Search for: All records

As human industrial technology advances, coastal communities face threats from both nature and industry. Rising tropical storms and sea levels lead to disruptive floods, endangering residents, industries, and vital infrastructure. While economic benefits come from new industrial facilities, expanded shipping, and water desalination, they also bring increased emissions, habitat destruction, and altered hydrology, harming air, water, and land resources. To be able to effectively and affordably monitor the air and water quality in coastal communities is vital. In this paper, we present an environmental monitoring system for coastal communities with low-cost sensors and capabilities to integrate and present data from multiple sources. The sensing system, powered by regenerative and city electricity sources, uses LoRa Wanto wirelessly transmit seawater and air quality data to LoRaWAN gateways, where it will be further forwarded to a server system for storage, analysis, and visualization. A proof of concept monitoring system is deployed in a coastal community in Texas. We present some of the data gathered and provide analysis on the cost benefits. 

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.