Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods

Water quality monitoring is crucial for ecological protection and water resource management. However, traditional monitoring methods suffer from limitations in temporal, spatial, and spectral resolution, which constrain the effective evaluation of urban rivers and multi-scale aquatic systems. To add...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongran Li, Nuo Wang, Zixuan Du, Deyu Huang, Mengjie Shi, Zhaoman Zhong, Dongqing Yuan
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2191
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115489086308352
author Hongran Li
Nuo Wang
Zixuan Du
Deyu Huang
Mengjie Shi
Zhaoman Zhong
Dongqing Yuan
author_facet Hongran Li
Nuo Wang
Zixuan Du
Deyu Huang
Mengjie Shi
Zhaoman Zhong
Dongqing Yuan
author_sort Hongran Li
collection DOAJ
description Water quality monitoring is crucial for ecological protection and water resource management. However, traditional monitoring methods suffer from limitations in temporal, spatial, and spectral resolution, which constrain the effective evaluation of urban rivers and multi-scale aquatic systems. To address challenges such as ecological heterogeneity, multi-scale complexity, and data noise, this paper proposes a deep learning framework, TL-Net, based on unmanned aerial vehicle (UAV) hyperspectral imagery, to estimate four water quality parameters: total nitrogen (TN), dissolved oxygen (DO), total suspended solids (TSS), and chlorophyll a (Chla); and to produce their spatial distribution maps. This framework integrates Transformer and long short-term memory (LSTM) networks, introduces a cross-temporal attention mechanism to enhance feature correlation, and incorporates an adaptive feature fusion module for dynamically weighted integration of local and global information. The experimental results demonstrate that TL-Net markedly outperforms conventional machine learning approaches, delivering consistently high predictive accuracy across all evaluated water quality parameters. Specifically, the model achieves an <i>R</i><sup>2</sup> of 0.9938 for TN, a mean absolute error (<i>MAE</i>) of 0.0728 for DO, a root mean square error (<i>RMSE</i>) of 0.3881 for total TSS, and a mean absolute percentage error (<i>MAPE</i>) as low as 0.2568% for Chla. A spatial analysis reveals significant heterogeneity in water quality distribution across the study area, with natural water bodies exhibiting relatively uniform conditions, while the concentrations of TN and TSS are substantially elevated in aquaculture areas due to aquaculture activities. Overall, TL-Net significantly improves multi-parameter water quality prediction, captures fine-scale spatial variability, and offers a robust and scalable solution for inland aquatic ecosystem monitoring.
format Article
id doaj-art-2b85dc34dcc24733835010fd7b21ec39
institution OA Journals
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-2b85dc34dcc24733835010fd7b21ec392025-08-20T02:36:33ZengMDPI AGRemote Sensing2072-42922025-06-011713219110.3390/rs17132191Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning MethodsHongran Li0Nuo Wang1Zixuan Du2Deyu Huang3Mengjie Shi4Zhaoman Zhong5Dongqing Yuan6School of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaWater quality monitoring is crucial for ecological protection and water resource management. However, traditional monitoring methods suffer from limitations in temporal, spatial, and spectral resolution, which constrain the effective evaluation of urban rivers and multi-scale aquatic systems. To address challenges such as ecological heterogeneity, multi-scale complexity, and data noise, this paper proposes a deep learning framework, TL-Net, based on unmanned aerial vehicle (UAV) hyperspectral imagery, to estimate four water quality parameters: total nitrogen (TN), dissolved oxygen (DO), total suspended solids (TSS), and chlorophyll a (Chla); and to produce their spatial distribution maps. This framework integrates Transformer and long short-term memory (LSTM) networks, introduces a cross-temporal attention mechanism to enhance feature correlation, and incorporates an adaptive feature fusion module for dynamically weighted integration of local and global information. The experimental results demonstrate that TL-Net markedly outperforms conventional machine learning approaches, delivering consistently high predictive accuracy across all evaluated water quality parameters. Specifically, the model achieves an <i>R</i><sup>2</sup> of 0.9938 for TN, a mean absolute error (<i>MAE</i>) of 0.0728 for DO, a root mean square error (<i>RMSE</i>) of 0.3881 for total TSS, and a mean absolute percentage error (<i>MAPE</i>) as low as 0.2568% for Chla. A spatial analysis reveals significant heterogeneity in water quality distribution across the study area, with natural water bodies exhibiting relatively uniform conditions, while the concentrations of TN and TSS are substantially elevated in aquaculture areas due to aquaculture activities. Overall, TL-Net significantly improves multi-parameter water quality prediction, captures fine-scale spatial variability, and offers a robust and scalable solution for inland aquatic ecosystem monitoring.https://www.mdpi.com/2072-4292/17/13/2191UAV hyperspectral imagingmulti-parameter regressionecological heterogeneitywater quality monitoringtransformerLSTM
spellingShingle Hongran Li
Nuo Wang
Zixuan Du
Deyu Huang
Mengjie Shi
Zhaoman Zhong
Dongqing Yuan
Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
Remote Sensing
UAV hyperspectral imaging
multi-parameter regression
ecological heterogeneity
water quality monitoring
transformer
LSTM
title Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
title_full Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
title_fullStr Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
title_full_unstemmed Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
title_short Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
title_sort multi parameter water quality inversion in heterogeneous inland waters using uav based hyperspectral data and deep learning methods
topic UAV hyperspectral imaging
multi-parameter regression
ecological heterogeneity
water quality monitoring
transformer
LSTM
url https://www.mdpi.com/2072-4292/17/13/2191
work_keys_str_mv AT hongranli multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods
AT nuowang multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods
AT zixuandu multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods
AT deyuhuang multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods
AT mengjieshi multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods
AT zhaomanzhong multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods
AT dongqingyuan multiparameterwaterqualityinversioninheterogeneousinlandwatersusinguavbasedhyperspectraldataanddeeplearningmethods