The competitiveness and innovation of the EU space sector depend on high educational standards and the availability of skilled professionals in the field, as well as the possibility for these professionals to enhance and update their skills through their careers to adapt to changing circumstances. This paper summarizes the collection and analysis of different educational programs in the space sector across the EU-27+UK. We identified and analyzed 3591 courses offered by 132 Degree Programs (DPs) at Bachelor (25 DPs) and Master (107 DPs) levels, 19 PhD programs, and 60 continuous education courses. The identified programs, learning objectives, and course descriptions have been mapped across different segments of the value chain of space activities (upstream, midstream, and downstream) and space-relevant knowledge domains and knowledge areas taxonomy. We created a structured and curated online catalog, that allows users to search, and retrieve the education offers in the space-related sectors.

Clouds in optical images are inevitable and can adversely affect subsequent analysis. Given that SAR imagery remains unaffected by cloud cover, many cloud removal methods involve the fusion of SAR and optical imagery. Unfortunately, existing methods for cloud removal through SAR-optical image fusion are computationally intensive and time-consuming, limiting their practical application. To address these challenges, this paper proposes a novel multi-feature fusion network (MFFNet) for SAR-optical image fusion, aiming to remove clouds from optical images effectively. The proposed method was applied to global and all-season Sentinel-1 and Sentinel-2 images. Quantitative experiments demonstrate that MFFNet achieves high accuracy and efficiency. Specifically, our method obtains an SSIM value of 87.10 and a speed of 25.97 FPS.

Field-Level cereal yield estimation using Machine Learning (ML) models poses a significant challenge especially when applied across large areas. A large sample size is required to represent the high yield variability caused by varying topographic and climatic conditions. To enhance ML-based prediction accuracy, we propose to decompose the complexity of agricultural landscape using landforms and agro-ecological zones and use these classes as spatially explicit constraints to partition field samples. We trained three ML models using remote sensing data to estimate wheat yield. When training ML models without the mentioned spatial constraints, we achieved an R2=0.58 and RMSE=840kg/ha. Training ML separately across various landform classes increase the accuracy. For instance, wheat yield cultivated in plain areas was predicted with R2=0.72, and RMSE=809kg/ha. These results emphasized the potential of training ML separately across main landform classes for improving the accuracy of yield predictions across diverse geographical contexts.

Clouds in remote sensing optical images often obscure essential information. They may lead to occlusion or distortion of ground features, thereby affecting the subsequent analysis and extraction of target information. Therefore, the removal of clouds in optical images is a critical task in various applications. SAR-optical image fusion has achieved encouraging performance in the reconstruction of cloud-covered information. Such methods, however, are extremely time-consuming and computationally intensive, making them difficult to apply in practice. This letter proposes a novel Feature Pyramid Network (FPNet) that effectively reconstructs the missing optical information. FPNet enables the extraction and fusion of multi-scale features from the SAR image and the cloudy optical image, as the FPNet leverages the power of convolutional neural networks by merging the feature maps from different scales. It can learn useful features efficiently because it downsamples the input images while preserving important information, thus reducing the computational workload. Experiments are conducted on a benchmark global SEN12MS-CR dataset and a regional South Sudan dataset. Results are compared with those of state-of-the-art methods such as DSen2-CR and GLF-CR. The experimental results demonstrate that FPNet accomplishes superior performance in terms of accuracy and visual effects. Both the inference and training speeds of FPNet are fast. Specifically, it runs at 96 FPS and requires less than four hours to train a single epoch using SEN12MS-CR on two 2080ti GPUs. Therefore, it is suitable for applying to various study areas.

We consider the problem of cost effective active learning for semantic segmentation, which aims at reducing the efforts of semantically annotating images. Current studies have ignored the inclusion of cost of labeling into their active learning frameworks. To this end, we first present a novel cost prediction module based on what we call the M-Net. M-Net combines the power of unsupervised W-Net and supervised U-Net to compute a refined segmentation map. The refined segmentation map is used to estimate the cost of annotations. The cost of annotation is estimated by the number of clicks required to annotate an image. To solve this task, we make use of the harris corner detector algorithm to estimate the location of the clicks required to annotate an image. Finally, we employ a multi armed bandit setting to minimize the cost of annotations while maximizing the performance of the semantic segmentation task. The M-Net outperforms fully supervised U-Net with +4.37 Acc and +3.75 mIoU. The proposed active learning framework also outperforms the existing baselines to prove the relevance of the approach in the current paradigm.

Tree species-level information is essential for effective forest management, conservation, policy development, and utilization. The availability of hyperspectral data creates new possibilities for species mapping. This study mapped tropical tree species in Shimoga, Karnataka, India by using the Airborne Visible and Infrared Imaging Spectrometer - Next Generation (AVIRIS-NG) hyperspectral data. Species mapping was performed by modifying the Random forest (RF) classifier using Principal Component Analysis (PCA) to transform the variables at each node into another space. The performance of PCA-based Rotation Random Forest (RoRF), was then compared with RF and Support Vector Machine (SVM), where RoRF outperformed both of them. A total of 20 tropical tree species were classified, highlighting the potential of the AVIRIS-NG data for species-level classification.

The goal of this work is to investigate the potential of PRecursore IperSpettrale della Missione Applicativa (PRISMA) hyperspectral data to predict the concentration of four macronutrients (K, P, N, S) and four micronutrients (Ca, Fe, Mg, Zn) in final wheat production. All investigated nutrients are essential to improving human nutrition. The initial findings indicate accurate predictions for Zn, P, Mg, S, K, Ca and Fe (R2 ranging from 0.57 to 0.74). N was less accurately estimated (R2 of 0.49). We conclude that the foliar chemical properties and temporal dynamics as detected by hyperspectral data translate successfully to the target micro- and macronutrients composition of the wheat production.

Information on cultivated crops is relevant for a large number of food security studies. Different scientific efforts are dedicated to generate this information from remote sensing images by means of machine learning methods. Unfortunately, these methods do not take account of the spatial-temporal relationships inherent in remote sensing images. In our paper, we explore the capability of a 3D Fully Convolutional Neural Network (FCN) to map crop types from multi-temporal images. In addition, we propose the Intersection Over Union (IOU) loss function for increasing the overlap between the predicted classes and ground reference data. The proposed method was applied to identify soybean and corn from a study area situated in the US corn belt using multi-temporal Landsat images. The study shows that our method outperforms related methods, obtaining a Kappa coefficient of 91.8%. We conclude that using the IOU loss function provides a superior choice to learn individual crop types.

Earth Observation (EO) to produce policy-driven information on slums has been receiving increasing attention amongst experts. However, the geo-ethical concerns associated with making slum information publicly available are commonly neglected among the EO community. This study analysed the geo-ethics in terms of technology, product, and application-level using topic-focused interviews in the Greater Accra Region, Ghana. We identified that potential users have little knowledge of machine learning-based slum mapping methods, which implies the need for technology and product documentation to improve the acceptability and usability of EO data. We observed an application mismatch among institutions. While NGOs and research institutions required data for pro-poor initiatives, most government institutions needed data for slum eradication. Such mismatches require a rethinking of how slum data should be made public. We present a guide to disseminate information to users in support of developing a global slum data repository.