Predictive Understanding of Stream Salinization in a Developed Watershed Using Machine Learning DOI
Jared D. Smith, Lauren Koenig,

Margaux J. Sleckman

et al.

Environmental Science & Technology, Journal Year: 2024, Volume and Issue: 58(42), P. 18822 - 18833

Published: Oct. 11, 2024

Stream salinization is a global issue, yet few models can provide reliable salinity estimates for unmonitored locations at the time scales required ecological exposure assessments. Machine learning approaches are presented that use spatially limited high-frequency monitoring and distributed discrete samples to estimate daily stream-specific conductance across watershed. We compare predictive performance of space- time-unaware Random Forest time-aware Recurrent Graph Convolution Neural Network (KGE: 0.67 0.64, respectively) explainable artificial intelligence methods interpret model predictions understand drivers. These applied Delaware River Basin, developed watershed with diverse land uses experiences anthropogenic from winter deicer applications. capture seasonality first flush deicers, streams elevated correspond well indicators application. This result suggests these be used identify potential salinity-impaired best management practices. Daily driven primarily by cover (urbanization) trends may represent processes weather up three months. Such modeling likely transferable other watersheds further risks

Language: Английский

A novel algal bloom risk assessment framework by integrating environmental factors based on explainable machine learning DOI Creative Commons

Lingfang Gao,

Yulin Shangguan,

Sun Zhong

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103098 - 103098

Published: March 1, 2025

Language: Английский

Citations

1

The effects of drought on biodiversity in UK river ecosystems: Drying rivers in a wet country DOI Creative Commons
Rachel Stubbington, Judy England, Romain Sarremejane

et al.

Wiley Interdisciplinary Reviews Water, Journal Year: 2024, Volume and Issue: 11(5)

Published: July 9, 2024

Abstract Climate change is interacting with water resource pressures to alter the frequency, severity and spatial extent of drought, which can thus no longer be considered a purely natural hazard. Although particularly severe ecological impacts drought have occurred in drylands, its effects on temperate ecosystems, including rivers, are also considerable. Extensive research spanning diverse range UK rivers offers an opportunity place past context intensifying climate examine likely future typically cool, wet country. Here, manifests instream as deficits surface water, modified flow velocities, and—increasingly—partial or complete drying previously perennial naturally non‐perennial reaches. As result, causes declines taxonomic functional biodiversity freshwater communities microorganisms, algae, plants, invertebrates fish, altering processes associated benefits people. recovered quickly after previous droughts, increase extremity may compromise recovery following events. The risk droughts that push ecosystems beyond thresholds persistent, species‐poor, functionally simplified states increasing. Research monitoring needed enable timely identification approaching such inform interventions pull these back from brink. Management actions support regimes promote diversify habitats, refuges, crucial within river they adapt changing world. This article categorized under: Water Life > Nature Freshwater Ecosystems Stresses Pressures Conservation, Management, Awareness

Language: Английский

Citations

5

Impact of hydrological drought occurrence, duration, and severity on Murray-Darling basin water quality DOI Creative Commons
Dilanka Athukoralalage, Justin D. Brookes, R. W. McDowell

et al.

Water Research, Journal Year: 2024, Volume and Issue: 252, P. 121201 - 121201

Published: Jan. 30, 2024

The severity and frequency of droughts are projected to increase globally due climate change, but the effects this on water quality uncertain. Murray-Darling Basin (MDB) is largest river system in Australia has been impacted by varying within recent decades. In study, we assessed influence hydrological their characteristics (severity duration) quality, utilising a long-term (1980-2017) dataset from two monitoring sites. main drought periods, duration severity, were identified using calculated Standardised Drought Index values (SDI) averaged monthly streamflow data. While several periods identified, longest greatest during Millennium (1998-2010). Nutrient loads concentrations Total Nitrogen Phosphorus post-drought significantly different. period showed lowest median interquartile range nutrient (total nitrogen, TN; oxidised NOX; total phosphorus, TP; soluble reactive SRP) for both sites, whereas highest reported (approx. 1 × 103 105 kg day−1 loads). Our analysis found significant relationships between SDI droughts. load N P initial flush increased with at This suggests that nutrients retained landscape released higher when catchment became wetter, hydrology was activated, mobilised. Hydrology key driver controlling inter-drought peak post-drought. had (p=0.01) TN TP not cumulative over 12-month period. Hydrological important factors MDB. Therefore, management efforts should be focused reducing occurrence these events, along implementation control measures.

Language: Английский

Citations

4

Expanding towards contraction: the alternation of floods and droughts as a fundamental component in river ecology DOI Creative Commons
Susana Bernal, José L. J. Ledesma, Xavier Peñarroya

et al.

Biogeochemistry, Journal Year: 2025, Volume and Issue: 168(1)

Published: Jan. 3, 2025

Abstract Climate warming is causing more extreme weather conditions, with both larger and intense precipitation events as well extended periods of drought in many regions the world. The consequence an alteration hydrological regime streams rivers, increase probability conditions. Mediterranean-climate usually experience on a seasonal basis thus, freshwater Mediterranean ecosystems can be used natural laboratories for better understanding how climate will impact ecosystem structure functioning elsewhere. In this paper, we revisited contextualized historical new datasets collected at Fuirosos, well-studied intermittent stream naturally experiencing events, to illustrate alternation floods droughts influence hydrology, microbial assemblages, water chemistry, potential biogeochemical processing. Moreover, revised some most influential conceptual quantitative frameworks river ecology assess what extent they incorporate occurrence events. Based exercise, identified knowledge gaps challenges guide future research under intensification cycle. Ultimately, aimed share lessons learned from which help understand warming-induced impacts transport cycling matter fluvial ecosystems.

Language: Английский

Citations

0

Trends and Impacts of Climate-induced Extreme Weather Events in South Africa (1920-2023) DOI Creative Commons
Godwell Nhamo, Lazarus Chapungu,

Gideon Walter Mutanda

et al.

Environmental Development, Journal Year: 2025, Volume and Issue: unknown, P. 101183 - 101183

Published: Feb. 1, 2025

Language: Английский

Citations

0

How Does Extreme Drought Affect Phytoplankton Community Assembly in Aquatic Reserves? A Study from the Confluence of Poyang Lake and Yangtze River, China DOI Creative Commons
Jiang Yu-fei, Wenting Shen, Lei Fang

et al.

Diversity, Journal Year: 2025, Volume and Issue: 17(4), P. 301 - 301

Published: April 21, 2025

Extreme drought events, intensified by climate change, critically threaten aquatic ecosystem stability restructuring phytoplankton communities. However, the mechanisms underlying drought-driven community assembly remain poorly understood. This study investigated impacts of extreme on dynamics in reserves Jiujiang City, China, a critical ecotone Yangtze River and Poyang Lake. Through multi-temporal sampling (2022–2023) across 12 sites, we integrated taxonomic, functional group, co-occurrence network analyses with environmental driver assessments. The results revealed that significantly reduced species diversity triggered shift from disturbance-adapted (e.g., MP group) to pollution-tolerant taxa W1 group). Deterministic processes dominated assembly, driven drought-induced filtering through water temperature, dissolved oxygen, nutrient fluctuations. Copper emerged as key stressor, correlating abundance Cryptophyta. Co-occurrence networks, cohesion, robustness exhibited heightened complexity under drought, emphasizing stress-induced mutualistic interactions. Our findings elucidate how reshapes communities via deterministic interactions, offering insights for managing ecosystems escalating climatic extremes.

Language: Английский

Citations

0

Individual and combined impacts of carbon dioxide enrichment, heatwaves, flow velocity variability, and fine sediment deposition on stream invertebrate communities DOI Creative Commons
Julia G. Hunn, James Orr,

Ann‐Marie Kelly

et al.

Global Change Biology, Journal Year: 2024, Volume and Issue: 30(5)

Published: May 1, 2024

Abstract Climate change and land‐use are widely altering freshwater ecosystem functioning there is an urgent need to understand how these broad stressor categories may interact in future. While much research has focused on mean temperature increases, climate also involves increasing variability of both water flow regimes concentrations atmospheric CO 2 , all with potential alter stream invertebrate communities. Deposited fine sediment a pervasive widespread impacts invertebrates. Sedimentation be managed at the catchment scale; thus, uncovering interactions three key stressors assist mitigation future threats. This first experiment investigate individual combined effects enriched heatwaves, velocity variability, realistic Using 128 mesocosms simulating small stony‐bottomed streams 7‐week experiment, we manipulated dissolved (ambient; enriched), (no sediment; 300 g dry sediment), two 7‐day heatwaves), (constant; variable). All treatments changed community composition. enrichment reduced abundances Orthocladiinae Chironominae increased Copepoda abundance. Variable had only positive (7 13 common taxa total abundance), contrast previous experiments showing negative velocity. was implicated most found, × being common. Communities forming under conditions sediment‐impacted ~20% fewer invertebrates than those either treatment alone. doubled ‐enriched without sediment, whereas no effect occurred sediment. Our findings provide new insights into land use running freshwaters, particular highlighting for elevated deposition unpredictable ways.

Language: Английский

Citations

3

Characteristics of river heatwaves in the Vistula River Basin, Europe DOI Creative Commons
Quan Zhou, Fabio Di Nunno, Jiang Sun

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(16), P. e35987 - e35987

Published: Aug. 1, 2024

Rivers worldwide are warming due to the impact of climate change and human interventions. This study investigated river heatwaves in Vistula River Basin, one largest systems Europe using long-term observed daily water temperatures from past 30 years (1991-2020). The results showed that increased frequency intensity Basin. total number clear increasing trend with an average rate 1.400 times/decade, duration at 14.506 days/decade, cumulative 53.169 °C/decade. Mann-Kendall (MK) test was also employed, showing statistically significant trends number, duration, for all rivers, including main watercourse its tributaries, few exceptions. Air temperature is major controller each hydrological station, increase air temperatures, will intensity. Another impacting factor flow, tend decrease suggested mitigation measures shall be taken reduce effect on systems.

Language: Английский

Citations

3

Predicting Post-Wildfire Stream Temperature and Turbidity: A Machine Learning Approach in Western U.S. Watersheds DOI Open Access
Junjie Chen, Heejun Chang

Water, Journal Year: 2025, Volume and Issue: 17(3), P. 359 - 359

Published: Jan. 27, 2025

Wildfires significantly impact water quality in the Western United States, posing challenges for resource management. However, limited research quantifies post-wildfire stream temperature and turbidity changes across diverse climatic zones. This study addresses this gap by using Random Forest (RF) Support Vector Regression (SVR) models to predict based on climate, streamflow, fire data from Clackamas Russian River Watersheds. We selected because they handle non-linear, high-dimensional data, balance accuracy with efficiency, capture complex dynamics minimal assumptions. The primary objectives were evaluate model performance, conduct sensitivity analyses, project mid-21st century under Representative Concentration Pathway (RCP) 4.5 8.5 scenarios. Sensitivity analyses indicated that 7-day maximum air discharge most influential predictors. Results show RF outperformed SVR, achieving an R2 of 0.98 root mean square error 0.88 °C predictions. Post-wildfire increased up 70 NTU during storm events highly burned subwatersheds. Under RCP 8.5, temperatures are projected rise 2.2 2050. RF’s ensemble approach captured non-linear relationships effectively, while SVR excelled datasets but struggled temporal variability. These findings underscore importance machine learning understanding post-fire hydrology. recommend adaptive reservoir operations targeted riparian restoration mitigate warming trends. highlights learning’s utility predicting impacts informing climate-resilient management strategies.

Language: Английский

Citations

0

Evolution of and mechanisms controlling water chemistry in the Beijiang River Basin over the past four decades DOI

Zaizhi Yang,

Tao Jiang, Zhongmin Liang

et al.

Journal of Geochemical Exploration, Journal Year: 2025, Volume and Issue: unknown, P. 107736 - 107736

Published: Feb. 1, 2025

Language: Английский

Citations

0