One-Dimensional Convolutional Neural Networks for Hyperspectral Analysis of Nitrogen in Plant Leaves

Accurately determining the nutritional status of plants can prevent many diseases caused by fertilizer disorders. Leaf analysis is one of the most used methods for this purpose. However, in order to get a more accurate result, disorders must be identified before symptoms appear. Therefore, this study aims to identify leaves with excessive nitrogen using one-dimensional convolutional neural networks (1D-CNN) on a dataset of spectral data using the Keras library. Seeds of cucumber were planted in several pots and, after growing the plants, they were divided into different classes of control (without excess nitrogen), N30% (excess application of nitrogen fertilizer by 30%), N60% (60% overdose), and N90% (90% overdose). Hyperspectral data of the samples in the 400–1100 nm range were captured using a hyperspectral camera. The actual amount of nitrogen for each leaf was measured using the Kjeldahl method. Since there were statistically significant differences between the classes, an individual prediction model was designed for each class based on the 1D-CNN algorithm. The main innovation of the present research resides in the application of separate prediction models for each class, and the design of the proposed 1D-CNN regression model. The results showed that the coefficient of determination and the mean squared error for the classes N30%, N60% and N90% were 0.962, 0.0005; 0.968, 0.0003; and 0.967, 0.0007, respectively. Therefore, the proposed method can be effectively used to detect over-application of nitrogen fertilizers in plants.

Estimation of Diagnosis and Recommendation Integrated System (DRIS), Compositional Nutrient Diagnosis (CND) and Range of Normality (RN) Norms for Mineral Diagnosis of Almonds Trees in Spain

To ensure good fertilization, it is necessary to know the optimum nutrient levels for each crop. The most common method for obtaining this information for almond trees is to perform a foliar analysis coupled with the use of interpretive tools such as the traditional range of normality. However, currently, there are other, more sophisticated methods such as the DRIS (Diagnosis and Recommendation Integrated System) and the CND (Compositional Nutrient Diagnosis) which take into account the relationship between nutrients. However, little information is available with respect to these methods in the case of almond trees. In the present work, 288 samples of three contrasting varieties of almond were analyzed—Ferraduel, Ferragnes, and Garrigues (Prunus dulcis, Mill.)—corresponding to bi-weekly sampling between the months of May and September. Leaf analysis data, run with different mathematical and statistical models, lead to knowledge of the optimum period for harvesting samples and the determination of the ranges of normality and norms of DRIS and CND for the Ferraduel, Ferragnes, and Garrigues varieties. Data gained from the leaf nutrient content reported that the best season to harvest and interpret leaf samples was July. In addition, Ferraduel and Ferragnes had higher N, P, and K (2.22, 0.14, and 1.04 mg Kg−1 dw, respectively) than Garrigues (2.00, 0.09. 0.67 mg Kg−1 dw). The norms obtained with the leaf mineral data showed similar values between the Ferraduel and Ferragnes varieties but different values for Garrigues variety. Therefore, Garriges had the highest N/P, N/K, P/K, and P × Mg norms in the DRIS method and the highest VN and VCa norms in the CND method.

Seasonal changes of macronutrients concentration in olive trees grown in acid and in alkaline soils

Leaf samples from mature olive (Olea europaea L. cv. ‘Kalamon’) trees were collected monthly from April 2018 to March 2019 from two olive orchards, cultivated one in acid and one in alkaline soil, located in Western Greece. Nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), and magnesium (Mg) concentrations in the leaves were determined and seasonal variation curves were calculated for each nutrient and orchard. The seasonal concentration patterns of N, P, K, Ca, and Mg nutrients were almost similar in both soils. Seasonal variation nutrient curves independently of soil acidity varied according to vegetation stages and no significant differences in nutrient concentrations were observed at different development stages between olives grown in the acid or the alkaline soils, with only one exception the leaf K concentration. The nutrient concentration measured in wintertime was at a sufficient level for optimum olive growth in both orchards. These concentrations could be used as reference values for leaf analysis interpretation and for developing an optimum fertilization program under Mediterranean climatic conditions.

Occurrence of Fungicides in Vineyard and the Surrounding Environment

Seventeen fungicides were determined in different matrices from vineyard areas, including vine leaves, soils, grapes and water, using gas chromatography coupled to tandem mass spectrometry (GC-MS/MS). For leaf analysis, ultrasound-assisted extraction (UAE) was performed evaluating different solvents. UAE was compared with other extraction techniques such as vortex extraction (VE) and matrix solid-phase dispersion (MSPD). The performance of the UAE method was demonstrated on vine leaf samples and on other types of samples such as tea leaves, underlining its general suitability for leaf crops. As regards other matrices, soils were analyzed by UAE and microwave-assisted extraction (MAE), grapes by UAE and waters by SPE using cork as the sorbent. The proposed method was applied to 17 grape leaf samples in which 14 of the target fungicides were detected at concentrations up to 1000 μg g−1. Furthermore, the diffusion and transport of fungicides was demonstrated not only in crops but also in environmental matrices.

APROVEITAMENTO DA ÁGUA DO PROCESSAMENTO DOS FRUTOS DE CAFÉ NA FERTIRRIGAÇÃO DE Brachiaria mutica

Considerando que a aplicação da água do processamento de café (APC), via fertirrigação, pode promover alterações nos teores de K do solo, na planta e na produção de massa seca do Brachiaria mutica (Capim Angola), realizou-se um trabalho com o objetivo de avaliar os teores disponíveis de K no perfil de um Neossolo Flúvico, na planta, e na produção de massa seca do capim angola decorrentes da aplicação de diferentes doses de APC. As parcelas receberam cinco tratamentos sendo: doses de APC 0, 57, 114, 171 e 228m³/ha, calculados de forma que a dose 114m³/ha elevasse o teor de K a 5% na CTC (T) do solo. Foram coletadas amostras de solo, aos 45 e 90 dias após a aplicação da APC, nas profundidades de 0 a 20 cm; 20 a 40 cm; 40 a 60 cm e 60 a 80 cm. Realizado também coletas, no mesmo período, de amostras para análise foliar e de massa seca. O uso da APC, na dose de 114 m³/ha promoveu incremento de K no solo apenas na camada de 0-20 cm. Observou-se ainda incremento em camadas inferiores mediante dosagens superiores. Não houve diferença na produção de biomassa e teores de nutrientes na planta, mediante os diversos tratamentos. Palavras-chave: pós-colheita; nutrição; lixiviação; potássio. Use of water for processing coffee beans in the fertigation of Brachiaria mutica ABSTRACT: Considering that the application of water from coffee processing (WCP), via fertigation, can promote changes in the K content of the soil, in the plant and the production of the dry mass of Brachiaria mutica (Capim Angola), work was carried out to evaluate evaluating the available levels of K in the profile of a Floss Neossol, in the plant, and the production of the dry mass of the Angola grass resulting from the application of different doses of WPC. The plots received five treatments: WPC doses 0, 57, 114, 171, and 228m³ / ha, calculated so that the 114m³ / ha dose raised the K content to 5% in the CTC (T) of the soil. Soil samples were collected at 45 and 90 days after WPC application, at depths of 0 to 20 cm; 20 to 40 cm; 40 to 60 cm and 60 to 80 cm. Samples for leaf analysis and dry mass were also collected in the same period. The use of WPC, at a dose of 114 m³ / ha, increased K in the soil only in the 0-20 cm layer. An increase was also observed in lower layers through higher dosages. There was no difference in the production of biomass and nutrient contents in the plant, through the different treatments. Keywords: Post-harvest; nutrition; leaching; potassium.

Reference values and diagnostic ranges to assess the degree of nutritional balance for cacao plants

Aim of study: The interpretation of results of leaf analysis can be performed by nutritional balance methods, such as Kenworthy method (KW) and diagnostic levels of contents, whose achievements for cacao constitute the main objective of this work.Area of study: Bahia, Brazil.Material and methods: The database covered cacao trees in two cultivation systems: agroforestry systems and full sun. The reference populations were composed of plots with relative yield higher than the average plus half a standard deviation of each of these cultivation systems, in addition to a combined population of both systems.Main results: The norms of the KW method were compared by the t test, for mean, with 72% concordance; and F, for variance, 82% concordant. The diagnoses made based on specific norms per cultivation system and the general norm agreed on average of 91%. Potential response curves were obtained as a function of the Balanced Indices of Kenworthy (BIK) for each nutrient, by the boundary-line method, in addition to sufficiency ranges for BIK and for leaf contents for cacao.Research highlights: It is concluded that the general KW norms associated with the original Kenworthy ranges or the specific ranges for cacao are efficient in the nutritional diagnosis of cacao.

Chemical analyses of flowers and leaves for nutritional diagnoses of coffee trees

ABSTRACT: The chemical analysis of flowers has been studied for some crops. In coffee trees, the flower tissue analysis could anticipate the nutritional diagnosis. This study aimed to: (i) compare the mineral composition of coffee flowers and leaves; and to (ii) generate reference values for nutritional diagnosis of coffee trees, based on flower and leaf analysis. Nutrient content of flowers and leaves and coffee productivity were evaluated in 26 commercial farms located in Manhuaçu, MG, Brazil throughout three years. The critical nutrient content range in flowers are respectively: 2.78 - 3.17, 0.23 - 0.28, 2.80 - 3.12, 0.30 - 0.37, 0.24 - 0.30, 0.15 - 0.18 dag kg-1 of N, P, K, Ca, Mg, and S; and 17 - 21, 12 - 18, 52 - 80, 26 - 43, and 28 - 48 mg kg-1 of Zn, Cu, Mn, Fe, and B. For leaves, the critical nutrient ranges are respectively: 2.63 - 2.86, 0.13 - 0.14, 2.13 - 2.33, 1.04 - 1.22, 0.27 - 0.33, 0.15 - 0.18 dag kg-1 of N, P, K, Ca, Mg, and S; and 9 - 14, 15 - 23, 80 - 115, 99 - 148, and 31 - 37 mg kg-1 of Zn, Cu, Mn, Fe, and B. The nutritional diagnosis of coffee trees for N, P, Ca, Fe, Cu, and Mn can be anticipated using flower analysis.