Retrieval of total suspended matter concentration in the yellow river estuary offshore area based on QAA-RF model DOI Creative Commons

Lianwei Li,

Zhi Zheng,

Cunjin Xue

et al.

International Journal of Remote Sensing, Journal Year: 2024, Volume and Issue: 45(24), P. 9421 - 9442

Published: Oct. 8, 2024

Total suspended matter is one of the crucial water quality parameters for both inland and marine environments, a key role in evaluating estuaries offshore areas. Each year, Yellow River carries significant amount sediment into semi-enclosed Bohai Sea, results prolonged high concentration total areas Estuary. This study focuses on region Estuary China. Utilizing Sentinel-2 satellite imagery data from 2020 to 2023 in-situ measured August 2022, address lack physical mechanisms currently studied machine learning retrieval methods, model that integrates physics-driven Quasi-Analytical Algorithm (QAA) data-driven Random Forest (RF) employed area. The fused (QAA-RF) compared analysed against regression models standalone models. indicate accuracy consistently higher than QAA-RF demonstrates highest (R2 = 0.87, MAE 5.01 mg L−1, RMSE 6.39 L−1). Based data, monthly conducted indicates that: (1) concentrations primarily concentrated near estuary region, with decreasing as distance increases. (2) exhibits distribution pattern values spring winter, lower summer autumn. (3) shows relatively small fluctuations at annual scale 2023.

Language: Английский

Predicting Water Potability: Leveraging Machine Learning Techniques DOI

Nabil Laya,

Jayashree S. Shetty

Published: May 17, 2024

Language: Английский

Citations

0

Evaluation of LoRa Network Performance for Water Quality Monitoring Systems DOI Creative Commons

Syarifah Nabilah Syed Taha,

Mohamad Sofian Abu Talip, Mahazani Mohamad

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(16), P. 7136 - 7136

Published: Aug. 14, 2024

Conserving water resources from scarcity and pollution is the basis of resource management quality monitoring programs. However, due to industrialization population growth in Malaysia, which have resulted poor many areas, this program needs be improved. A smart system based on internet things (IoT) paradigm was designed analyze conditions real time enable effective management. Long-range (LoRa) application low-power, wide-area networking concept has become a phenomenon IoT applications. This study proposes implementation LoRa network system-based approach. The nodes were embedded with measuring sensors pH, turbidity, temperature, total dissolved solids, oxygen, designated stations. They operate at transmission power 14 dB bandwidth 125 kHz. properties tested two different antenna gains 2.1 dBi 3 dBi, three spread factors 7, 9, 12. stations located Sungai Pantai Anak Air Batu rivers Universiti Malaya campus, Malaysia. Following dashboard display K-means analysis data received by gateway, it determined that both are Class II B rivers. results evaluation performance strength signal indicator, noise ratio, loss packet, path best −83 dBm, 7 dB, <0%, 64.41 respectively, minimum sensitivity −129.1 dBm. demonstrated its efficiency an urban environment for river purposes.

Language: Английский

Citations

0

Retrieval of total suspended matter concentration in the yellow river estuary offshore area based on QAA-RF model DOI Creative Commons

Lianwei Li,

Zhi Zheng,

Cunjin Xue

et al.

International Journal of Remote Sensing, Journal Year: 2024, Volume and Issue: 45(24), P. 9421 - 9442

Published: Oct. 8, 2024

Total suspended matter is one of the crucial water quality parameters for both inland and marine environments, a key role in evaluating estuaries offshore areas. Each year, Yellow River carries significant amount sediment into semi-enclosed Bohai Sea, results prolonged high concentration total areas Estuary. This study focuses on region Estuary China. Utilizing Sentinel-2 satellite imagery data from 2020 to 2023 in-situ measured August 2022, address lack physical mechanisms currently studied machine learning retrieval methods, model that integrates physics-driven Quasi-Analytical Algorithm (QAA) data-driven Random Forest (RF) employed area. The fused (QAA-RF) compared analysed against regression models standalone models. indicate accuracy consistently higher than QAA-RF demonstrates highest (R2 = 0.87, MAE 5.01 mg L−1, RMSE 6.39 L−1). Based data, monthly conducted indicates that: (1) concentrations primarily concentrated near estuary region, with decreasing as distance increases. (2) exhibits distribution pattern values spring winter, lower summer autumn. (3) shows relatively small fluctuations at annual scale 2023.

Language: Английский

Citations

0