Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis
Controlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, the complex factors affecting water quality (plant shading and suspended matter in water) make direct estimation extremely challenging. Considering the spectral response mechanisms...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/22/4643 |
| _version_ | 1797508491167924224 |
|---|---|
| author | Jinhua Liu Jianli Ding Xiangyu Ge Jingzhe Wang |
| author_facet | Jinhua Liu Jianli Ding Xiangyu Ge Jingzhe Wang |
| author_sort | Jinhua Liu |
| collection | DOAJ |
| description | Controlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, the complex factors affecting water quality (plant shading and suspended matter in water) make direct estimation extremely challenging. Considering the spectral response mechanisms of emergent plants, we coupled discrete wavelet transform (DWT) and fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), and eXtreme Gradient Boosting (XGBoost)) to mine this potential spectral information. A total of 567 models were developed, and airborne hyperspectral data processed with various DWT scales and FOD techniques were compared. The effective information in the hyperspectral reflectance data were better emphasized after DWT processing. After DWT processing the original spectrum (OR), its sensitivity to TN in water was maximally improved by 0.22, and the correlation between FOD and TN in water was optimally increased by 0.57. The transformed spectral information enhanced the TN model accuracy, especially for FOD after DWT. For RF, 82% of the model R<sup>2</sup> values improved by 0.02~0.72 compared to the model using FOD spectra; 78.8% of the bagging values improved by 0.01~0.53 and 65.0% of the XGBoost values improved by 0.01~0.64. The XGBoost model with DWT coupled with grey relation analysis (GRA) yielded the best estimation accuracy, with the highest precision of R<sup>2</sup> = 0.91 for L6. In conclusion, appropriately scaled DWT analysis can substantially improve the accuracy of extracting TN from UAV hyperspectral images. These outcomes may facilitate the further development of accurate water quality monitoring in sophisticated global waters from drone or satellite hyperspectral data. |
| first_indexed | 2024-03-10T05:05:42Z |
| format | Article |
| id | doaj.art-1514047ccd67480ea049eabbd72351f0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T05:05:42Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1514047ccd67480ea049eabbd72351f02023-11-23T01:20:53ZengMDPI AGRemote Sensing2072-42922021-11-011322464310.3390/rs13224643Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform AnalysisJinhua Liu0Jianli Ding1Xiangyu Ge2Jingzhe Wang3Key Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Science, Xinjiang University, Urumqi 830046, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Science, Xinjiang University, Urumqi 830046, ChinaKey Laboratory of Smart City and Environment Modelling of Higher Education Institute, College of Resources and Environment Science, Xinjiang University, Urumqi 830046, ChinaMNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area and Guangdong Key Laboratory of Urban Informatics and Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen University, Shenzhen 518060, ChinaControlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, the complex factors affecting water quality (plant shading and suspended matter in water) make direct estimation extremely challenging. Considering the spectral response mechanisms of emergent plants, we coupled discrete wavelet transform (DWT) and fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), and eXtreme Gradient Boosting (XGBoost)) to mine this potential spectral information. A total of 567 models were developed, and airborne hyperspectral data processed with various DWT scales and FOD techniques were compared. The effective information in the hyperspectral reflectance data were better emphasized after DWT processing. After DWT processing the original spectrum (OR), its sensitivity to TN in water was maximally improved by 0.22, and the correlation between FOD and TN in water was optimally increased by 0.57. The transformed spectral information enhanced the TN model accuracy, especially for FOD after DWT. For RF, 82% of the model R<sup>2</sup> values improved by 0.02~0.72 compared to the model using FOD spectra; 78.8% of the bagging values improved by 0.01~0.53 and 65.0% of the XGBoost values improved by 0.01~0.64. The XGBoost model with DWT coupled with grey relation analysis (GRA) yielded the best estimation accuracy, with the highest precision of R<sup>2</sup> = 0.91 for L6. In conclusion, appropriately scaled DWT analysis can substantially improve the accuracy of extracting TN from UAV hyperspectral images. These outcomes may facilitate the further development of accurate water quality monitoring in sophisticated global waters from drone or satellite hyperspectral data.https://www.mdpi.com/2072-4292/13/22/4643total nitrogendiscrete wavelet transformfractional order discretizationmachine learninghyperspectralemergent plants |
| spellingShingle | Jinhua Liu Jianli Ding Xiangyu Ge Jingzhe Wang Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis Remote Sensing total nitrogen discrete wavelet transform fractional order discretization machine learning hyperspectral emergent plants |
| title | Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis |
| title_full | Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis |
| title_fullStr | Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis |
| title_full_unstemmed | Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis |
| title_short | Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis |
| title_sort | evaluation of total nitrogen in water via airborne hyperspectral data potential of fractional order discretization algorithm and discrete wavelet transform analysis |
| topic | total nitrogen discrete wavelet transform fractional order discretization machine learning hyperspectral emergent plants |
| url | https://www.mdpi.com/2072-4292/13/22/4643 |
| work_keys_str_mv | AT jinhualiu evaluationoftotalnitrogeninwaterviaairbornehyperspectraldatapotentialoffractionalorderdiscretizationalgorithmanddiscretewavelettransformanalysis AT jianliding evaluationoftotalnitrogeninwaterviaairbornehyperspectraldatapotentialoffractionalorderdiscretizationalgorithmanddiscretewavelettransformanalysis AT xiangyuge evaluationoftotalnitrogeninwaterviaairbornehyperspectraldatapotentialoffractionalorderdiscretizationalgorithmanddiscretewavelettransformanalysis AT jingzhewang evaluationoftotalnitrogeninwaterviaairbornehyperspectraldatapotentialoffractionalorderdiscretizationalgorithmanddiscretewavelettransformanalysis |