Although hyperspectral images capture very detailed information about the scanned objects, their efficient analysis, transfer, and storage are still important practical challenges due to their large volume. Classifying and segmenting such imagery are the pivotal steps in virtually all applications, hence developing new techniques for these tasks is a vital research area. Here, deep learning has established the current state of the art. However, deploying large-capacity deep models on-board an Earth observation satellite poses additional technological challenges concerned with their memory footprints, energy consumption requirements, and robustness against varying-quality image data, with the last problem being under-researched. In this paper, we tackle this issue, and propose a set of simulation scenarios that reflect a range of atmospheric conditions and noise contamination that may ultimately happen on-board an imaging satellite. We verify their impact on the generalization capabilities of spectral and spectral-spatial convolutional neural networks for hyperspectral image segmentation. Our experimental analysis, coupled with various visualizations, sheds more light on the robustness of the deep models and indicate that specific noise distributions can significantly deteriorate their performance. Additionally, we show that simulating atmospheric conditions is key to obtaining the learners that generalize well over image data acquired in different imaging settings.

Although deep learning is gaining more widespread use in hyperspectral image analysis, it is challenging to train high-capacity models in a supervised way—ground-truth sets are expensive to obtain, and they are practically always extremely imbalanced. To deal with the problem of missing ground-truth data, its high dimensionality and potential redundancy, we introduce a novel unsupervised feature learning technique to extract discriminative features from the original data. It exploits recurrent neural network-based asymmetric autoencoders (AEs) to learn the compressed representation of unlabeled data, and can elaborate both spectral and spectral–spatial features. Our extractors can be incorporated into the unsupervised segmentation pipeline—they can be followed by any clustering algorithm. The experiments revealed that our approaches deliver high-quality segmentation without any prior class labels, and are one order of magnitude faster than 3-D convolutional AEs. Our algorithms outperform or work on par with other approaches while allowing for significant data reduction.

Hyperspectral images capture very detailed information about scanned objects and, hence, can be used to uncover various characteristics of the materials present in the analyzed scene. However, such image data are difficult to transfer due to their large volume, and generating new ground-truth datasets that could be utilized to train supervised learners is costly, time-consuming, very user-dependent, and often infeasible in practice. The research efforts have been focusing on developing algorithms for hyperspectral data classification and unmixing, which are two main tasks in the analysis chain of such imagery. Although in both of them, the deep learning techniques have bloomed as an extremely effective tool, designing the deep models that generalize well over the unseen data is a serious practical challenge in emerging applications. In this paper, we introduce the deep ensembles benefiting from different architectural advances of convolutional base models and suggest a new approach towards aggregating the outputs of base learners using a supervised fuser. Furthermore, we propose a model augmentation technique that allows us to synthesize new deep networks based on the original one by injecting Gaussian noise into the model’s weights. The experiments, performed for both hyperspectral data classification and unmixing, show that our deep ensembles outperform base spectral and spectral-spatial deep models and classical ensembles employing voting and averaging as a fusing scheme in both hyperspectral image analysis tasks.

Maintaining farm sustainability through optimizing the agricultural management practices helps build more planet-friendly environment. The emerging satellite missions can acquire multispectral and hyperspectral imagery which captures more detailed spectral information concerning the scanned area, hence allows us to benefit from subtle spectral features during the analysis process in agricultural applications. We introduce an approach for extracting 2.5-m cultivated land maps from 10-m Sentinel-2 (S-2) multispectral image (MSI) series which benefits from a compact graph convolutional neural network. The experiments indicate that our models not only outperform classical and deep machine learning techniques through delivering higher quality segmentation maps, but also dramatically reduce the memory footprint when compared to U-Nets (almost 8k trainable parameters of our models, with up to 31-M parameters of U-Nets). Such memory frugality is pivotal in the missions which allow us to uplink a model to the artificial intelligence (AI)-powered satellite once it is in orbit, as sending large nets is impossible due to the time constraints.

Hyperspectral unmixing remains one of the most challenging tasks in the analysis of such data. Deep learning has been blooming in the field and proved to outperform other classic unmixing techniques, and it can be effectively deployed onboard Earth observation satellites equipped with hyperspectral imagers. In this letter, we follow this research pathway and propose a multibranch convolutional neural network that benefits from fusing spectral, spatial, and spectral–spatial features in the unmixing process. The results of our experiments, backed up with the ablation study, revealed that our techniques outperform others from the literature and lead to higher quality fractional abundance estimation. Also, we investigated the influence of reducing the training sets on the capabilities of all algorithms and their robustness against noise, as capturing large and representative ground-truth sets is time-consuming and costly in practice, especially in emerging Earth observation scenarios.

Enhancing agricultural methods through the utilization of Earth observation and artificial intelligence (AI) has emerged as a significant concern. The ability to quantify soil parameters on a large scale can play a pivotal role in optimizing the fertilization process. While techniques for noninvasive estimation of soil parameters from hyperspectral images (HSIs) exist, their validation typically occurs across different datasets and employs varying validation protocols. This diversity renders them inherently challenging (or even impossible) to compare objectively.