The prediction of severe weather events such as hurricanes is always a challenging task in the history of climate research, and many deep learning models have been developed for predicting the severity of weather events. When a disastrous hurricane strikes a coastal region, it causes serious hazards to human life and habitats and also reflects a prodigious amount of economic losses. Therefore, it is necessary to build models to improve the prediction accuracy and to avoid such significant losses in all aspects. However, it is impractical to predict or monitor every storm formation in real time. Though various techniques exist for diagnosing the tropical cyclone intensity such as convolutional neural networks (CNN), convolutional auto-encoders, recurrent neural network (RNN), etc., there are some challenges involved in estimating the tropical cyclone intensity. This study emphasizes estimating the tropical cyclone intensity to identify the different categories of hurricanes and to perform post-disaster management. An improved deep convolutional neural network (CNN) model is used for predicting the weakest to strongest hurricanes with the intensity values using infrared satellite imagery data and wind speed data from HURDAT2 database. The model achieves a lower Root mean squared error (RMSE) value of 7.6 knots and a Mean squared error (MSE) value of 6.68 knots by adding the batch normalization and dropout layers in the CNN model. Further, it is crucial to predict and evaluate the post-disaster damage for implementing advance measures and planning for the resources. The fine-tuning of the pre-trained visual geometry group (VGG 19) model is accomplished to predict the extent of damage and to perform automatic annotation for the image using the satellite imagery data of Greater Houston. VGG 19 is also trained using video datasets for classifying various types of severe weather events and to annotate the weather event automatically. An accuracy of 98% is achieved for hurricane damage prediction and 97% accuracy for classifying severe weather events. The results proved that the proposed models for hurricane intensity estimation and its damage prediction enhances the learning ability, which can ultimately help scientists and meteorologists to comprehend the formation of storm events. Finally, the mitigation steps in reducing the hurricane risks are addressed.

In order to formulate the long-term and short-term development plans to meet the energy needs, there is a great demand for accurate energy forecasting. Energy autonomy helps to decompose a large-scale grid control into a small sized decisions to attain robustness and scalability through energy independence level of a country. Most of the existing energy demand forecasting models predict the amount of energy at a regional or national scale and failed to forecast the demand for power generation for small-scale decentralized energy systems, like micro grids, buildings, and energy communities. A novel model called Sailfish Whale Optimization-based Deep Long Short- Term memory (SWO-based Deep LSTM) to forecast electricity demand in the distribution systems is proposed. The proposed SWO is designed by integrating the Sailfish Optimizer (SO) with the Whale Optimization Algorithm (WOA). The Hilbert-Schmidt Independence Criterion (HSIC) is applied on the dataset, which is collected from the Central electricity authority, Government of India, for selecting the optimal features using the technical indicators. The proposed algorithm is implemented in MATLAB software package and the study was done using real-time data. The optimal features are trained using Deep LSTM model. The results of the proposed model in terms of install capacity prediction, village electrified prediction, length of R & D lines prediction, hydro, coal, diesel, nuclear prediction, etc. are compared with the existing models. The proposed model achieves percentage improvements of 10%, 9.5%,6%, 4% and 3% in terms of Mean Squared Error (MSE) and 26%, 21%, 16%, 12% and 6% in terms of Root Mean Square Error (RMSE) for Bootstrap-based Extreme Learning Machine approach (BELM), Direct Quantile Regression (DQR), Temporally Local Gaussian Process (TLGP), Deep Echo State Network (Deep ESN) and Deep LSTM respectively. The hybrid approach using the optimization algorithm with the deep learning model leads to faster convergence rate during the training process and enables the small-scale decentralized systems to address the challenges of distributed energy resources. The time series datasets of different utilities are trained using the hybrid model and the temporal dependencies in the sequence of data are predicted with point of interval as 5 years-head. Energy autonomy of the country till the year 2048 is assessed and compared.

Deep learning (DL) models have been recently widely used to extract task-oriented patterns from large scale of datasets, and to improve the data image understanding and analysis accuracy in many different decision-making processes for tasks such as image classification, segmentation, detection, and so on. However, in practice, the performances of DL models are easily affected by environmental illumination conditions. Conversely, DL models can also be utilized for extracting the illumination hints from the images, and these hints are critically useful for improving the model robustness, classifying the environmental scenes, estimating scene depth information, and rendering 3D objects. In this study, an extensive and exhaustive review is carried out for DL based color constancy, indoor and outdoor illumination estimation, and image depth estimations with the considerations of strengths and weaknesses of DL models. This study also explores the different network designs and the paradoxes in parameter optimization during the model training. Current technology barriers involved in implementing these models and recommendations to overcome these barriers are also suggested in the review.