The study trains a convolutional LSTM on ten annual Earth Observation variables to forecast desertification dynamics in Ceará, Brazil, achieving modest improvements over persistence and capturing 53‑69% of the regional degradation trend. While the model slightly outperforms simple baselines one to four years ahead, it explains only a small fraction of cell‑level variance, indicating that EO data are more reliable for regional trends than for individual pixel predictions. The authors also demonstrate that elevation and EVI channels degrade forecast skill, and use Monte Carlo dropout to quantify uncertainty in future degradation maps.
arXiv:2607. 04117v1 Announce Type: new Abstract: ERA5 seasonal climate variables contain predictive information about future glacier retreat beyond what satellite imagery alone provides, yet existing deep learning methods focus on mapping current boundaries rather than forecasting future ones.
arXiv:2605. 13566v2 Announce Type: replace Abstract: Land Surface Temperature (LST) is a key variable for various applications, such as urban climate and ecology studies.
arXiv:2606. 23833v1 Announce Type: new Abstract: Terrestrial water storage (TWS) integrates snow, soil moisture, surface water, and groundwater and is a key indicator of how climate variability and human activity reshape the global water cycle.
arXiv:2606. 27277v1 Announce Type: new Abstract: Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under changing meteorological conditions.
The paper introduces a lightweight deep learning framework that forecasts Brazilian soybean yields using only routine weather data and two simple static inputs (crop year and agro-environmental label). Across 20 seasons, transformer-based models achieved the highest accuracy, outperforming traditional ridge regression and a moving‑average baseline by nearly 48%. Ablation studies show that the static inputs and spatial expansion improve performance without adding complexity, and SHAP analysis highlights the importance of crop year and weather variables in driving yield variations.
arXiv:2607. 04190v1 Announce Type: new Abstract: Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularly in mountainous regions where temperature can vary by several degrees over short distances.
arXiv:2602. 16579v2 Announce Type: replace-cross Abstract: Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer from a performance gap when transitioning from historical reanalysis to operational forecast products.
arXiv:2610.02248v1 Announce Type: new Abstract: Operational land surface forecasting systems built on Mamba-family Structured State Space Models absorb non-stationary confounding events (unrecorded i...
The paper presents a Vision Transformer-based model for subseasonal soil‑moisture forecasting over Europe, showing that forecast skill depends heavily on how the prediction problem is formulated. By using residual learning and forecasting root‑zone soil moisture in physical units, the model outperforms persistence and existing deep‑learning and ECMWF baselines, providing well‑calibrated probabilistic predictions. However, predicting flash drought onset—defined by rapid multi‑pentad intensification—remains a challenge shared by all current subseasonal‑to‑seasonal systems.
arXiv:2608. 09966v1 Announce Type: cross Abstract: European summer warming reflects interactions among background change, persistent ocean--land--circulation states, and same-season variability.
arXiv:2608. 11638v1 Announce Type: new Abstract: Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable.
The paper introduces RNN Maxent, a new extension of the Maxent species distribution modelling framework that replaces its fixed linear feature dictionary with a neural network—specifically a Gated Recurrent Unit (GRU)—trained end‑to‑end via backpropagation. This approach retains Maxent’s presence‑only statistical foundations, background normalisation, and probability calibration while learning nonlinearity directly from data. Applied to Desert Locust distribution modelling using 50‑day environmental time‑series, RNN Maxent outperforms standard Maxent, achieving higher ROC AUC (0.862 vs. 0.792) and F1 scores (0.671 vs. 0.590).