An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data
Nitrogen (N), phosphorous (P), and potassium (K) are important macronutrients to crops. Deficiencies of these nutrients can change the pigment content in leaves and affect photosynthesis, resulting in the similar spectral characteristics at some wavelengths. Thus, one of the most important challenge...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/24/4060 |
| _version_ | 1797544937063972864 |
|---|---|
| author | Shishi Liu Xin Yang Qingfeng Guan Zhifeng Lu Jianwei Lu |
| author_facet | Shishi Liu Xin Yang Qingfeng Guan Zhifeng Lu Jianwei Lu |
| author_sort | Shishi Liu |
| collection | DOAJ |
| description | Nitrogen (N), phosphorous (P), and potassium (K) are important macronutrients to crops. Deficiencies of these nutrients can change the pigment content in leaves and affect photosynthesis, resulting in the similar spectral characteristics at some wavelengths. Thus, one of the most important challenges in crop nutrient stress assessment through the canopy’s spectral reflectance is the ability to discriminate different nutrient stress conditions. This study proposes a three-layer ensemble-modeling framework to analyze N, P, and K nutrient stresses utilizing canopy hyperspectral data of crops. The framework selects spectral bands that are sensitive to N, P, and K nutrient deficiency levels, using ensembles of random forest classifiers, and then the reflectance of the selected bands is transformed into the more distinguishable probability features to diagnose the N, P, and K nutrient deficiency levels. For this study, this proposed framework was applied to winter oilseed rape (<i>Brassica napus</i> L.) during the overwintering stage, with 915 spectra samples collected from 14 field experiments. The analysis of nutrient deficiency levels resulting from the proposed framework was compared with that of single random forest, support vector machine, and artificial neural network classifiers, using the same reflectance features selected in the first layer of the framework. The overall accuracy of the nutrient deficiency analysis achieved by the proposed framework reached 80.76%, which was 16.55%, 18.43%, and 35.74% higher than the single random forest, support vector machine, and artificial neural network classifiers, respectively. The proposed framework demonstrated competitive advantages in differentiating the medium deficiency of N and K, and the severe deficiency of K from the normal conditions, boosting the accuracy from below 25% to above 50% because the probability features enhanced the differences among nutrient deficiency levels. |
| first_indexed | 2024-03-10T14:08:33Z |
| format | Article |
| id | doaj.art-23afc2b02f584576b76837977e981eea |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T14:08:33Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-23afc2b02f584576b76837977e981eea2023-11-21T00:24:26ZengMDPI AGRemote Sensing2072-42922020-12-011224406010.3390/rs12244060An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral DataShishi Liu0Xin Yang1Qingfeng Guan2Zhifeng Lu3Jianwei Lu4School of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, ChinaSchool of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, ChinaSchool of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430078, ChinaSchool of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, ChinaSchool of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, ChinaNitrogen (N), phosphorous (P), and potassium (K) are important macronutrients to crops. Deficiencies of these nutrients can change the pigment content in leaves and affect photosynthesis, resulting in the similar spectral characteristics at some wavelengths. Thus, one of the most important challenges in crop nutrient stress assessment through the canopy’s spectral reflectance is the ability to discriminate different nutrient stress conditions. This study proposes a three-layer ensemble-modeling framework to analyze N, P, and K nutrient stresses utilizing canopy hyperspectral data of crops. The framework selects spectral bands that are sensitive to N, P, and K nutrient deficiency levels, using ensembles of random forest classifiers, and then the reflectance of the selected bands is transformed into the more distinguishable probability features to diagnose the N, P, and K nutrient deficiency levels. For this study, this proposed framework was applied to winter oilseed rape (<i>Brassica napus</i> L.) during the overwintering stage, with 915 spectra samples collected from 14 field experiments. The analysis of nutrient deficiency levels resulting from the proposed framework was compared with that of single random forest, support vector machine, and artificial neural network classifiers, using the same reflectance features selected in the first layer of the framework. The overall accuracy of the nutrient deficiency analysis achieved by the proposed framework reached 80.76%, which was 16.55%, 18.43%, and 35.74% higher than the single random forest, support vector machine, and artificial neural network classifiers, respectively. The proposed framework demonstrated competitive advantages in differentiating the medium deficiency of N and K, and the severe deficiency of K from the normal conditions, boosting the accuracy from below 25% to above 50% because the probability features enhanced the differences among nutrient deficiency levels.https://www.mdpi.com/2072-4292/12/24/4060hyperspectral remote sensingcrop nutrient deficiencyrandom forest classifierensemble modeling |
| spellingShingle | Shishi Liu Xin Yang Qingfeng Guan Zhifeng Lu Jianwei Lu An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data Remote Sensing hyperspectral remote sensing crop nutrient deficiency random forest classifier ensemble modeling |
| title | An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data |
| title_full | An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data |
| title_fullStr | An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data |
| title_full_unstemmed | An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data |
| title_short | An Ensemble Modeling Framework for Distinguishing Nitrogen, Phosphorous and Potassium Deficiencies in Winter Oilseed Rape (<i>Brassica napus</i> L.) Using Hyperspectral Data |
| title_sort | ensemble modeling framework for distinguishing nitrogen phosphorous and potassium deficiencies in winter oilseed rape i brassica napus i l using hyperspectral data |
| topic | hyperspectral remote sensing crop nutrient deficiency random forest classifier ensemble modeling |
| url | https://www.mdpi.com/2072-4292/12/24/4060 |
| work_keys_str_mv | AT shishiliu anensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT xinyang anensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT qingfengguan anensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT zhifenglu anensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT jianweilu anensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT shishiliu ensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT xinyang ensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT qingfengguan ensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT zhifenglu ensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata AT jianweilu ensemblemodelingframeworkfordistinguishingnitrogenphosphorousandpotassiumdeficienciesinwinteroilseedrapeibrassicanapusilusinghyperspectraldata |