Masked image modeling (MIM), a common selfsupervised learning (SSL) technique, has been extensively studied for remote sensing image processing. Nevertheless, its effectiveness for hyperspectral imagery (HSI) remains underexplored due to the distinct data structures and high dimensionality. This paper aims to provide a detailed understanding of MIM from different perspectives of representation learning and statistical analysis for HSI classification tasks. Our study reveals that the MIM paradigm injects inductive bias in the attention mechanism of the transformer model, which is advantageous for capturing the local discrepancies between the spectra. We also show that MIM can increase the diversity of the attention heads in every layer, which is beneficial for the model in extracting more discriminative features from different spectral bands. The similarity of representations from various layers further proves this. Furthermore, our investigation highlights how MIM introduces a dynamic perspective to spectral representations, enabling the model to learn more robust and discriminative features. The final numerical experiments indicate that a moderate mask ratio can enhance the performance of downstream tasks. This suggests that designing a more targeted masking strategy might be necessary to achieve higher and more stable gains in downstream task performance. Without bells and whistles, the vanilla MIM improves the overall classification accuracy by an average of 2.69% over its SL counterpart. We hope that our findings can advance the understanding of MIM in HSI and inspire the design of a more stable SSL paradigm for HSI processing.

Advancements in Earth system science have seen a surge in diverse datasets. Earth System Data Cubes (ESDCs) have been introduced to efficiently handle this influx of high-dimensional data. ESDCs offer a structured, intuitive framework for data analysis, organising information within spatio-temporal grids. The structured nature of ESDCs unlocks significant opportunities for Artificial Intelligence (AI) applications. By providing well-organised data, ESDCs are ideally suited for a wide range of sophisticated AI-driven tasks. An automated framework for creating AI-focused ESDCs with minimal user input could significantly accelerate the generation of task-specific training data. Here we introduce cubo, an open-source Python tool designed for easy generation of AI-focused ESDCs. Utilising collections in SpatioTemporal Asset Catalogs (STAC) that are stored as Cloud Optimised GeoTIFFs (COGs), cubo efficiently creates ESDCs, requiring only central coordinates, spatial resolution, edge size, and time range.

Accurate quantification of Gross Primary Production (GPP) is crucial for understanding terrestrial carbon dynamics. It represents the largest atmosphere-to-land CO2flux, especially significant for forests. Eddy Covariance (EC) measurements are widely used for ecosystem-scale GPP quantification but are globally sparse. In areas lacking local EC measurements, remote sensing (RS) data are typically utilised to estimate GPP after statistically relating them to in-situ data. Deep learning offers novel perspectives, and the potential of recurrent neural network architectures for estimating daily GPP remains underexplored. This study presents a comparative analysis of three architectures: Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs), and Long-Short Term Memory (LSTMs). Our findings reveal comparable performance across all models for full-year and growing season predictions. Notably, LSTMs outperform in predicting climate-induced GPP extremes. Furthermore, our analysis highlights the importance of incorporating radiation and RS inputs (optical, temperature, and radar) for accurate GPP predictions, particularly during climate extremes.

In recent years, there has been a growing interest in using image super-resolution (SR) techniques in remote sensing. These techniques aim to reconstruct high-resolution (HR) imagery from low-resolution (LR) sources. Despite the development of sophisticated SR methodologies, determining what constitutes ‘good’ SR is still a matter of debate. Present-day literature often presents SR models through a strong computer vision perspective, heavily relying on synthetic datasets. Moreover, commonly used metrics often prioritize attributes that do not necessarily correspond to improvements in spatial resolution. To address this challenge, we presentOpenSR-test, a comprehensive benchmark designed exclusively for evaluating SR of remote sensing images. Our framework incorporates specific quality metrics and curated cross-sensor datasets, each spanning various scale factors with consistent metadata. UtilizingOpenSR-test, we evaluate state-of-the-art SR algorithms from a remote sensing perspective. TheOpenSR-testframework and datasets are publicly available at https://esaopensr.github.io/opensr-test/.

In Earth observation, deep learning models rely heavily on comprehensive datasets for training and evaluation. However, the relevance of data quality is often underestimated, leading to subpar generalization in real-world remote sensing scenarios. This study aims to bridge this gap by proposing a straightforward method to identify critical human annotation errors in semantic segmentation datasets. The approach is based on two indices: trustworthiness and hardness. By implementing these indices, we estimate the extent of human annotation errors in CloudSEN12, a global dataset specifically designed for cloud detection in Sentinel-2 imagery. Considering only the trustworthiness index, our approach identified 1794 potential labelling errors among 10,000 image patches. Out of these, 106 were confirmed as human errors, resulting in a true positive rate of 9.86%. When this method was applied to other extensive cloud masking datasets, such as KappaSet and Sentinel-2 Cloud Mask Catalogue, it was found that over 44% of the human labels were inaccurate. These results do not imply the inferior quality of these datasets, instead, they highlight the considerable shift between the annotation protocols, making inter-dataset benchmarking exercises inequitable.

This paper introduces DTACSNet, a Convolutional Neural Network (CNN) model specifically developed for efficient onboard atmospheric correction and cloud detection in optical Earth observation satellites. The model is developed with Sentinel-2 data. Through a comparative analysis with the operational Sen2Cor processor, DTACSNet demonstrates a significantly better performance in cloud scene classification (F2 score of 0.89 for DTACSNet compared to 0.51 for Sen2Cor v2.8) and a surface reflectance estimation with average absolute error below 2% in reflectance units. Moreover, we tested DTACSNet on hardware-constrained systems similar to recent deployed missions and show that DTACSNet is 11 times faster than Sen2Cor with a significantly lower memory consumption footprint. These preliminary results highlight the potential of DTACSNet to provide enhanced efficiency, autonomy, and responsiveness in onboard data processing for Earth observation satellite missions.