Next Article in Journal
Using Spatial Semantics and Interactions to Identify Urban Functional Regions
Next Article in Special Issue
Foreword to the Special Issue on Machine Learning for Geospatial Data Analysis
Previous Article in Journal
Revealing Recurrent Urban Congestion Evolution Patterns with Taxi Trajectories
Previous Article in Special Issue
Generative Street Addresses from Satellite Imagery
Article Menu
Issue 4 (April) cover image

Export Article

Open AccessFeature PaperArticle
ISPRS Int. J. Geo-Inf. 2018, 7(4), 129; https://doi.org/10.3390/ijgi7040129

Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders

Technical University of Munich, Arcisstraße 21, 80333 Munich, Germany
*
Author to whom correspondence should be addressed.
Received: 22 January 2018 / Revised: 13 March 2018 / Accepted: 17 March 2018 / Published: 21 March 2018
(This article belongs to the Special Issue Machine Learning for Geospatial Data Analysis)
Full-Text   |   PDF [7805 KB, uploaded 3 May 2018]   |  

Abstract

Earth observation (EO) sensors deliver data at daily or weekly intervals. Most land use and land cover classification (LULC) approaches, however, are designed for cloud-free and mono-temporal observations. The increasing temporal capabilities of today’s sensors enable the use of temporal, along with spectral and spatial features.Domains such as speech recognition or neural machine translation, work with inherently temporal data and, today, achieve impressive results by using sequential encoder-decoder structures. Inspired by these sequence-to-sequence models, we adapt an encoder structure with convolutional recurrent layers in order to approximate a phenological model for vegetation classes based on a temporal sequence of Sentinel 2 (S2) images. In our experiments, we visualize internal activations over a sequence of cloudy and non-cloudy images and find several recurrent cells that reduce the input activity for cloudy observations. Hence, we assume that our network has learned cloud-filtering schemes solely from input data, which could alleviate the need for tedious cloud-filtering as a preprocessing step for many EO approaches. Moreover, using unfiltered temporal series of top-of-atmosphere (TOA) reflectance data, our experiments achieved state-of-the-art classification accuracies on a large number of crop classes with minimal preprocessing, compared to other classification approaches. View Full-Text
Keywords: deep learning; multi-temporal classification; land use and land cover classification; recurrent networks; sequence encoder; crop classification; sequence-to-sequence; Sentinel 2 deep learning; multi-temporal classification; land use and land cover classification; recurrent networks; sequence encoder; crop classification; sequence-to-sequence; Sentinel 2
Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Rußwurm, M.; Körner, M. Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders. ISPRS Int. J. Geo-Inf. 2018, 7, 129.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
ISPRS Int. J. Geo-Inf. EISSN 2220-9964 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top