Buildings that are rotated with respect to the sensor trajectory could be erroneously classified as vegetated areas in the Pauli basis, and subsequently in many decomposition theorems despite the considerable amount of work done to solve that issue. This misjudgement is linked to the high level of their cross-polarized contribution. Using electromagnetic simulation tools and image analysis, we study the value of these cross-polarization components. We show that forested areas and cities exhibit significantly different cross-polarization levels; indeed, the origin of these components is actually distinct. Based on that, to discriminate between the two environments, we introduce an extension to the Pauli basis where the cross polarization is split into two classes, one for rotated dihedrals and the other for random scatterers. This approach is then tested on two synthetic aperture radar images: the first acquired at C-band using RADARSAT-2 over Downtown San Francisco and the second using RAMSES at X-band over an industrial area near Paris.

With an increase in the amount of natural disasters, the combined use of cloud-penetrating Synthetic Aperture Radar and deep learning becomes unavoidable for their monitoring. This article proposes a methodology for forest fire detection using unsupervised location-expert autoencoders and Sentinel-1 SAR time series. The models are trained on SAR multitemporal images over a specific area using a reference period and extract any deviating time series over that same area for the test period. We present three variations of the autoencoder, incorporating either temporal features or spatiotemporal features, and we compare it against a state-of-the-art supervised autoencoder. Despite their limitations, we show that unsupervised approaches are on par with supervised techniques, performance-wise. A specific architecture, the fully temporal autoencoder, stands out as the best-performing unsupervised approach by leveraging temporal information of Sentinel-1 time series using one-dimensional convolutional layers. The approach is generic and can be applied to many applications, though we focus here on forest fire detection in Canadian boreal forests as a successful use case.

Polarimetric Synthetic Aperture Radar (PolSAR) images containing cities may exhibit misclassified areas when using polarimetric decompositions. Several articles relate this problem to the effects of orientation between the facades of buildings and the acquisition trajectory. Materials also play a role in polarimetric behavior. This paper deals with this combined effect of material and orientation. It analyzes different sets of data, airborne or space-borne, at L-, C- and X-bands, and for different orientation angles. It shows that considering dielectric dihedral rather than metallic in the polarimetric mechanism of double-bounce has a very important impact on the differences of intensities between the channels HH and VV. This difference is very important for small angles of orientation, and then decreases for large angles. Furthermore, the curves of the ratios between polarimetric intensities as a function of the orientation angle vary little with the materials and the frequencies encountered in all the scenarios envisaged. The signal of the ratio VV/HH raises a plateau around −1 dB for orientations higher than 30°. We also observe a plateau for HV/HH, but with a value around −5 dB.

We present a fully unsupervised learning pipeline, which involves both a projection method and a clustering algorithm dedicated to the pixel-wise classification of multitemporal SAR images. We design a Convolutional Autoencoder as the method to project our time series onto a lower dimensional latent space, where semantically similar temporal signals are placed close together. The additional use of convolutional layers as feature extraction steps allows us to exploit the sequential nature of time series, exhibiting higher representation performance than fully connected layers. The extracted clusters can encapture different semantic levels to either separate classes or extract outlying temporal signals. The application of this method to crop-types mapping enables the extraction of major crop-types within a scene, without supervision. In a labeled context, this method also allows for the extraction of outlying profiles which can lead to the discovery of mislabeled time series.

This paper aims to quantify the errors in the provided agricultural crop types, estimate the possible error rate in the available dataset, and propose a correction strategy. This quantification could establish a confidence criterion useful for decisions taken on this data or to have a better apprehension of the possible consequences of using this data in learning downstream functions such as classification. We consider two agricultural label errors: crop type mislabels and mis-split crops. To process and correct these errors, we design a two-step methodology. Using class-specific convolutional autoencoders applied to synthetic aperture radar (SAR) time series of free-to-use and temporally dense Sentinel-1 data, we detect out-of-distribution temporal profiles of crop time series, which we categorize as one out of the three following possibilities: crop edge confusion, incorrectly split crop areas, and potentially mislabeled crop. We then relabel crops flagged as mislabeled using an Otsu threshold-derived confidence criteria. We numerically validate our methodology using a controlled disruption of labels over crops of confidence. We then compare our methods to supervised algorithms and show improved quality of relabels, with up to 98% correct relabels for our method, against up to 91% for Random Forest-based approaches. We show a drastic decrease in the performance of supervised algorithms under critical conditions (smaller and larger amounts of introduced label errors), with Random Forest falling to 56% of correct relabels against 95% for our approach. We also explicit the trade-off made in the design of our method between the number of relabels, and their quality. In addition, we apply this methodology to a set of agricultural labels containing probable mislabels. We also validate the quality of the corrections using optical imagery, which helps highlight incorrectly cut crops and potential mislabels. We then assess the applicability of the proposed method in various contexts and scales and present how it is suitable for verifying and correcting farmers’ crop declarations.