Search for: All records

Various techniques in computer vision have been proposed for water level detection. However, existing methods face challenges during adverse conditions including snow, fog, rain, and nighttime. In this paper, we introduce a novel approach that analyzes images for water level detection by incorporating a deblurring process to increase image clarity. By employing real-time object detection technique YOLOv5, we show that the proposed approach can achieve significantly improved precision, during both daytime and nighttime under under challenging weather circumstances. 

Coastal flooding is a severe and recurring problem, as evidenced by recent disasters that have caused significant damage for coastal communities. A community’s ability to mitigate the effects of coastal flooding depends on the local context and its adaptive capacity. Although past research has highlighted the important role that non-governmental organizations play in building adaptive capacity to support effective adaptation, few studies have focused specifically on rural, community-based nonprofits. To fill this gap, we employ a mixed-methods approach to evaluate the role of the Ingleside on the Bay Coastal Watch Association (IOBCWA), a resident-led, community-based nonprofit, in building adaptive capacity to coastal flooding in the City of Ingleside on the Bay (IOB; pop. 800), located in the Coastal Bend Region of Texas. By applying a grounded theory framework, we show that IOBCWA has improved the adaptive capacity of IOB through five primary activities: engaging in community organizing, boosting advocacy and outreach, implementing evidence-based data collection, building capacity among residents, and developing regional communication networks. Our findings are further examined using the Regional Fingerprint tool (Hirschfeld et al., 2020) to assess progress toward building regional adaptive capacity. We identify a need for more formalized policies, enhanced regional partnerships, and broader inclusion of socially vulnerable groups to address environmental challenges. Overall, this work highlights the important role that small, community-based nonprofits like IOBCWA play in building community adaptive capacity and suggests the need for a more comprehensive regional approach with participation from multiple stakeholders to address challenges related to coastal flooding. 

In the process of developing a smart city framework, sensor data are crucial to enable cities and communities to make informed decisions on future plans. Involving community-based organizations and residents is an integral component of this process to ensure equity and accessibility of data. This study aims to develop a sociotechnical network to (1) identify vulnerability zones; (2) measure data on flooding, air, and water quality; and (3) inform community members and decision-makers through a data dashboard. A small coastal town in the Texas Coastal Bend region is utilized as a case study. Methodologically, this study utilizes participatory action research to frame a mixed-methods approach toward developing a data dashboard. This research project is a practical guide for engaged scholars in the social sciences, engineering, and urban design fields. The outcomes include recommendations for the engaged community and provide a data-dashboard targeting academic and non-academic audiences, residents, and decision-makers.