgraded the seismic status of Chennai from Low Seismic Hazard (Zone II) to Moderate Seismic Hazard (Zone III)–(BIS: 1893 (2001)). In this connection, a first level seismic microzonation map of Chennai city has been produced with a GIS platform using the themes, viz, Peak Ground Acceleration (PGA), Shear wave velocity at 3 m, Geology, Ground water fluctuation and bed rock depth. The near potential seismic sources were identified from the remote-sensing study and seismo-tectonic details from published literatures. The peak ground acceleration for these seismic sources were estimated based on the attenuation relationship and the maximum PGA for Chennai is 0.176 g. The groundwater fluctuation of the city varies from 0–4 m below ground level. The depth to bedrock configuration shows trough and ridges in the bedrock topography all over the city. The seismic microzonation analysis involved grid datasets (the discrete datasets from different themes were converted to grids) to compute the final seismic hazard grid through integration and weightage analysis of the source themes. The Chennai city has been classified into three broad zones, viz, High, Moderate and Low Seismic Hazard. The High seismic Hazard concentrated in a few places in the western central part of the city. The moderate hazard areas are oriented in NW-SE direction in the Western part. The southern and eastern part will have low seismic hazard. The result of the study may be used as first-hand information in selecting the appropriate earthquake resistant features in designing the forthcoming new buildings against seismic ground motion of the city.

Among all the natural hazards, earthquake prediction is an arduous task. Although many studies have been published on earthquake hazard assessment (EHA), very few have been published on the use of artificial intelligence (AI) in spatial probability assessment (SPA). There is a great deal of complexity observed in the SPA modeling process due to the involvement of seismological to geophysical factors. Recent studies have shown that the insertion of certain integrated factors such as ground shaking, seismic gap, and tectonic contacts in the AI model improves accuracy to a great extent. Because of the black-box nature of AI models, this paper explores the use of an explainable artificial intelligence (XAI) model in SPA. This study aims to develop a hybrid Inception v3-ensemble extreme gradient boosting (XGBoost) model and shapely additive explanations (SHAP). The model would efficiently interpret and recognize factors’ behavior and their weighted contribution. The work explains the specific factors responsible for and their importance in SPA. The earthquake inventory data were collected from the US Geological Survey (USGS) for the past 22 years ranging the magnitudes from 5 M_w and above. Landsat-8 satellite imagery and digital elevation model (DEM) data were also incorporated in the analysis. Results revealed that the SHAP outputs align with the hybrid Inception v3-XGBoost model (87.9% accuracy) explanations, thus indicating the necessity to add new factors such as seismic gaps and tectonic contacts, where the absence of these factors makes the prediction model performs poorly. According to SHAP interpretations, peak ground accelerations (PGA), magnitude variation, seismic gap, and epicenter density are the most critical factors for SPA. The recent Turkey earthquakes (M_w 7.8, 7.5, and 6.7) due to the active east Anatolian fault validate the obtained AI-based earthquake SPA results. The conclusions drawn from the explainable algorithm depicted the importance of relevant, irrelevant, and new futuristic factors in AI-based SPA modeling.

Background: The areas prone to geological hazards such as liquefaction need special attention with respect to social vulnerability. Though liquefaction by itself may not result in damage, it may trigger a series of ground failures such as ground oscillation, lateral spread, loss of bearing strength, etc., which cause heavy damage. Globally, during the past few decades liquefaction hazard analysis has become one of the important criteria in seismic risk analysis and mitigation management, especially for urban areas. Greater Chennai is one of the million-plus population cities in India. The city also felt earthquakes/tremors in the past history. Method: The present study aims to assess the social vulnerability of the population density of the Greater Chennai area due to liquefaction susceptibility using GIS technology. The liquefaction susceptibility map (hazard) for the Greater Chennai was prepared by integration of geological and geomorphological parameters and analyzed over socioeconomic parameters (exposure) using an integration of GIS and AHP. Results: The result showed that around 53% of Greater Chennai’s households and population are very much exposed to liquefaction hazard. Conclusions: This study can be used as a base level study for decision-making during land use planning as well as disaster mitigation planning.