Abstract
Sea ice concentration (SIC) data acquired by passive microwave sensors at daily temporal frequencies over extended areas provide seasonal characteristics of sea ice dynamics and play a key role as an indicator of global climate trends; however, it is typically challenging to study long-term time series. Of the various advanced remote sensing techniques that address this issue, temporal mixture analysis (TMA) methods are often used to investigate the temporal characteristics of environmental factors, including SICs in the case of the present study. This study aims to forecast daily SICs for one year using a combination of TMA and time series modeling in two stages. First, we identify temporally meaningful sea ice signatures, referred to as temporal endmembers, using machine learning algorithms, and then we decompose each pixel into a linear combination of temporal endmembers. Using these corresponding fractional abundances of endmembers, we apply a autoregressive model that generally fits all Antarctic SIC data for 1979 to 2013 to forecast SIC values for 2014. We compare our results using the proposed approach based on daily SIC data reconstructed from real fractional abundances derived from a pixel unmixing method and temporal endmember signatures. The proposed method successfully forecasts new fractional abundance values, and the resulting images are qualitatively and quantitatively similar to the reference data.
Highlights
Sea ice dynamics play an important role in climate change and global warming studies by revealing high latitude temperature trends
We propose a novel approach of forecasting daily Sea ice concentration (SIC) for the present year (2014) using temporal mixture analysis (TMA) results derived from previous years (1979-2013) reported in Chi et al (2016) and using time series analysis models
The TMA stage is identical to the experimental part of the previous study (Chi et al, 2016) and is composed of three steps
Summary
Sea ice dynamics play an important role in climate change and global warming studies by revealing high latitude temperature trends. Sea ice in the Arctic has exhibited a long-term negative trend while sea ice in the Antarctic has been expanding for decades (Parkinson et al, 2012). Sea ice concentration (SIC) is typically estimated using passive microwave data because of the daily revisit cycle, the relatively low sensitivity to atmospheric water content and clouds, and the large contrast in emissivity between open water and sea ice (Comiso et al, 1997, Ivanova et al, 2014). TMA provides seasonal characteristics of univariate information such as SIC as well as a unique summary of long-term time series (Piwowar et al, 1998, Chi et al, 2016). In addition to sea ice studies, TMA has been applied to various applications in agriculture and urban studies
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
