Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders

By Marc Rußwurm, Marco Körner. ISPRS Int. J. Geo Inf., 2018

339 citations recorded by the source corpus.

Earth observation (EO) sensors deliver data with daily or weekly temporal resolution. Most land use and land cover (LULC) approaches, however, expect cloud-free and mono-temporal observations. The increasing temporal capabilities of today's sensors enables 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 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, which 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, we achieved in our experiments state-of-the-art classification accuracies on a large number of crop classes with minimal preprocessing compared to other classification approaches.

Subfields: Ecology, Global and Planetary Change, Media Technology

View Paper: https://www.semanticscholar.org/paper/900630185a31b573fefd7fd2195b93c80df8cdb3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Global and Planetary Change

In Media Technology

Citations in the corpus

Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery (2018, methodology): “and RNN [22], [23], [37]–[39] are well-established techniques for remote sensing applications, to the best of our”
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series (2018, positive): “First developed for sequential data, RNN models have been recently applied to several classification tasks in remote sensing, especially for crop mapping [45,46,48].”
Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification (2020, positive): “To exploit both spatialandtemporalinformationofhigh-resolutionSITS,hybrid architecturescombiningconvolutionalandrecurrentlayers[24], [25]andconvolutional-recurrentneuralnetworks[26]havebeen introducedandcomprehensivelycompared[27].”
Self-Attention for Raw Optical Satellite Time Series Classification (2019, background): “To utilize both spatial and temporal features from the time series, combinations of convolutional layers with recurrent layers [43, 42] and convolutional-recurrent networks [51] have been explored and comprehensively compared in [49].”