Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water

Particulate phosphorus (PP) is a major contributor to lakes developing eutrophic. It also serves as one of the most significant sources of phosphorus for primary productivity, serving as a possible source of soluble reactive phosphorus, and contributing a sizable amount of the total phosphorus (TP),...

Full description

Saved in:
Bibliographic Details
Main Authors: Banglong Pan, Wuyiming Liu, Zhuo Diao, Qianfeng Gao, Lanlan Huang, Shaoru Feng, Juan Du, Qi Wang, Jiayi Li, Jiamei Cheng
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Spectroscopy
Online Access:http://dx.doi.org/10.1155/jspe/9683030
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225427475759104
author Banglong Pan
Wuyiming Liu
Zhuo Diao
Qianfeng Gao
Lanlan Huang
Shaoru Feng
Juan Du
Qi Wang
Jiayi Li
Jiamei Cheng
author_facet Banglong Pan
Wuyiming Liu
Zhuo Diao
Qianfeng Gao
Lanlan Huang
Shaoru Feng
Juan Du
Qi Wang
Jiayi Li
Jiamei Cheng
author_sort Banglong Pan
collection DOAJ
description Particulate phosphorus (PP) is a major contributor to lakes developing eutrophic. It also serves as one of the most significant sources of phosphorus for primary productivity, serving as a possible source of soluble reactive phosphorus, and contributing a sizable amount of the total phosphorus (TP), so monitoring the spatial and temporal variability of PP is crucial for understanding eutrophication in water bodies. This study aims to propose an algorithm to accurately predict the PP concentration and to assess the performance of the model. Considering Chaohu Lake as a case study, we proposed a random forest algorithm based on the convolutional neural network (CNN-RF) to investigate the spatial and temporal patterns of PP concentration in the lake using HJ-2 hyperspectral satellite images. The applicability of backpropagation (BP) neural network, random forest (RF), convolutional neural network (CNN), and CNN-RF models for remote sensing inversion of PP concentration is assessed through model comparison. The results indicate that the CNN-RF model has the best prediction performance, with a coefficient of determination (R2) of 0.91, a residual prediction deviation (RPD) of 3.42, a root mean square error (RMSE) of 0.0155 mg/L, and a percentage bias (PBIAS) of 5.01%, which is better than the BP model by 42%, 106%, 51%, and 81%, the RF model by 25%, 77%, 44%, and 59%, and the CNN model by 9.6%, 42%, 30%, and 49%, respectively, and 59% better than the CNN model. The inversion findings suggest that the PP of Chaohu Lake is substantially high in summer and autumn but comparatively low in spring and winter. The spatial distribution demonstrates an arrangement of highest in the western part of the lake, second in the eastern region, and lowest in the central, with obvious spatial and temporal distribution characteristics, and the trend is closely related to the quarterly mean air temperature and mean precipitation. This indicates that based on the differences in phosphorescence scattering signals of different morphologies in water bodies, the use of hyperspectral remote sensing and the CNN-RF model can effectively extract PP spatiotemporal information, strengthen the learning capability of multiscale characteristics, and contribute to the improvement of the precision of estimating PP concentration, which could provide an innovative approach for determining the degree of eutrophication of lake water bodies.
format Article
id doaj-art-b84f14661f1f481da3a9c8aaff350ccf
institution Kabale University
issn 2314-4939
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Spectroscopy
spelling doaj-art-b84f14661f1f481da3a9c8aaff350ccf2025-08-25T00:00:03ZengWileyJournal of Spectroscopy2314-49392025-01-01202510.1155/jspe/9683030Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake WaterBanglong Pan0Wuyiming Liu1Zhuo Diao2Qianfeng Gao3Lanlan Huang4Shaoru Feng5Juan Du6Qi Wang7Jiayi Li8Jiamei Cheng9School of Environmental and Energy EngineeringSchool of Environmental and Energy EngineeringCollege of Geoexploration Science and TechnologySchool of Environmental and Energy EngineeringSchool of Environmental and Energy EngineeringAnhui Provincial Key Laboratory of Environmental Pollution Control and Resource ReuseSchool of Environmental and Energy EngineeringSchool of Environmental and Energy EngineeringSchool of Environmental and Energy EngineeringSchool of Environmental and Energy EngineeringParticulate phosphorus (PP) is a major contributor to lakes developing eutrophic. It also serves as one of the most significant sources of phosphorus for primary productivity, serving as a possible source of soluble reactive phosphorus, and contributing a sizable amount of the total phosphorus (TP), so monitoring the spatial and temporal variability of PP is crucial for understanding eutrophication in water bodies. This study aims to propose an algorithm to accurately predict the PP concentration and to assess the performance of the model. Considering Chaohu Lake as a case study, we proposed a random forest algorithm based on the convolutional neural network (CNN-RF) to investigate the spatial and temporal patterns of PP concentration in the lake using HJ-2 hyperspectral satellite images. The applicability of backpropagation (BP) neural network, random forest (RF), convolutional neural network (CNN), and CNN-RF models for remote sensing inversion of PP concentration is assessed through model comparison. The results indicate that the CNN-RF model has the best prediction performance, with a coefficient of determination (R2) of 0.91, a residual prediction deviation (RPD) of 3.42, a root mean square error (RMSE) of 0.0155 mg/L, and a percentage bias (PBIAS) of 5.01%, which is better than the BP model by 42%, 106%, 51%, and 81%, the RF model by 25%, 77%, 44%, and 59%, and the CNN model by 9.6%, 42%, 30%, and 49%, respectively, and 59% better than the CNN model. The inversion findings suggest that the PP of Chaohu Lake is substantially high in summer and autumn but comparatively low in spring and winter. The spatial distribution demonstrates an arrangement of highest in the western part of the lake, second in the eastern region, and lowest in the central, with obvious spatial and temporal distribution characteristics, and the trend is closely related to the quarterly mean air temperature and mean precipitation. This indicates that based on the differences in phosphorescence scattering signals of different morphologies in water bodies, the use of hyperspectral remote sensing and the CNN-RF model can effectively extract PP spatiotemporal information, strengthen the learning capability of multiscale characteristics, and contribute to the improvement of the precision of estimating PP concentration, which could provide an innovative approach for determining the degree of eutrophication of lake water bodies.http://dx.doi.org/10.1155/jspe/9683030
spellingShingle Banglong Pan
Wuyiming Liu
Zhuo Diao
Qianfeng Gao
Lanlan Huang
Shaoru Feng
Juan Du
Qi Wang
Jiayi Li
Jiamei Cheng
Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water
Journal of Spectroscopy
title Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water
title_full Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water
title_fullStr Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water
title_full_unstemmed Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water
title_short Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water
title_sort assessment of a hyperspectral remote sensing model performance for particulate phosphorus in optically shallow lake water
url http://dx.doi.org/10.1155/jspe/9683030
work_keys_str_mv AT banglongpan assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT wuyimingliu assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT zhuodiao assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT qianfenggao assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT lanlanhuang assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT shaorufeng assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT juandu assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT qiwang assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT jiayili assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater
AT jiameicheng assessmentofahyperspectralremotesensingmodelperformanceforparticulatephosphorusinopticallyshallowlakewater