Satellite retrievals of water quality for diverse inland waters from Sentinel-2 images: An example from Zhejiang Province, China

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 132, P. 104048 - 104048

Published: July 26, 2024

Language: Английский

---

Utilizing machine learning to evaluate heavy metal pollution in the world's largest mangrove forest

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 951, P. 175746 - 175746

Published: Aug. 23, 2024

Language: Английский

---

Intelligent Predictive Networks for Nonlinear Oxygen-Phytoplankton-Zooplankton Coupled Marine Ecosystems under Environmental and Climatic Disruptions

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 1, 2024

Language: Английский

---

Synergistic optimization of predictive models for water quality analysis in treatment plants using machine learning and evolutionary algorithms

Evolutionary Intelligence, Journal Year: 2025, Volume and Issue: 18(2)

Published: Feb. 21, 2025

Language: Английский

---

Interpretable Ai-Enhanced Reliable River Water Quality Prediction with Multi Remote Sensing Data Sources: Insights from Meteorological & Spatial-Temporal Variables

Published: Jan. 1, 2025

Language: Английский

---

Data-driven identification of pollution sources and water quality prediction using Apriori and LSTM models: A case study in the Hanjiang River basin

Journal of Contaminant Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 104570 - 104570

Published: April 1, 2025

Language: Английский

---

Shifting Patterns in the Weather Regimes That Drive Regional Drought: Demonstration for South Africa

International Journal of Climatology, Journal Year: 2025, Volume and Issue: unknown

Published: April 24, 2025

ABSTRACT Traditional vulnerability assessments of climate change impacts often rely on randomised precipitation scenarios that lack a strong physical science basis. Furthermore, the limitations General Circulation Models (GCMs) in accurately representing local fields undermine their utility for projecting future hydroclimatic extremes. To address these gaps risk management, this study explores role large‐scale atmospheric circulation patterns, known as weather regimes (WRs), explaining and regional dynamics South Africa. Utilising Non‐Homogeneous Hidden Markov Chain approach, we identified six primary WRs Africa, each exhibiting distinct seasonal patterns. The results show winter near Cape Town is dominated by three linked to higher rainfall, whilst summer influenced two associated with drier conditions. WR‐precipitation relationship Africa appears be topographic features (e.g., Great Escarpment Fold Mountains) ocean currents (Agulhas Benguela), leading spatial responses WR configurations. Importantly, significant shifts frequencies have been observed over past decades, particularly marked since 2010. Notably, historically rainfall has replaced WR, contributing worsening drought conditions, including 2015–2017 “Day Zero” drought. During period, dryness occurred more frequently than historical average, wetter years before after were characterised low‐pressure (low 500 hPa geopotential height anomalies) conducive precipitation. In contrast, high‐pressure (high anomaly) dry This analysis underscores critical link between patterns These findings can inform development WR‐based generators, providing valuable tools adaptation planning.

Language: Английский

---

In Situ Hyperspectral Reflectance Sensing for Mixed Water Quality Monitoring: Insights from the RUT Agricultural Irrigation District

Water, Journal Year: 2025, Volume and Issue: 17(9), P. 1353 - 1353

Published: April 30, 2025

Water-quality monitoring in agricultural irrigation systems is challenging due to the dynamic and heterogeneous nature of mixed water sources, which complicates traditional remote sensing-based assessment methods. Traditional quality relies on sampling laboratory analysis, can be time-consuming, labor-intensive, spatially limited. In situ hyperspectral reflectance sensing (HRS) presents a promising alternative, offering high-resolution, non-invasive capabilities. However, applying HRS mixed-water environments—where served-water effluent, precipitation, natural river converge—presents significant challenges variability composition environmental conditions. While has been widely explored controlled or homogeneous bodies, its application highly remains understudied. This study addresses this gap by evaluating relationships between data (450–900 nm) key water-quality parameters—pH, turbidity, nitrates, chlorophyll-a—across three campaigns Colombian tropical system. A Pearson’s correlation analysis revealed strongest spectral associations for with positive correlations at 500 nm (r ≈ 0.76) 700 0.85) negative near-infrared (850 nm, r −0.88). Conversely, pH exhibited weak diffuse correlations, maximum 0.51. Despite their optical activity, turbidity chlorophyll-a showed unexpectedly likely complexity matrix. Random Forest regression identified regions each parameter, yet model performance was limited, R2 values ranging from 0.51 (pH) −1.30 (chlorophyll-a), RMSE 0.41 1.51, reflecting predictive modeling temporally wastewater systems. these challenges, establishes baseline future applications complex highlights critical further investigation. To improve feasibility assessments, research should focus enhancing data-preprocessing techniques, integrating complementary modalities, refining models better account variability.

Language: Английский

---

Monitoring the Water Quality Distribution Characteristics in the Huaihe River Basin Based on the Sentinel-2 Satellite

Water, Journal Year: 2024, Volume and Issue: 16(6), P. 860 - 860

Published: March 16, 2024

Remote sensing technology plays a crucial role in the rapid and wide-scale monitoring of water quality, which is great significance for pollution prevention control. In this study, downstream nearshore areas Huaihe River Basin were selected as study area. By utilizing spectral information from standard solution measurements laboratory situ quality data matched with satellite spatiotemporal data, inversion models total phosphorus (TP) ammonia nitrogen (NH3-N) parameters developed. The validation results using field demonstrated that performed well, coefficients determination (R2) 0.7302 0.8024 root mean square errors 0.02614 mg/L 0.0368 nitrogen, respectively. applying to Sentinel-2 images 2022, temporal spatial distribution characteristics concentrations area obtained. concentration ranged 0.05 0.30 mg/L, while 0.10 0.40 mg/L. Overall, appeared be stable. southern region Guan estuary showed slightly higher parameter compared northern region, North Jiangsu Irrigation Main Canal was affected by dilution river water, resulting lower estuarine

Language: Английский

---

Landsat monitoring reveals the history of river organic pollution across China during 1984-2023

Water Research, Journal Year: 2025, Volume and Issue: unknown, P. 123210 - 123210

Published: Jan. 1, 2025

Language: Английский

---