Apalachicola Bay in the Florida panhandle is home to a rich variety of salt water and freshwater wetlands but unfortunately is also subject to a wide range of hydrologic extreme events. Extreme hydrologic events such as hurricanes and droughts continuously threaten the area. The impact of hurricane and drought on both fresh and salt water wetlands was investigated over the time period from 2000 to 2015 in Apalachicola Bay using spatio-temporal changes in the Landsat based NDVI. Results indicate that salt water wetlands were more resilient than fresh water wetlands. Results also suggest that in response to hurricanes, the coastal wetlands took almost a year to recover while recovery following a drought period was observed after only a month. This analysis was successful and provided excellent insights into coastal wetland health. Such long term study is heavily dependent on optical sensor that is subject to data loss due to cloud coverage. Therefore, a novel method is proposed and demonstrated to recover the information contaminated by cloud. Cloud contamination is a hindrance to long-term environmental assessment using information derived from satellite imagery that retrieve data from visible and infrared spectral ranges. Normalized Difference Vegetation Index (NDVI) is a widely used index to monitor vegetation and land use change. NDVI can be retrieved from publicly available data repositories of optical sensors such as Landsat, Moderate Resolution Imaging Spectro-radiometer (MODIS) and several commercial satellites. Landsat has an ongoing high resolution NDVI record starting from 1984. Unfortunately, the time series NDVI data suffers from the cloud contamination issue. Though simple to complex computational methods for data interpolation have been applied to recover cloudy data, all the techniques are subject to many limitations. In this paper, a novel Optical Cloud Pixel Recovery (OCPR) method is proposed to repair cloudy pixels from the time-space-spectrum continuum with the aid of a machine learning tool, namely random forest (RF) trained and tested utilizing multi-parameter hydrologic data. The RF based OCPR model was compared with a simple linear regression (LR) based OCPR model to understand the potential of the model. A case study in Apalachicola Bay is presented to evaluate the performance of OCPR to repair cloudy NDVI reflectance for two specific dates. The RF based OCPR method achieves a root mean squared error of 0.0475 sr?1 between predicted and observed NDVI reflectance values. The LR based OCPR method achieves a root mean squared error of 0.1257 sr?1. Findings suggested that the RF based OCPR method is effective to repair cloudy values and provide continuous and quantitatively reliable imagery for further analysis in environmental applications.
Master of Science (M.S.)
College of Engineering and Computer Science
Civil, Environmental, and Construction Engineering
Civil Engineering; Water Resources Engineering
Length of Campus-only Access
Masters Thesis (Open Access)
Tahsin, Subrina, "Remote Sensing of Coastal Wetlands: Long term vegetation stress assessment and data enhancement technique" (2016). Electronic Theses and Dissertations, 2004-2019. 5339.