Optical Cloud Pixel Recovery via Machine Learning

Abstract

Remote sensing derived 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. Studies that are heavily dependent on optical sensors are subject to data loss due to cloud coverage. Specifically, cloud contamination is a hindrance to long-term environmental assessment when using information from satellite imagery retrieved from visible and infrared spectral ranges. Landsat has an ongoing high-resolution NDVI record starting from 1984. Unfortunately, this long time series NDVI data suffers from the cloud contamination issue. Though both simple and complex computational methods for data interpolation have been applied to recover cloudy data, all the techniques have limitations. In this paper, a novel Optical Cloud Pixel Recovery (OCPR) method is proposed to repair cloudy pixels from the time-space-spectrum continuum using a Random Forest (RF) trained and tested with multi-parameter hydrologic data. The RF-based OCPR model is compared with a linear regression model to demonstrate the capability of OCPR. A case study in Apalachicola Bay is presented to evaluate the performance of OCPR to repair cloudy NDVI reflectance. The RF-based OCPR method achieves a root mean squared error of 0.016 between predicted and observed NDVI reflectance values. The linear regression model achieves a root mean squared error of 0.126. Our findings suggest that the RF-based OCPR method is effective to repair cloudy pixels and provides continuous and quantitatively reliable imagery for long-term environmental analysis.

Wetland Dynamics Inferred from Spectral Analyses of Hydro-Meteorological Signals and Landsat Derived Vegetation Indices

“…However, the complete NDVI time series data were limited by clouds and other effects. For instance, only 252 months of data were usable out of the 384 months of the study time period [15,29]. Since NDVI is released as a 16-day composite, when two images were available for a given month the one with less cloud coverage was selected.…”

“…The remainder of the data came from Landsat-8. In order to overcome the remaining data gaps in the time series [29], a Saviszky-Golay filter was used for both interpolating missing data and discounting spurious low NDVI values [30][31][32]. To compare the performance of the filter, a goodness of fit test between the original NDVI and some known but reconstructed NDVI data using the Saviltzky-Golay filter was conducted.…”

The recent developments in cloud removal approaches of MODIS snow cover product

“…Because of the high albedo, high thermal emissivity, low thermal conductivity, and water storage ability (Tait et al, 2000;Tekeli and Tekeli, 2012), snow has a significant in-fluence on the energy balance (Robinson et al, 1993;Crawford et al, 2013), the hydrological cycle (Şorman et al, 2007;Kostadinov and Lookingbill, 2015), and climate change (Cohen and Entekhabi, 1999;Brown, 2000). In recent years, increasing attention has been focused on monitoring the spatial and temporal change of snow cover (Gao et al, 2012).…”

“…Microwave-based products are derived according to the relationship between microwave energy and snow depth (SD) or the snow water equivalent (SWE) when the snowpack is dry (Tait et al, 2000;Wulder et al, 2007). Microwavebased products are free from cloud cover contamination and can capture the snow information with an all-time and allweather ability.…”

“…However, the spatial resolution of passive microwave remote sensing systems is usually so low (> 1 km) that they are not able to acquire the detailed information of snow (Foster et al, 1984). Generally speaking, passive microwave-based products are not suitable for mesoscale or micro-scale research and may result in confusion between wet snow, thin snow, and forest (Tait et al, 2000). In addition, because of the limitations of the imaging orbit gap, microwave-based products are subject to spatial gaps.…”