Explore the vast range of titles available.

Lake level changes are critical indicators of hydrological balance and climate change, yet long‐term monthly lake level reconstruction is challenging with incomplete or short‐term data. Data‐driven models, while promising, struggle with nonstationary lake level changes and complex dependencies on meteorological factors, limiting their applicability. Here, we introduce the Hydroformer, a frequency domain enhanced multi‐attention Transformer model designed for monthly lake level reconstruction, utilizing reanalysis data. This model features two innovative mechanisms: (a) Frequency‐Enhanced Attention (FEA) for capturing long‐term temporal dependence, and (b) Causality‐based Cross‐dimensional Attention (CCA) to elucidate how specific meteorological factors influence lake level. Seasonal and trend patterns of catchment meteorological factors and lake level are initially identified by a time series decomposition block, then independently learned and refined within the model. Tested across 50 lakes globally, the Hydroformer excelled in reconstruction periods ranging from half to three times the training‐test length. The model exhibited good performance even when training data missing rates were below 50%, particularly in lakes with significant seasonal fluctuations. The Hydroformer demonstrated robust generalization across lakes of varying sizes, from 10.11 to 18,135 km2, with median values for R2, MAE, MSE, and RMSE at 0.813, 0.313, 0.215, and 0.4, respectively. Furthermore, the Hydroformer outperformed data‐driven models, improving MSE by 29.2% and MAE by 24.4% compared to the next best model, the FEDformer. Our method proposes a novel approach for reconstructing long‐term water level changes and managing lake resources under climate change. Plain Language Summary Lake water levels, as key indicators of hydrologic dynamics and catchment balance, are vital for understanding climate impacts and managing water resources. However, the lack of continuous measurements for most global lakes, combined with the inability of traditional data‐driven models to effectively decipher complex interactions with catchment hydrological processes, leads to significant gaps in generalizability, accuracy, and reconstructive length. Given these limitations, accurate monthly reconstructions of lake level remain a persistent challenge. To address this, we develop Hydroformer, an innovative frequency domain enhanced multi‐attention Transformer model, utilizing reanalysis data for monthly lake level reconstruction. It employs two innovative attention mechanisms: Frequency‐Enhanced Attention for capturing long‐term temporal dependencies and Causality‐based Cross‐dimensional Attention for cross‐dimensional causal dependencies between catchment meteorological factors and lake level. Through a decomposition block, the model efficiently recognizes and refines inherent seasonal and trend patterns, leading to a comprehensive understanding of lake behaviors. Through testing on 50 global lakes, the Hydroformer has exhibited exceptional performance in reconstructing water levels for lakes ranging from 10.11 to 18,135 km2, adeptly handling short‐term, long‐term, and varying proportions of data gaps. It notably outperforms supervised data‐driven models. This positions it as a vital instrument for monthly lake level reconstruction, showcasing the power of integrating advanced artificial intelligence techniques in hydrological modeling. Key Points A novel frequency domain enhanced multi‐attention Transformer model, Hydroformer, has been built for reconstructing monthly lake level using reanalysis data The model accurately extends reconstructions 2–3 times the training data length, excelling with less than 50% missing training data Hydroformer surpasses advanced AI‐based models, improving MSE and MAE by over 20% and demonstrating strong generalization across lakes of varying sizes

This study uses the Holocene lake sediment of Lake Ķūži (Latvia, Vidzeme Heights) for environmental reconstruction with multi-proxy records including lithology, computerised axial tomography scan, grain-size analysis, geochemistry, diatoms and macrofossils, supported by AMS radiocarbon dating. Numerical analyses (PCA; CONISS) reveal three main phases in the development of the lake. Response to the Lateglacial–Holocene transition in Lake Ķūži took place around 11,300 cal. BP. Organogenic sedimentation started with distinctive 5-cm-thick peat layer and was followed by lacustrine sedimentation of carbonaceous gyttja. Several findings of the peat layer with similar dated age and position at different absolute altitudes indicate that lake basin was formed by glaciokarstic processes. In the Early Holocene (until around 8,500 cal. BP), the lake was shallow and holomictic, surrounded by unstable catchment with erosion and inflow events. Predominance of diatom species of Cyclotella and Tabellaria, large numbers of respiratory horns of phantom midge pupae (Chaoboridae), high Fe/Mn ratio, as well as the presence of laminated sediments indicates the transition to a dimictic and oligo-mesotrophic lake conditions with high water level, anoxia in the near-bottom and stable catchment in the Middle Holocene (8,500–2,000 cal. BP). This contrasts with many hydrologically sensitive lakes in Northern and Eastern Europe in which the water level fell several meters during this period. During the Late Holocene (from 2,000 cal. BP to the present), the lithological and biotic variables reveal major changes, such as the increase in erosion (coarser grain-size fraction) and eutrophication [diatoms Aulacoseira ambigua (Grun.) Sim., Stephanodiscus spp., Cyclostephanos dubius (Fricke) Round]. Characteristics of lake-catchment system during the Late Holocene reflect anthropogenic signal superimposed on the natural forcing factors. To date, the Late Quaternary palaeolimnological reconstructions using lake sediment has been limited in the Baltic region. Therefore, findings from Lake Ķūži provide important information about environmental and climatic changes that took place in this part of Eastern Europe. This study shows that the relative importance of climate and local factors has varied over the time and it is essential to consider the lake basin topography, catchment size and land cover as potential dominant forcing factors for changes in sedimentary signal.

A multi-proxy investigation of two sediment cores from the large closed-basin Lake Qinghai provides evidence of abrupt changes in paleolimnological conditions across the late-glacial/Holocene transition. The chronology of the lacustrine sediment sequence is framed by four AMS ^sup 14^C ages for aquatic-plant macrofossil seeds. Four distinct stratigraphic units are identified on the basis of abrupt shifts in lithology, carbonate composition, δ^sup 18^O of authigenic carbonates, magnetic susceptibility characteristics, and total nitrogen content. These units represent four environmental stages that were each initiated by three abrupt changes in hydro-climatic regime at 11,600, 10,700, and 10,000 ^sup 14^C yrs B.P. Each of the four environmental stages thus represents a characteristic precipitation-to-evaporation balance for the lake catchment. The paleoenvironmental evidence indicates that the lake before 11,600 ^sup 14^C yrs B.P. was very shallow with carbonate production and organic productivity much lower than in the Holocene, suggesting a much colder and drier climate than in the Holocene. From 11,600 to 10,700 ^sup 14^C yrs B.P., the presence of clastic laminations and Ruppia fossil seeds suggests an increased inflow of sediment-laden waters into the lake. Between 10,700 and 10,000 ^sup 14^C yrs B.P., the development of a carbonate playa lake indicates that a negative water balance persisted. From 10,000 ^sup 14^C yrs B.P. an abrupt increase in rainfall is suggested by a sudden termination of the playa lake environment and the diluted lake waters, as evidenced by negative shift in both total carbonate content and δ^sup 18^O values of mineral carbonate. However, the lake level during the early Holocene was about 20 m shallower than today, indicating that the effective moisture then was much lower than it is today. The multi-proxy record suggests a step-wise pattern of climatic change across the late-glacial/Holocene transition along with abrupt shifts in P-E balance on the N. E. Tibet-Qinghai Plateau. This pattern is characterized by reorganization of Asian monsoon circulation, which probably was determined by increasing summer insolation and changes in surface boundary conditions accompanying regional deglaciation. The arid event at 10,700-10,000 ^sup 14^C yrs B.P. is interpreted as a Younger Dryas equivalent, although climatic cooling is not indicated by the evidence at hand.[PUBLICATION ABSTRACT]

Lakes provide important water resources and many essential ecosystem services. Some of Earth's largest lakes recently reached record‐low levels, suggesting increasing threats from climate change and anthropogenic activities. Yet, continuous monitoring of lake levels is challenging at a global scale due to the sparse in situ gauging network and the limited spatial or temporal coverage of satellite altimeters. A few pioneering studies used water areas and hypsometric curves to reconstruct water levels but suffered from large uncertainties due to the lack of high‐quality hypsometry data. Here, we propose a novel proxy‐based method to reconstruct multi‐decadal water levels from 1992 to 2018 for both large and small lakes using Landsat images and ICESat (2003–2009) and recently launched ICESat‐2 (2018+) laser altimeters. Using the new method, we evaluate reconstructed levels of 342 lakes worldwide, with sizes ranging from 1 to 81,844 km2. Reconstructed water levels have a median root‐mean‐square error (RMSE) of 0.66 m, equivalent to 57% of the standard deviation of monthly level variability. Compared with two recently reconstructed water level data sets, the proposed method reduces the median RMSE by 27%–32%. The improvement is attributable to the new method's robust construction of high‐quality hypsometry, with a median R2 value of 0.92. Most reconstructed water level time series have a bi‐monthly or higher frequency. Given that ICESat‐2 and Landsat can observe hundreds of thousands of water bodies, this method can be applied to conduct an improved global inventory of time‐varying lake levels and thus inform water resource management more broadly than existing methods. Key Points Landsat images and laser altimeters were leveraged to reconstruct multi‐decadal lake levels of both large and small lakes Reconstructed water levels were validated against observed levels on 342 global lakes with a median error of 0.66 m Most of the reconstructed lake level time series have a bi‐monthly or higher frequency

Relatively short records of Total Water Storage Anomalies (TWSA) from the Gravity Recovery and Climate Experiment (GRACE) and its Follow‐On (GRACE‐FO) missions have impeded our understanding of their full range and long‐term variability over the Lake Victoria Basin (LVB). This study introduces an Enhanced RecNet (ERecNet) to reconstruct the LVB's TWSA from 1971 to 2022 using precipitation and Lake Victoria's level data. ERecNet integrates a multi‐layer perceptron and a combination of gridded and basin‐averaged loss functions for improving reconstruction performance. Our results reveal that ERecNet can successfully reconstruct the LVB's TWSA variations, outperforming hydrological models and reanalysis products in capturing the TWSA trends and amplitudes. The reconstruction aligns closely with the lake level and precipitation patterns while effectively closing the LVB's water balance budget. This study provides the first reconstruction of both human‐ and climate‐driven TWSA data over the LVB, offering valuable insights into its long‐term hydrological variability. Plain Language Summary The Lake Victoria Basin (LVB) is an important region for millions of people, but understanding how its water storage changes over time has been challenging due to limited data. Satellite missions like GRACE and GRACE‐FO provide valuable information on water storage, but their observations only cover a short period. In this study, we developed a new model called ERecNet to fill in the gaps in data by reconstructing the LVB's water storage changes from 1971 to 2022. ERecNet uses rainfall data and Lake Victoria's water level to create a more accurate picture of how water storage has varied over the past 50 years. Our model performs better than other methods, such as hydrological models and reanalysis data sets, in capturing the ups and downs of water storage. This is the first time human and climate influences on water storage in the LVB have been reconstructed in such detail. The findings offer important insights into how the basin's water resources have changed over time and can help inform better management of this critical resource. Key Points An enhanced RecNet model for reconstructing total water storage anomalies (TWSA) is introduced over the Lake Victoria Basin (LVB) The reconstruction outperforms hydrological models and reanalysis products in capturing the LVB's TWSA trends and amplitudes The reconstructed TWSA effectively closes the LVB's water balance budget

We present a reference, comprehensive, high-resolution, digital mosaic of ice motion in Antarctica assembled from multiple satellite interferometric synthetic-aperture radar data acquired during the International Polar Year 2007 to 2009. The data reveal widespread, patterned, enhanced flow with tributary glaciers reaching hundreds to thousands of kilometers inland over the entire continent. This view of ice sheet motion emphasizes the importance of basal-slip—dominated tributary flow over deformation-dominated ice sheet flow, redefines our understanding of ice sheet dynamics, and has far-reaching implications for the reconstruction and prediction of ice sheet evolution.

Reconstruction of the catastrophic drainage following the Millennium Eruption (ME) of Changbaishan‐Tianchi volcano in 946 ± 20 CE is of great significance, as it contributes to improving the regional maximum flood record and develop rare flood risk analysis. However, limited knowledge exists concerning the failure mode, magnitude, and transport processes of the outburst flooding. In this work, we present a whole system model that describes the paleohydrology of catastrophic drainage using geological records along the downstream valley. The model encompasses the crater lake dynamics, an approximation of the breach erosion process and flood propagation downstream. The boulder competence method was used to constrain by reasonable flow parameters, while mitigating the uncertainty caused by the ambiguous geological paleostage indicators. Paleohydrologic analysis indicates that at least 1 km3 of water was released from the caldera, with the vertical breach erosion rates as high as 34 m/hr. Volcanic activity during the ME II may have directly contributed to triggering of the flood event. The local hydrodynamic response of the downstream riverbed captures the dynamic migration patterns of sediments across spatio‐temporal scales, offering a comprehensive interpretation of the specific scouring surfaces observed in the geological profile. The analysis of simulated inundation boundaries reveals that not all recorded inundations can be attributed to the crater lake outburst event. Reconstructions of megafloods based on downstream constraints on flood stage, velocity and discharge can help to infer and constrain the dynamics of dam failure mechanisms, and also contribute to our understanding of these complex paleohydrologic events. Plain Language Summary Based on the integration of geomorphologic information on megaflood and lahar deposits in the Changbaishan‐Tianchi volcanic field, the study discusses the transport processes and triggering conditions of catastrophic hydrologic events. Specifically, we present a whole system model that occurred a catastrophic drainage after the Millennium Eruption (ME). In the system, the dam erosion rate and the paleo‐lake level were treated as unknowns. A series of simulations serves to match dynamically simulated critical flow velocity with downstream geomorphic evidence, such as volcanic cone‐source boulders and flood deposits. The paleohydrologic analysis indicates that at least 1 km3 of water was released from the caldera, with the erosion rate as close as 34 m/hr. Volcanic activity in ME II may have directly contributed to the largest flood event. Moreover, the velocity constraint of boulder competence method excludes the scenario where the similar inundation area caused by unreasonable parameter combination. The reconstruction of the megaflood not only help to infer the dynamics and mean parameters of the dam failure mechanism, but also to reveal the complex spatial and temporal patterns of paleohydrologic events. Subsequently, the relevant inundation area of the single catastrophic flood event was corrected. Key Points A whole system model combining volcanic source boulder and outcrops was proposed to reconstruct catastrophic drainage Considering different outburst scenarios to ascertain the breach incision rate was 30–38 m/hr, and released nearly 1.2 km3 of water Correcting inundation area for the outburst flood event following the Millennium Eruption

In arid-zone water resource management and water-security assessment, changes in water-body volume are key indicators of water availability and regulation performance. However, arid-zone lakes often lack sufficient bathymetric information to constrain geometry under low lake-level conditions. Shrinkage-driven hydrological disconnection can destabilize extrapolation of water level–storage relationships. This increases uncertainty in quantifying long-term storage changes. Here, we develop a multi-digital elevation model (DEM) hypsometry framework to reconstruct near-monthly lake storage for 1993–2024, recovering storage during low-level periods without bathymetric surveys. Reconstructed changes agree with independent satellite altimetry (r = 0.93 for level and 0.90 for storage), outperforming above-water-only (r ≈ 0.637 for water level) and conventional model-selection base-lines (r ≈ 0.753 for water level). The framework was quantified across three scenarios: expanding lakes, lake systems and reservoirs, and terminally shrinking lakes. For the persistently shrinking Big Aral Sea, under the whole-lake modeling assumption, the Copernicus-based reconstruction provides a cumulative storage change of −214.3 km3, closest to the satellite altimetry estimate of −210.68 km3 among the tested DEMs. In contrast, other DEMs overestimate the 1993–2024 cumulative loss by 66.15–141.01 km3. Sub-lake modeling further adjusts the Shuttle Radar Topography Mission (SRTM)-based cumulative change to −248.38 km3, substantially reducing structural bias caused by lake disconnection. This study provides a transferable technical framework for lake storage reconstruction in arid regions under degraded low lake-level conditions and hydrological disconnection.

In 2023, Tropical Cyclone Freddy caused severe damage in southern Malawi, flooding much of the lowland area near Lake Chilwa and displacing many residents. This study evaluates long-term, region-specific mitigation strategies to lessen future risks, using a novel approach that combines drone and satellite data, building footprints, and 3D simulations to analyze how building elevation affects flood damage and assess Property-Level Flood Risk Adaptation measures. Results show a significant difference in ground elevation between affected and unaffected buildings, with damaged structures generally at lower levels. The 3D simulation confirmed a water-level rise of approximately 3.0 m caused by Freddy. Scenario analysis indicates that elevating buildings by 2.0, 2.5, and 3.0 m could reduce direct flood exposure and 64%, 76%, and 91% of damage, respectively. These insights can inform the development of targeted regional risk-mitigation strategies through Property-Level Flood Risk Adaptation in high-risk areas.

Long highly-resolved proxies for runoff are in high demand for hydrological forecasts and water management in arid Central Asia. An accurate (R2 = 0.53) reconstruction of October-September discharge of the Ili River in Kazakhstan, 1779–2015, is developed from moisture-sensitive tree rings of spruce sampled in the Tian Shan Mountains. The fivefold extension of the gauged discharge record represents the variability of runoff in the Lake Balkhash Basin for the last 235 years. The reconstruction shows a 40 year long interval of low discharge preceded a recent high peak in the first decade of the 2000s followed by a decline to more recent levels of discharge not seen since the start of the gauged record. Most reconstructed flow extremes (± 2σ) occur outside the instrumental record (1936–2015) and predate the start of large dam construction (1969). Decadal variability of the Ili discharge corresponds well with hydrological records of other Eurasian internal drainages modeled with tree rings. Spectral analysis identifies variance peaks (highest near 42 year) consistent with main hemispheric oscillations of the Eurasian climatic system. Seasonal comparison of the Ili discharge with sea-level-pressure and geopotential height data suggests periods of high flow likely result from the increased contribution of snow to runoff associated with the interaction of Arctic air circulation with the Siberian High-Pressure System and North Atlantic Oscillation.