Estimation Method of Chlorophyll Concentration Distribution Based on UAV Aerial Images considering Turbid Water Distribution in a Reservoir

Published: April 5, 2024

The causes of algal blooms in reservoirs are often complexly intertwined with chemical, physical, and biological factors such as the supply nutrients. Observation phytoplankton distribution high spatiotemporal resolution is necessary to track nutrient sources that cause understand their behavior response wind water temperature stratification. from a UAV, which has excellent temporal spatial resolution, considered be an effective method obtain quality information comprehensively. On other hand, it not only growth plankton affects color surface but also turbidity. Furthermore, since brightness value passive sensors optical cameras changes depending on amount insolation, perform analysis after making corrections for this. In this study, we attempted develop estimating chlorophyll concentration aerial images taken UAVs using machine learning takes into account correction based insolation turbidity evaluated by satellite image analysis.

Language: Английский

Machine Learning Based Inversion of Water Quality Parameters in Typical Reach of Rural Wetland by Unmanned Aerial Vehicle Images

Water, Journal Year: 2024, Volume and Issue: 16(22), P. 3163 - 3163

Published: Nov. 5, 2024

Rural wetlands are complex landscapes where rivers, croplands, and villages coexist, making water quality monitoring crucial for the well-being of nearby residents. UAV-based imagery has proven effective in capturing detailed features bodies, it a popular tool assessments. However, few studies have specifically focused on drone-based rural their seasonal variations. In this study, Xiangfudang Wetland Park, Jiaxin City, Zhejiang Province, China, was taken as study area to evaluate parameters, including total nitrogen (TN), phosphors (TP), chemical oxygen demand (COD), turbidity degree (TUB). We assessed these parameters across summer winter seasons using UAV multispectral field sample data. Four machine learning algorithms were evaluated compared inversion based situ survey data images. The results show that ANN algorithm yielded best estimating TN, COD, TUB, with validation R2 0.78, 0.76, 0.57, respectively; CatBoost performed TP estimation, RMSE values 0.72 0.05 mg/L. Based spatial estimation results, average COD concentration body 16.05 ± 9.87 mg/L summer, higher than (13.02 8.22 mg/L). Additionally, mean TUB 18.39 Nephelometric Turbidity Units (NTU) 20.03 NTU winter. This demonstrates novelty effectiveness wetlands, providing critical insights into variations areas.

Language: Английский