Improving the explainability of CNN-LSTM-based flood prediction with integrating SHAP technique DOI Creative Commons
Hao Huang,

Zhaoli Wang,

Yaoxing Liao

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 84, P. 102904 - 102904

Published: Nov. 17, 2024

Language: Английский

A systematic review of climate change science relevant to Australian design flood estimation DOI Creative Commons
Conrad Wasko, Seth Westra, Rory Nathan

et al.

Hydrology and earth system sciences, Journal Year: 2024, Volume and Issue: 28(5), P. 1251 - 1285

Published: March 15, 2024

Abstract. In response to flood risk, design estimation is a cornerstone of planning, infrastructure design, setting insurance premiums, and emergency planning. Under stationary assumptions, guidance the methods used in are firmly established practice mature their theoretical foundations, but under climate change, still its infancy. Human-caused change influencing factors that contribute risk such as rainfall extremes soil moisture, there need for updated guidance. However, barrier updating translation science into practical application. For example, most pertaining historical changes focuses on examining trends annual maximum events or application non-stationary frequency analysis. Although this valuable, practice, exceedance probabilities much rarer than events, 1 % probability event even rarer, using rainfall-based procedures, at locations where few no observations streamflow. Here, we perform systematic review summarize state-of-the-art understanding impact Australian context, while also drawing international literature. addition, meta-analysis, whereby results from multiple studies combined, conducted extreme provide quantitative estimates possible future changes. This information described context contemporary facilitate inclusion practice.

Language: Английский

Citations

10

DeepBase: A Deep Learning-based Daily Baseflow Dataset across the United States DOI Creative Commons
Parnian Ghaneei, Hamid Moradkhani

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Jan. 7, 2025

High quality baseflow data is important for advancing water resources modeling and management, as it captures the critical role of groundwater delayed sources in contributing to streamflow. Baseflow main recharge source runoff during dry period, particularly understanding interaction between surface systems. This study focuses on estimating using deep learning algorithms that enhance estimation capabilities both gauged ungauged basins. Recognizing shortage accessible high daily data, our objective generate a dataset across contiguous United States (CONUS) 1661 basins from 1981 2022. provides valuable information earth environmental scientists, resource managers, enhancing cycle. It also an foundation contributions extreme events such droughts floods. The can be used new benchmark future studies aimed at improving hydrological predictions managing more effectively.

Language: Английский

Citations

1

Shifted dominant flood drivers of an alpine glacierized catchment in the Tianshan region revealed through interpretable deep learning DOI Creative Commons
Wenting Liang, Weili Duan, Yaning Chen

et al.

npj Climate and Atmospheric Science, Journal Year: 2025, Volume and Issue: 8(1)

Published: Jan. 25, 2025

Language: Английский

Citations

1

CAMELS-IND: hydrometeorological time series and catchment attributes for 228 catchments in Peninsular India DOI Creative Commons
Nikunj K. Mangukiya, Kanneganti Bhargav Kumar, Pankaj Dey

et al.

Earth system science data, Journal Year: 2025, Volume and Issue: 17(2), P. 461 - 491

Published: Feb. 5, 2025

Abstract. We introduce CAMELS-IND (Catchment Attributes and MEteorology for Large-sample Studies – India), a dataset containing hydrometeorological time series catchment attributes 472 catchments in Peninsular India, of which 228 have observed streamflow data available over 30 % the period between 1980 to 2020. India covers 15 interstate river basins defined by Central Water Commission (CWC), where flow water level datasets are several gauge stations through open-source Resources Information System (India-WRIS). However, many these lack reliable metadata, not an analysis-ready format large-sample hydrological studies. Therefore, we utilized their boundaries, characterized as with from Geospatial hydrologic analyses (GHI) (Goteti, 2023). For each catchments, provides mean meteorological forcings 41 years (1980–2020) 211 representing hydroclimatic land cover characteristics extracted multiple sources (including ground-based observations, remote sensing-based products, reanalyses datasets). follows same standards previously developed CAMELS USA, Chile, Brazil, Great Britain, Australia, Switzerland, Germany facilitate comparisons those countries inclusion global Notably, includes 19 forcings, including precipitation, maximum, minimum, average temperature, long-wave short-wave radiation flux, U V components wind, relative humidity, evaporation rates canopy soil surface, actual potential evapotranspiration, moisture four layers (covering depth up 3 m below ground) detailed also derived human influences, number dams utilization, total volume contents population density, increases urban agricultural studies understand influences on hydrology. Furthermore, predicted regionally trained long short-term memory (LSTM)-based model all can fill gaps or serve benchmark testing developing new models. envision that will provide strong foundation community-led effort toward gaining insights hydrologically distinct Indian solving pertinent issues related management, quantification risk assessment extremes, unraveling regional-scale functioning, climate change impact across India. The is at https://doi.org/10.5281/zenodo.14005378 (Mangukiya et al., 2024).

Language: Английский

Citations

1

Soil moisture-atmosphere interactions drive terrestrial carbon-water trade-offs DOI Creative Commons
Wenqi Sun, Sha Zhou, Bofu Yu

et al.

Communications Earth & Environment, Journal Year: 2025, Volume and Issue: 6(1)

Published: March 1, 2025

Language: Английский

Citations

1

China’s adaptive response to climate change through air-conditioning DOI Creative Commons
Hongbo Duan, Xi Ming, Xiao-Bing Zhang

et al.

iScience, Journal Year: 2023, Volume and Issue: 26(3), P. 106178 - 106178

Published: Feb. 10, 2023

Studies have shown that the soaring demand for air conditioners in recent years is closely related to worsening global warming; however, little evidence has been provided China. This study uses weekly data of 343 Chinese cities investigate how conditioner sales respond climate variability. We detected a U-shaped relationship between air-conditioning and temperature. An additional day with average temperature above 30°C increases by 16.2%. Heterogeneity analysis shows adoption different south north By combining our estimates shared socioeconomic pathway scenarios, we project China's mid-century resulting electricity demand. Under fossil-fueled development scenario, Pearl River Delta would rise 71% (65.7%-87.6%) summer. On average, per capita will surge 28% (23.2%-35.4%) China mid-century.

Language: Английский

Citations

20

Changes in Mediterranean flood processes and seasonality DOI Creative Commons
Yves Tramblay, Patrick Arnaud, Guillaume Artigue

et al.

Hydrology and earth system sciences, Journal Year: 2023, Volume and Issue: 27(15), P. 2973 - 2987

Published: Aug. 11, 2023

Abstract. Floods are a major natural hazard in the Mediterranean region, causing deaths and extensive damages. Recent studies have shown that intense rainfall events becoming more extreme this region but, paradoxically, without leading to an increase severity of floods. Consequently, it is important understand how flood changing explain absence trends magnitude despite increased extremes. A database 98 stations southern France with average record 50 years daily river discharge data between 1959 2021 was considered, together high-resolution reanalysis product providing precipitation simulated soil moisture classification weather patterns associated over France. Flood events, corresponding occurrence 1 event per year (5317 total), were extracted classified into excess-rainfall, short-rainfall, long-rainfall types. Several characteristics been also analyzed: durations, base flow contribution floods, runoff coefficient, total maximum rainfall, antecedent moisture. The evolution through time these seasonality analyzed. Results indicated that, most basins, floods tend occur earlier during year, mean date being, on average, advanced by month 1959–1990 1991–2021. This seasonal shift could be attributed frequency southern-circulation types spring summer. An extreme-event has observed, decrease before events. majority excess saturated soils, but their relative proportion decreasing time, notably spring, concurrent short rain For basins there positive correlation coefficients remaining stable dryer soils producing less lower In context increasing aridity, relationship likely cause magnitudes observed change These changes quite homogeneous domain studied, suggesting they rather linked regional climate than catchment characteristics. study shows even trends, properties may need accounted for when analyzing long-term hazards.

Language: Английский

Citations

18

Regional flood frequency analysis in North Africa DOI Creative Commons
Yves Tramblay, El Mahdi El Khalki,

Abderrahmane Khedimallah

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 630, P. 130678 - 130678

Published: Jan. 24, 2024

The Maghreb countries located in North Africa are strongly impacted by floods, causing extended damage and numerous deaths. Until now, the lack of accessibility river discharge data prevented regional studies on potential changes flood hazards or development frequency estimation methods. A new database daily for 98 basins Algeria, Morocco, Tunisia, has been compiled, with an average 36 years complete records over time period 1960–2018. peaks-over-threshold sampling events is considered first to detect trends annual magnitude floods. trend analysis results revealed no significant at level, only a few spurious due isolated extreme clustered events. An envelope curve relating maximum floods range catchment areas developed, this region such large database. Then, methods quantiles were compared. from multiple characteristics (including soil types, land use, elevation, geology) was performed comparing two linear regression methods, Stepwise Lasso regression, machine learning algorithm, Random Forests. Results indicate better performance estimate ungauged locations, mean absolute relative errors close 50 % bias 20 %. most relevant predictors identified models topographic wetness index, which provides estimates than area, but also altitude, rainfall, bulk density. study could be useful improve operational procedures sizing hydraulic structures sites.

Language: Английский

Citations

8

Flooding in the Yellow River Basin, China: Spatiotemporal patterns, drivers and future tendency DOI Creative Commons
Yixin Sun, Qiang Zhang, Vijay P. Singh

et al.

Journal of Hydrology Regional Studies, Journal Year: 2024, Volume and Issue: 52, P. 101706 - 101706

Published: Feb. 20, 2024

The Yellow River Basin (YRB) in China. This study is devoted to simulating flood changes with return periods of 10, 20, 30, 50, 100 and 200 years under three Representative Concentration Pathways (RCPs) using CaMa-Flood models, examining the drivers. In historical period (1961–2005), middle lower YRB specifically Wei (WRB) (a tributary YRB) are dominated by higher risks once-in-200-year magnitude 9989.63 m3/s. Under climate change scenarios, relative once-in-100-year increased from 125.0% (RCP2.6) 204.9% (RCP8.5) during (1961–2005) long-term (2076–2092). flood-prone regions were more susceptible magnitude. Meanwhile, area ranged 73.6% 95.2% YRB. Increased was typically related lengthened interval floods RCP2.6 RCP6.0 while decreased commonly linked intervals RCP8.5 scenarios. Notably, we observed correlations between 7-day maximum precipitation compared those daily precipitation, soil moisture, floods. Co-occurrences events hydrometeorological extremes upper

Language: Английский

Citations

8

Exploring the actual spatial resolution of 1 km satellite soil moisture products DOI Creative Commons
Luca Brocca, Jaime Gaona,

Davide Bavera

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 945, P. 174087 - 174087

Published: June 20, 2024

High-resolution soil moisture data is crucial in the development of hydrological applications as it provides detailed insights into spatiotemporal variability moisture. The emergence advanced remote sensing technologies, alongside widespread adoption machine learning, has facilitated creation continental and global products both at fine spatial (1 km) temporal (daily) scales. Some these rely on several sources input (satellite, situ, modelling), therefore an evaluation their actual resolution required. Nevertheless, absence appropriate ground monitoring networks poses a significant challenge for this assessment. In study, five high-resolution (S1-RT1, S1-COP, SMAP-Planet, SMAP-NSIDC, ESACCI-Zheng) were analysed evaluated throughout Italian territory, together with coarse (12.5 dataset comparison (ASCAT-HSAF). main objective to investigate resolution, accuracy. Firstly, cross-comparison space time carried out, including use triple collocation analysis. Secondly, application-based assessment implemented, considering irrigation, fire, drought, precipitation case studies. results clearly indicate limitations potential each product. Sentinel-1 based (S1-COP S1-RT1) are found able reproduce patterns by detecting localised events precipitation. Their lower leads accuracies than that SMAP-Planet product, comparable SMAP-NSIDC ESACCI-Zheng products. However, have coarser 1 km. study highlights need further research improve products, particularly determine accurately represented At same time, address first opening promising activities operational hydrology water resources management.

Language: Английский

Citations

8