TY - JOUR
T1 - A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements
AU - Osco, Lucas Prado
AU - Ramos, Ana Paula Marques
AU - Pinheiro, Mayara Maezano Faita
AU - Moriya, Érika Akemi Saito
AU - Imai, Nilton Nobuhiro
AU - Estrabis, Nayara
AU - Ianczyk, Felipe
AU - de Araújo, Fábio Fernando
AU - Liesenberg, Veraldo
AU - de Castro Jorge, Lúcio André
AU - Li, Jonathan
AU - Ma, Lingfei
AU - Gonçalves, Wesley Nunes
AU - Marcato, José
AU - Creste, José Eduardo
N1 - Publisher Copyright:
© 2020 by the authors.
PY - 2020/3/1
Y1 - 2020/3/1
N2 - This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro-and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 x 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms' prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients.
AB - This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro-and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 x 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms' prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients.
KW - Artificial intelligence
KW - Macronutrient
KW - Micronutrient
KW - Proximal sensor
KW - Spectroscopy
UR - https://www.scopus.com/pages/publications/85082304342
U2 - 10.3390/rs12060906
DO - 10.3390/rs12060906
M3 - 文章
AN - SCOPUS:85082304342
SN - 2072-4292
VL - 12
JO - Remote Sensing
JF - Remote Sensing
IS - 6
M1 - 906
ER -