The traditional carbon-based approach towards sustainability has long caused the concepts of green and sustainable energies to be used interchangeably. Recent studies have tried to advance this archaic view by considering more aspects of sustainability. However, almost all major studies have been concerned with only the economic and environmental aspects of electricity generation, whereas the concept of sustainability is beyond these two criteria. In this paper, we seek to provide a methodology for a more comprehensive definition of electricity generation sustainability based on the lessons learned from previous studies and additional metrics suggested by them. The main characteristics of select electricity generation technologies were studied, and their environmental, economic, social, and technical criteria as well as the uncertainties associated with them were selected as the four major factors in our paper. It has also been argued that the utilization of regional resources in addition to the inherent characteristics of electricity generation technologies is vital in providing a realistic view of sustainability. Of the sustainability assessment methods previously introduced, the Relative Aggregate Footprint (RAF) method was used in conjunction with the previously selected criteria as the basis of the study due to its ability to incorporate additional criteria and regional considerations. As such, the framework for sustainability assessment presented in this research accounts for major criteria identified in the literature and takes the available regional resources that affect the feasibility of each electricity technology into account. This study paves the way for the presentation of new guidelines for the creation of more comprehensive electricity generation sustainability measures to distinguish between the concepts of green and profitable vs. sustainable energies to support the development of sustainable energy portfolios.

Heavy rains and tropical storms often result in floods, which are expected to increase in frequency and intensity. Flood prediction models and inundation mapping tools provide decision-makers and emergency responders with crucial information to better prepare for these events. However, the performance of models relies on the accuracy and timeliness of data received from in-situ gaging stations and remote sensing; each of these data sources has its limitations, especially when it comes to real-time monitoring of floods. This study presents a vision-based framework for measuring water levels and detecting floods using Computer Vision and Deep Learning (DL) techniques. The DL models use time-lapse images captured by surveillance cameras during storm events for the semantic segmentation of water extent in images. Three different DL-based approaches, namely PSPNet, TransUNet, and SegFormer, were applied and evaluated for semantic segmentation. The predicted masks are transformed into water level values by intersecting the extracted water edges, with the 2D representation of a point cloud generated by an Apple iPhone 13 Pro LiDAR sensor. The estimated water levels were compared to reference data collected by an ultrasonic sensor. The results showed that SegFormer outperformed other DL-based approaches by achieving 99.55% and 99.81% for Intersection over Union (IoU) and accuracy, respectively. Moreover, the highest correlations between reference data and the vision-based approach reached above 0.98 for both the coefficient of determination (R2) and Nash-Sutcliffe Efficiency. This study demonstrates the potential of using surveillance cameras and Artificial Intelligence for hydrologic monitoring and their integration with existing surveillance infrastructure.