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 × 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. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions.

The objective of this investigation was to study and optimize a hyperspectral unmanned aerial vehicle (UAV)-based remotesensing system for the Brazilian environment. Comprised mainly of forest and sugarcane, the study area was located in the western region of the State of São Paulo. A novel hyperspectral camera based on a tunable Fabry-Pérot interferometer was mounted aboard a UAV due to its flexibility and capability to acquire data with a high temporal and spatial resolution. Five approaches designed to produce mosaics of hyperspectral images, which represent the hemispherical directional reflectance factor of targets in the Brazilian environment, are presented and evaluated. The method considers the irradiance variation during image acquisition and the effects of the bidirectional reflectance distribution function. The main goal was achieved by comparing the spectral responses of radiometric reference targets acquired with a spectroradiometer in the field with those produced by the five different approaches. The best results were achieved by correcting the bidirectional reflectance distribution function effects and by applying a least squares method to a radiometric block adjustment using only the image data, thereby achieving a root mean square error of 11.35%.

The traditional method of measuring nitrogen content in plants is a time-consuming and labor-intensive task. Spectral vegetation indices extracted from unmanned aerial vehicle (UAV) images and machine learning algorithms have been proved effective in assisting nutritional analysis in plants. Still, this analysis has not considered the combination of spectral indices and machine learning algorithms to predict nitrogen in tree-canopy structures. This paper proposes a new framework to infer the nitrogen content in citrus-tree at a canopy-level using spectral vegetation indices processed with the random forest algorithm. A total of 33 spectral indices were estimated from multispectral images acquired with a UAV-based sensor. Leaf samples were gathered from different planting-fields and the leaf nitrogen content (LNC) was measured in the laboratory, and later converted into the canopy nitrogen content (CNC). To evaluate the robustness of the proposed framework, we compared it with other machine learning algorithms. We used 33,600 citrus trees to evaluate the performance of the machine learning models. The random forest algorithm had higher performance in predicting CNC than all models tested, reaching an R2 of 0.90, MAE of 0.341 g·kg−1 and MSE of 0.307 g·kg−1. We demonstrated that our approach is able to reduce the need for chemical analysis of the leaf tissue and optimizes citrus orchard CNC monitoring.

The aim of this research was to develop a methodology involving aerial surveying using an unmanned aerial system (UAS), processing and analysis of images obtained by a hyperspectral camera, achieving results that enable discrimination and recognition of sugarcane plants infected with mosaic virus. It was necessary to characterize the spectral response of healthy and infected sugarcane plants in order to define the correct mode of operation for the hyperspectral camera, which provides many spectral band options for imaging but limits each image to 25 spectral bands. Spectral measurements of the leaves of infected and healthy sugarcane with a spectroradiometer were used to produce a spectral library. Once the most appropriate spectral bands had been selected, it was possible to configure the camera and carry out aerial surveying. The empirical line approach was adopted to obtain hemispherical conical reflectance factor values with a radiometric block adjustment to produce a mosaic suitable for the analysis. A classification based on spectral information divergence was applied and the results were evaluated by Kappa statistics. Areas of sugarcane infected with mosaic were identified from these hyperspectral images acquired by UAS and the results obtained had a high degree of accuracy.

Modeling the hyperspectral response of vegetables is important for estimating water stress through a noninvasive approach. This article evaluates the hyperspectral response of water-stress induced lettuce (Lactuca sativa L.) using artificial neural networks (ANN). We evenly split 36 lettuce pots into three groups: control, stress, and bacteria. Hyperspectral response was measured four times, during 14 days of stress induction, with an ASD Fieldspec HandHeld spectroradiometer (325–1075 nm). Both reflectance and absorbance measurements were calculated. Different biophysical parameters were also evaluated. The performance of the ANN approach was compared against other machine learning algorithms. Our results show that the ANN approach could separate the water-stressed lettuce from the non-stressed group with up to 80% accuracy at the beginning of the experiment. Additionally, this accuracy improved at the end of the experiment, reaching an accuracy of up to 93%. Absorbance data offered better accuracy than reflectance data to model it. This study demonstrated that it is possible to detect early stages of water stress in lettuce plants with high accuracy based on an ANN approach applied to hyperspectral data. The methodology has the potential to be applied to other species and cultivars in agricultural fields.