Abstract

ABSTRACT In this study, we assess the potential of X-band Interferometric Synthetic Aperture Radar imagery for automated classification of sea ice over the Baltic Sea. A bistatic SAR scene acquired by the TanDEM-X mission over the Bothnian Bay in March of 2012 was used in the analysis. Backscatter intensity, interferometric coherence magnitude, and interferometric phase have been used as informative features in several classification experiments. Various combinations of classification features were evaluated using Maximum likelihood (ML), Random Forests (RF) and Support Vector Machine (SVM) classifiers to achieve the best possible discrimination between open water and several sea ice types (undeformed ice, ridged ice, moderately deformed ice, brash ice, thick level ice, and new ice). Adding interferometric phase and coherence-magnitude to backscatter-intensity resulted in improved overall classification performance compared to using only backscatter-intensity. The RF algorithm appeared to be slightly superior to SVM and ML due to higher overall accuracies, however, at the expense of somewhat longer processing time. The best overall accuracy (OA) for three methodologies were achieved using combination of all tested features were 71.56, 72.93, and 72.91% for ML, RF and SVM classifiers, respectively. Compared to OAs of 62.28, 66.51, and 63.05% using only backscatter intensity, this indicates strong benefit of SAR interferometry in discriminating different types of sea ice. In contrast to several earlier studies, we were particularly able to successfully discriminate open water and new ice classes.

Highlights

  • I ntr o d u cti o n S y nt h eti c A p ert ur e R a d ar ( S A R) d at ahavebeen us edtomo nit or i c e- c o v er e d m ariti m e r e gi o ns f or a p pr o xi m at el y t hr eedecad es ( R ess el, Fr ost, andLehn er 2 0 1 5 )

  • T h us, wecancon cl udeth at di ff er e n c es b et weenRF wit hMLandSVM cl assi fi ers w er e r e m ar k a bl e f or u n d ef or medice, ri dgedice, m o d er at el y d ef or mediceand br as hiceb ut w er e n ot c o nsi d er a bl e f or newice, t hi cklev el iceandopenw at er cl ass es

  • Als o di ff er e n c es b et weenRF wit hMLandSVM cl assi fi ers w er e r e m ar k a bl e f or u n d ef or medice, ri dgedice, m o d er at el y d ef or mediceand br as hiceb ut w er e n ot c o nsi d er a bl e f or newice, t hi cklev el iceandopenw at er cl ass es

Read more

Summary

ABSTR ACT

I n t his st u d y, w e ass ess t h e p ot e nti al of X- bandI nt erf er o m etri c S y nt h eti c A p ert ur e R a d ar i m a g er y f or a ut o m at e d cl assi fi c ati o n of seaiceov er t h e B alti c S e a. T h e p arti c ul ar o bj e cti v es of t his st u d y ar e: (i) t o ass ess t h e p ot e nti al of v ari o us SARfe at ur es, s u c h as b a c ks c att er-i nt e nsit y, i nt erf er o m etri c c o h er e n c e- m a g nit udeandi nt erf er o m etri c p h as e, as w ell as t h eir c o m bi n ati o ns, f or c h ar a ct eri zi ngseaice usi n g X- bandSARd at a a n d, (ii) t o d et er mi n e w hi c h cl assi fi c ati o n m et h o d ( R F, M L, S V M) is m or e s uit a bl e f or i nf erri ngseaicetyp es usi n g st u di edInSARfe at ur es. D es cri pti o n of seaice cl ass es

Ne wice
Ri dgedice
Br as h i c e
Ackno wl edgme nt s

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

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.