Determining leaf nutrient concentrations in citrus trees using UAV imagery and machine learning

Nutrient assessment of plants, a key aspect of agricultural crop management and varietal development programs, traditionally is time demanding and labor-intensive. This study proposes a novel methodology to determine leaf nutrient concentrations of citrus trees by using unmanned aerial vehicle (UAV) multispectral imagery and artificial intelligence (AI). The study was conducted in four different citrus field trials, located in Highlands County and in Polk County, Florida, USA. In each location, trials contained either ‘Hamlin’ or ‘Valencia’ sweet orange scion grafted on more than 30 different rootstocks. Leaves were collected and analyzed in the laboratory to determine macro- and micronutrient concentration using traditional chemical methods. Spectral data from tree canopies were obtained in five different bands (red, green, blue, red edge and near-infrared wavelengths) using a UAV equipped with a multispectral camera. The estimation model was developed using a gradient boosting regression tree and evaluated using several metrics including mean absolute percentage error (MAPE), root mean square error, MAPE-coefficient of variance (CV) ratio and difference plot. This novel model determined macronutrients (nitrogen, phosphorus, potassium, magnesium, calcium and sulfur) with high precision (less than 9% and 17% average error for the ‘Hamlin’ and ‘Valencia’ trials, respectively) and micro-nutrients with moderate precision (less than 16% and 30% average error for ‘Hamlin’ and ‘Valencia’ trials, respectively). Overall, this UAV- and AI-based methodology was efficient to determine nutrient concentrations and generate nutrient maps in commercial citrus orchards and could be applied to other crop species.

Leaf Nutrient Concentrations and Dry Biomass of Fig Plants as Modified by the Application of NPK: A Preliminary Study

Aims: The effect of a complete NPK matrix on leaf nutrient concentrations and dry biomass of ‘Black Mission’ fig plant organs was tested under an intensive culture system and protected environment. Study Design: A randomized complete block design with four blocks was employed. Place and Duration of Study: The experiment was conducted from April to November 2016 at the Campo Experimental La Laguna, located in Matamoros, Coahuila, Mexico. This research station belongs to the Instituto Nacional de Investigaciones Forestales, Agrícolas y Pecuarias (INIFAP) of Mexico. The experiment was set up under a macro tunnel equipped with a shade mesh with 50% sunlight attenuation. Methodology: Two-year-old fig plants (cv. ‘Black Mission’) previously propagated from stem cuttings were used. There were three application rates each for N (0, 80, and 160 kg ha-1), P (0, 40 and 80 kg ha-1), and K (0, 80, and 160 kg ha-1) arranged in a balanced factorial matrix of 27 treatments. After harvest, leaf samples were collected to determine nutrient concentrations and they were split into roots, shoots, leaves, and fruit Results: The greatest total dry biomass was produced by the interaction of 80 kg ha-1 N and 40 kg ha-1 P and yielded the following leaf nutrient concentrations (mean ± SD): N 2.9 ± 0.3%, P 0.11 ± 0.01%, K 2.1 ± 0.4%, Ca 1.4 ± 0.7%, Mg 0.34 ± 0.03%, Fe 166.4 ± 49.5 mg kg-1, Cu 6.3 ± 1.7 mg kg-1, Mn 83.3 ± 20.9 mg kg-1, and Zn 22. 6 ± 3.8 mg kg-1. Application of 80 kg ha-1 N and 40 kg ha-1 P could be suggested for commercial fig production. Conclusion: Application of 80 kg ha-1 N and 40 kg ha-1 P could be tested under similar commercial production systems; however, the addition of supplemental K deserves further study.

Leaf nutrients of two Cycas L. species contrast among in situ and ex situ locations

An understanding of leaf nutrient relations is required for tree conservation and horticulture success. The study of cycad leaf nutrient dynamics has expanded in recent years, but direct comparisons among reports remains equivocal due to varying sampling protocols. We used Cycas micronesica K.D. Hill and Cycas nongnoochiae K.D. Hill trees to determine the influence on leaf nutrient concentrations of in situ versus ex situ locations and orientation of leaves within the tree canopy. Nitrogen, phosphorus, and potassium concentrations of leaves from ex situ plants exceeded those from in situ plants, and the differences were not explained by soil nutrient differences. Calcium concentrations of leaves varied among the site pairs, with differences primarily explained by soil calcium. Magnesium concentrations of leaves were not different among all location pairs even though soil magnesium concentrations varied among the sites more than any of the other elements. Differences in leaf macronutrient concentrations among four C. micronesica provenances were minimal when grown in a common garden. Lateral orientation of leaves did not influence any of the essential elements for either of the species. These findings indicate that the lateral orientation of cycad leaves does not influence leaf nutrient concentrations, leaf nutrient relations of cycad plants in managed ex situ settings do not align with leaf nutrient relations in habitat, and these differences are not explained by soil nutrition for most elements. We suggest that leaf nutrient concentrations should be determined in all niche habitats within the geographic range of a cycad species in order to fully understand the leaf physiology of each species.

Computer Tools for Diagnosing Citrus Leaf Symptoms (Part 1): Diagnosis and Recommendation Integrated System (DRIS)

This new 2-page article provides instructions for using the Diagnosis and Recommendation Integrated System, or DRIS, a web tool designed for analyzing leaf nutrient concentrations of Florida citrus. Written by Arnold Schumann and published by the UF/IFAS Department of Soil and Water Sciences.

Exploratory analysis of nutrient concentrations in Eucalyptus leaf color patterns

The aim of this study was to evaluate the use of leaf color pattern to analyze leaf nutrient concentrations in Eucalyptus and to establish relationships between color patterns and leaf nutrient concentrations. The study was carried out in Eucalyptus stands at 25 months old using three leaves from the lower of tree crowns classified into five color patterns of Munsell color charts for plant tissues. The principal component analyses and the self-organizing maps were used to aid in the classification of samples in leaf color patterns. Subsequently, the k-means cluster algorithm was performed. In principal component analysis, the 7.5 GY 8/8 leaf color pattern stood out from the others and it was mainly influenced by nitrogen, phosphorous, copper, and potassium concentrations. The samples of 7.5 GY 8/4 leaf color pattern did not present a great nitrogen, phosphorous, sulfur, copper and potassium concentrations as the 7.5 GY 8/8 neither a great manganese, calcium, boron, zinc and iron concentrations as others leaf color patterns. The self-organizing map provides a greater proximity between the 7.5 GY 8/8 and 7.5 GY 8/4 leaf color patterns and the others leaf color patterns were randomly distributed in the U-matrix. Although the k-means algorithm presented two clusters in both analyses, the self-organizing map presented a slight superiority than principal component analysis. Using leaf color patterns was possible to infer about leaf nutrient concentrations in Eucalyptus. Both methods were able to distinguish only the healthy leaves 7.5 GY 8/8 from those whose were in the leaf senescence process.