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.

Biodiversity underlies ecosystem functioning. While aboveground biodiversity is often well studied, the belowground microbiome, in particular protists, remains largely unknown. Indeed, holistic insights into soil microbiome structures in natural soils, especially in hyperdiverse biomes such as the Brazilian Cerrado, remain unexplored. Here, we study the soil microbiome across four major vegetation zones of the Cerrado, ranging from grass-dominated to tree-dominated vegetation with a focus on protists. We show that protist taxon richness increases towards the tree-dominated climax vegetation. Early successional habitats consisting of primary grass vegetation host most potential plant pathogens and least animal parasites. Using network analyses combining protist with prokaryotic and fungal sequences, we show that microbiome complexity increases towards climax vegetation. Together, this suggests that protists are key microbiome components and that vegetation succession towards climax vegetation is stimulated by higher loads of animal and plant pathogens. At the same time, an increase in microbiome complexity towards climax vegetation might enhance system stability.

The use of herbicides is important for controlling weeds in crops. However, they can present impacts on soil properties, such as biological properties. In this study, we evaluated the responses of soil microbial biomass and enzymes activity to the application of the herbicides imazethapyr and flumioxazin and their mixture in an experiment under laboratory conditions, using soils with a different history of use. Soil microbial biomass C (MBC) decreased, while microbial biomass N (MBN) was not affected after the application of the herbicides as compared to the control. Soil respiration, respiratory quotient, and dehydrogenase (DHA) activity increased significantly after the application of the herbicides compared to the control. The hydrolysis of fluorescein diacetate (FDA) was not significantly different between the control and the herbicide treatments. The principal response curve showed the largest initial effects for the flumioxazin, followed by imazethapyr and their mixture. Flumioxazin had a different influence on soil respiration and respiratory quotient than imazethapyr and their mixture. Finally, the effects of herbicides on soil microbial biomass and enzymes are short-term as we observed recovery in the biological parameters over time.

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.