Decoding Flow-Ecology Relationships: A Machine learning framework for flow regime Characterization and riparian vegetation prediction

Ecological Indicators, Journal Year: 2025, Volume and Issue: 175, P. 113517 - 113517

Published: May 1, 2025

Language: Английский

---

Warmer winter under climate change would reshape the winter subsurface drainage pattern in Eastern Canada

Agricultural and Forest Meteorology, Journal Year: 2025, Volume and Issue: 370, P. 110602 - 110602

Published: May 8, 2025

Language: Английский

---

Algal bloom forecasting leveraging signal processing: a novel perspective from ensemble learning

Water Research, Journal Year: 2025, Volume and Issue: unknown, P. 123800 - 123800

Published: May 1, 2025

Language: Английский

---

Enhancing river water quality in different seasons through management of landscape patterns at various spatial scales

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 373, P. 123653 - 123653

Published: Dec. 10, 2024

Language: Английский

---

Cathodic electrochemiluminescence of boron and nitrogen-codoped carbon dots for the detection of dissolved oxygen in seawater

Talanta, Journal Year: 2024, Volume and Issue: 279, P. 126529 - 126529

Published: July 10, 2024

Language: Английский

---

Water quality ensemble prediction model for the urban water reservoir based on the hybrid long short-term memory (LSTM) network analysis

AQUA - Water Infrastructure Ecosystems and Society, Journal Year: 2024, Volume and Issue: 73(8), P. 1621 - 1642

Published: July 15, 2024

ABSTRACT The water quality of drinking reservoirs directly impacts the supply safety for urban residents. This study focuses on Da Jing Shan Reservoir, a crucial source Zhuhai City and Macau Special Administrative Region. aim is to establish prediction model reservoirs, which can serve as vital reference plants when formulating their plans. In this research, after smoothing data using Hodrick-Prescott filter, we utilized long short-term memory (LSTM) network create Reservoir. Simulation calculations reveal that model's fitting degree consistently above 60%. Specifically, accuracy pH, dissolved oxygen (DO), biochemical demand (BOD) in aligns with actual results by more than 70%, effectively simulating reservoir's changes. Moreover, parameters such DO, BOD, total phosphorus, relative forecasting error LSTM less 10%, confirming validity. offer an essential predicting

Language: Английский

---

Explainable deep learning identifies patterns and drivers of freshwater harmful algal blooms

Environmental Science and Ecotechnology, Journal Year: 2024, Volume and Issue: 23, P. 100522 - 100522

Published: Dec. 27, 2024

The escalating magnitude, frequency, and duration of harmful algal blooms (HABs) pose significant challenges to freshwater ecosystems worldwide. However, the mechanisms driving HABs remain poorly understood, in part due strong regional specificity processes uneven data availability. These complexities make it difficult generalize HAB dynamics effectively predict their occurrence using traditional models. To address these challenges, we developed an explainable deep learning approach long short-term memory (LSTM) models combined with explanation techniques that can capture complex patterns provide insights into key drivers. We applied this for density modeling at 102 sites China's lakes reservoirs over three years. LSTMs captured daily dynamics, achieving mean maximum Nash-Sutcliffe efficiency coefficients 0.48 0.95 during testing phase. Moreover, water temperature emerged as primary driver both nationally 30% localities, stronger sensitivity observed mid-to low-latitudes. also identified similarities allow successful transferability dynamics. Specifically, fine-tuned transfer learning, improved prediction accuracy 75% gauged areas. Overall, LSTM-based addresses by tackling limitations. By accurately predicting identifying critical drivers, provides actionable HABs, ultimately aids implementation effective mitigation measures nationwide ecosystems.

Language: Английский

---

Warmer Winter Under Climate Change Would Reshape the Winter Subsurface Drainage Pattern in Eastern Canada: A Bio-Physical Modeling and Machine Learning Approach

Published: July 10, 2024

Subsurface drainage is a key loss pathway for water and nutrients from agricultural land in Eastern Canada. Winter presently dominant period of subsurface nutrient cold climates. Under climate change, however, future winter patterns may change significantly due to reductions snow cover soil freezing. This study evaluated the performance RZ-SHAW model four machine-learning (ML) models simulating five sites The calibrated/trained ML were then applied predicted (high emission scenario: RCP8.5) spanning 1950 2100 comprehend potential alteration under global warming. Among models, Cubist SVM-RBF emerged as most accurate, offering competing short-term simulation capabilities compared modelwith lower computational demand. Simulation by both predict significant increase volume frequency end 21st century (1950-2005 vs. 2070-2100) (RZ-SHAW: 243 mm 328 (+35%); 75.5 days 102.9 (+45%), models: 250 425 (+70%); 121.9 129.2 (+8%)). simulated shift towards more evenly spread pattern throughout months baseline century. was driven shorter coverage periods, advancement snowmelt timing, fewer freezing soil. Thus, timing peak trough expected reverse, with February becoming month April lowest century's end.

Language: Английский

---

A Machine Learning Framework for Enhanced Assessment of Sewer System Operation under Data Constraints and Skewed Distributions

ACS ES&T Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 25, 2024

Language: Английский

---

Enhanced prediction of river dissolved oxygen through feature- and model-based transfer learning

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 372, P. 123310 - 123310

Published: Nov. 20, 2024

Language: Английский

---