What drives the distinct evolution of the Aral Sea and Lake Balkhash? Insights from a novel CD-RF-FA method DOI Creative Commons
Shuang Liu, Aihua Long, Geping Luo

и другие.

Journal of Hydrology Regional Studies, Год журнала: 2024, Номер 56, С. 102014 - 102014

Опубликована: Окт. 16, 2024

Язык: Английский

Projections of streamflow intermittence under climate change in European drying river networks DOI Creative Commons
Louise Mimeau, Annika Künne, Alexandre Devers

и другие.

Hydrology and earth system sciences, Год журнала: 2025, Номер 29(6), С. 1615 - 1636

Опубликована: Март 25, 2025

Abstract. Climate and land use changes, as well human water flow alteration, are causing worldwide shifts in river dynamics. During the last decades, low flows, intermittence, drying have increased many regions of world, including Europe. This trend is projected to continue amplify future, resulting more frequent intense hydrological droughts. However, due a lack data studies on temporary rivers past, little known about processes governing development intermittence drying, their timing frequency, or long-term evolution under climate change. Moreover, understanding impact change up crucial assess aquatic ecosystems, biodiversity functional integrity freshwater systems. study one first present future projections intermittent networks analyse changes patterns at high spatial temporal resolution. Flow were produced using hybrid model forced with projection from 1985 until 2100 three scenarios six European networks. The studied watershed areas situated different biogeographic regions, located Spain, France, Croatia, Hungary, Czechia, Finland, range 150 350 km2. Additionally, indicators developed calculated (1) characteristics spells reach scale (2) extent network various time intervals. results for all show that increase expand space, despite differences amplitude changes. Temporally, addition average frequency events, duration increases over year. Seasonal expected result an earlier onset longer persistence throughout Summer maxima likely shift spring, extended periods additional occurring autumn extending into winter season some regions. A analysis extreme events shows dry observed recent years could become regular by end century. we observe transitions perennial reaches future.

Язык: Английский

Процитировано

1
Exploring the spatio-temporal dynamics of disturbed metacommunities: A mechanistic modeling approach to species resistance and resilience strategies in drying river networks DOI Creative Commons
Lysandre Journiac, Franck Jabot, Claire Jacquet

и другие.

Ecological Modelling, Год журнала: 2025, Номер 506, С. 111136 - 111136

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

1
Estimation of the prevalence of non-perennial rivers and streams in anthropogenically altered river basins by random Forest modeling: A case study for the Yellow river basin DOI Creative Commons
L Zhang, Mahdi Abbasi, Xiaoli Yang

и другие.

Journal of Hydrology, Год журнала: 2025, Номер unknown, С. 132910 - 132910

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Changes in the summer seasonal cycle of lakes in the Inner Tibetan Plateau since the 21st century DOI
Fuwan Gan,

Yang Gao,

Zheng Wei

и другие.

Climatic Change, Год журнала: 2025, Номер 178(4)

Опубликована: Март 25, 2025

Язык: Английский

Процитировано

0
Forecasting monthly runoff in a glacierized catchment: A comparison of extreme gradient boosting (XGBoost) and deep learning models DOI Creative Commons
Mohammed Majeed Hameed, Adil Masood,

Ashwaq Hamid

и другие.

PLoS ONE, Год журнала: 2025, Номер 20(5), С. e0321008 - e0321008

Опубликована: Май 23, 2025

Accurate monthly runoff forecasting is vital for water management, flood control, hydropower, and irrigation. In glacierized catchments affected by climate change, influenced complex hydrological processes, making precise even more challenging. To address this, the study focuses on Lotschental catchment in Switzerland, conducting a comprehensive comparison between deep learning ensemble-based models. Given significant autocorrelation time series data, which may hinder evaluation of prediction models, novel statistical method employed to assess effectiveness models detecting turning points data. The performance Extreme Gradient Boosting (XGBoost) was compared with long short-term memory (LSTM) random forest (RF) one-month-ahead forecasting. used 20 years data (2002–2021), 70% (2002–2015) dedicated training calibration, remaining (2016–2021) testing. findings testing phase results show that XGBoost model achieves best accuracy, R² 0.904, RMSE 1.554 m³/sec, an NSE 0.797, Willmott index ( d ) 0.972, outperforming both LSTM RF also found estimated accurately, obtaining improvements up 22% 34% Overall, study’s are essential global resource providing insights can inform sustainable practices support societies impacted change.

Язык: Английский

Процитировано

0
Comparative assessment of empirical Random Forest family’s model in simulating future streamflow in different basin of Sarawak, Malaysia DOI
Zulfaqar Sa’adi, Shamsuddin Shahid, Mohammed Sanusi Shiru

и другие.

Journal of Atmospheric and Solar-Terrestrial Physics, Год журнала: 2024, Номер 265, С. 106381 - 106381

Опубликована: Ноя. 2, 2024

Язык: Английский

Процитировано

1
What drives the distinct evolution of the Aral Sea and Lake Balkhash? Insights from a novel CD-RF-FA method DOI Creative Commons
Shuang Liu, Aihua Long, Geping Luo

и другие.

Journal of Hydrology Regional Studies, Год журнала: 2024, Номер 56, С. 102014 - 102014

Опубликована: Окт. 16, 2024

Язык: Английский

Процитировано

0