Weather-based prediction of anthracnose severity using artificial neural network models

Data were collected and analysed from seven field sites in Australia, Brazil and Colombia on weather conditions and the severity of anthracnose disease of the tropical pasture legume Stylosanthes scabra caused by Colletotrichum gloeosporioides. Disease severity and weather data were analysed using artificial neural network (ANN) models developed using data from some or all field sites in Australia and/or South America to predict severity at other sites. Three series of models were developed using different weather summaries. of these, ANN models with weather for the day of disease assessment and the previous 24 h period had the highest prediction success, and models trained on data from all sites within one continent correctly predicted disease severity in the other continent on more than 75% of days; the overall prediction error was 21.9% for the Australian and 22.1% for the South American model. of the six cross-continent ANN models trained on pooled data for five sites from two continents to predict severity for the remaining sixth site, the model developed without data from Planaltina in Brazil was the most accurate, with >85% prediction success, and the model without Carimagua in Colombia was the least accurate, with only 54% success. In common with multiple regression models, moisture-related variables such as rain, leaf surface wetness and variables that influence moisture availability such as radiation and wind on the day of disease severity assessment or the day before assessment were the most important weather variables in all ANN models. A set of weights from the ANN models was used to calculate the overall risk of anthracnose for the various sites. Sites with high and low anthracnose risk are present in both continents, and weather conditions at centres of diversity in Brazil and Colombia do not appear to be more conducive than conditions in Australia to serious anthracnose development.

Prediction of occurrences of diverse chemical classes in the Asteraceae through artificial neural networks

The training and the application of a neural network system for the prediction of occurrences of secondary metabolites belonging to diverse chemical classes in the Asteraceae is described. From a database containing about 604 genera and 28,000 occurrences of secondary metabolites in the plant family, information was collected encompassing nine chemical classes and their respective occurrences for training of a multi-layer net using the back-propagation algorithm. The net supplied as output the presence or absence of the chemical classes as well as the number of compounds isolated from each taxon. The results provided by the net from the presence or absence of a chemical class showed a 89% hit rate; by excluding triterpenes from the analysis, only 5% of the genera studied exhibited errors greater than 10%. Copyright (C) 2004 John Wiley Sons, Ltd.

An intelligent system to real time rainfall prediction using radar data

This work presents a new approach for rainfall measurements making use of weather radar data for real time application to the radar systems operated by institute of Meteorological Research (IPMET) - UNESP - Bauru - SP-Brazil. Several real time adjustment techniques has been presented being most of them based on surface rain-gauge network. However, some of these methods do not regard the effect of the integration area, time integration and distance rainfall-radar. In this paper, artificial neural networks have been applied for generate a radar reflectivity-rain relationships which regard all effects described above. To evaluate prediction procedure, cross validation was performed using data from IPMET weather Doppler radar and rain-gauge network under the radar umbrella. The preliminary results were acceptable for rainfalls prediction. The small errors observed result from the spatial density and the time resolution of the rain-gauges networks used to calibrate the radar.

Prediction and spatial variability of soil dynamic properties in sugar cane fields of São Paulo State Brazil

The objective of this work was to model and diagnose the spatial variability of soil load support capacity (SLSC) in sugar cane crop fields, as well as to evaluate the management impact on São Paulo State soil structure. The investigated variables were: pressure preconsolidation (sigma(p)), apparent cohesion () and internal friction angle (). The conclusions from the results were that the models and spatial dependence maps constitute important tools in the prediction and location of the mechanical internal strength of soils cultivated with sugar cane. They will help future soil management decisions so that soil structure sustainability will not be compromised.

Synthesis, characterization and electrochemical study of layered double hydroxides intercalated with 2-thiophenecarboxylate anions

The synthesis, characterization, and electrochemical study of the Zn(II)-Al(III) and Zn(II)-Cr(III) Layered Double Hydroxides (LDHs) containing 2-thiopenecarboxylate as the interlayer anions are described. The LDHs were prepared by the constant pH coprecipitation technique followed by hydrothermal treatment for 72 h. The materials were analyzed by PXRD, FT-IR, C-13 CP-MAS, EDX, TEM, and CV. The presence of the organic heterocyclic anions was confirmed by FT-IR and the related solid-state C-13 NMR data strongly suggested that these were dimerised during coprecipitation. Accordingly, the basal spacing found by the X-ray technique was similar to 15.3 Angstrom, a distance coincident with the formation of bilayers of the intercalated anions. The structural organization of all the new materials was greatly enhanced by hydrothermal treatment, as shown by PXRD. The improved organization of the bilayered structures had a strong influence in the electrochemical behaviour of clay-modified electrodes produced with these materials, such as the diminished resistance to the ionic flow through the LDHs films. (C) 2003 Elsevier Ltd. All rights reserved.

Prediction via neural networks of the residual hydrogen peroxide used in photo-fenton processes for effluent treatment

This communication proposes the use of neural networks in the prediction of residual concentrations of hydrogen peroxide from the treatment of effluents through Advanced Oxidative Processes (AOP's), in particular, the photo-Fenton process. To verify the efficiency of the oxidative process, the Chemical Oxygen Demand (COD) parameter, the values of which may be modified by the presence of oxidizing agents such as residual hydrogen peroxide, is frequently taken in account. The analysis of the H2O2 interference was performed by spectrophotometry at 450 nm wavelength, via the monitoring of the reaction of ammonia with metavanadate. The results of the hydrogen peroxide residual concentration were modeled via a feedforward neural network, with the correlation coefficients between actual and predicted values above 0.96, indicating good prediction capacity.

Magnetic field of an in-plane vortex inside and outside a layered superconducting film

In the present work we study an anisotropic layered superconducting film of finite thickness. The film surfaces are considered parallel to the be face of the crystal. The vortex lines are oriented perpendicular to the film surfaces and parallel to the superconducting planes. We calculate the local field and the London free energy for this geometry. Our calculation is a generalization of previous works where the sample is taken as a semi-infinite superconductor. As an application of this theory we investigate the flux spreading at the super conducting surface.

Optimization of Radial Basis Function neural network employed for prediction of surface roughness in hard turning process using Taguchi's orthogonal arrays

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Field profiles of bulk plasmon polariton modes in layered systems containing a metamaterial

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Investigation of Ferroelectric Layered Perovskite Barium Bismuth Tantalate Prepared by Solid-State Reaction

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Unfolding of plasmon-polariton modes in one-dimensional layered systems containing anisotropic left-handed materials

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Use of progeny testing in beef cattle: Prediction of genetic gain in a Nelore Cattle Breeding Program

Genetic gains predicted for selection, based on both individual performance and progeny testing, were compared to provide information to be used in implementation of progeny testing for a Nelore cattle breeding program. The prediction of genetic gain based on progeny testing was obtained from a formula, derived from methodology of Young and Weiler (J. Genetics 57: 329-338, 1960) for two-stage selection, which allows prediction of genetic gain per generation when the individuals under test have been pre-selected on the basis of their own performance. The application of this formula also allowed determination of the number of progeny per tested bull needed to maximize genetic gain, when the total number of tested progeny is limited.

Morphological prediction of worker size discrimination and relative abundance of sympartic species of Pseudacteon (Dipt., Phoridae) parasitoids of the fire ant, Solenopsis saevissima (Hym., Formicidae) in Brazil

Patterns of attack for collected species of phorids are predicted using multivariate morphometrics of female Pseudacteon species and worker size distributions of parasitized fire ants, Solenopsis saevissima. The model assumes that there is a direct correlation between phorid size and the size range of the worker ant attacked, and presumes that worker sizes are a resource that is divided by sympatric phorid species to minimize joint parasitism. These results suggest that the community of sympatric Pseudacteon species on only one host species coexists by restricting the size of workers attacked, and secondarily by differing diel patterns of ovipositional activity. When we compared relative abundance of species of Pseudacteon with the size distribution of foragers of S. saevissima, our observed distribution did not differ significantly from our predicted relative abundance of females of Pseudacteon. The activity of Pseudacteon may be a factor determining forager size distributions.