This study aimed to evaluate the Artificial Neural Network (ANN) to establish a classification and analysis of degraded soils and its recovery in response to lime and gypsum application. The analyzed degraded soil was classified as Oxisol, and the physical attributes considered were: soil density, soil porosity (macroporosity and microporosity) and soil penetration resistance. The ANN used in this study is the backpropagation composed of two layers, the middle layer and the output layer, with supervised training. The network has four inputs, that are the physical attributes of the soil, in the middle layer the network contains ten neurons and the output layer only one neuron, which has the function of informing if the soil was recovered (R), partially recovered (PR) or not recovered (NR). The analyzed data come from the year 2012, concerning the depths 0.0-0.1 m, 0.1-0.2 m and 0.2-0.4 m. Considering the performance of ANN, it was verified that the network obtained an adequate training to classify the degraded soils, showing low mean square error of analyzed data. Therefore, ANN is considered an interesting alternative and a powerful automatic tool to classify degraded soils during recovery process.
The objective of this study was to study the physical attributes and the organic matter of a Red-Yellow Oxisol cultivated with Urochloa decumbens pasture in recovery with different introducing ways of Stylosanthes cv. Campo Grande. The experiment was conducted at the Agency for Agribusiness Technology of São Paulo (APTA), in the municipality of Andradina/ SP, between October 2016 and September 2017. The experimental design was the randomized complete block design with four replicates and the treatments were composed of six strategies (partial desiccation, total desiccation, scarification, "rome" harrowing and plowing + harrowing.) in the no-tillage legume in the pasture, in addition to the control. Stability of aggregates, flocculation, soil porosity, organic matter and soil texture were evaluated in three layers: 0-0.10; 0.10-0.20 and 0.20-0.40 m. Soil organic matter content was higher in the topsoil layers (from 15.75 to 17.75 mg dm -3 ) and decreased with depth (from 10.50 to 11.50 mg dm -3 ). The indicated macroporosity was below the value considered ideal for the plants development. Studied treatments did not influence the organic matter content, porosity and soil density. Soil quality was influenced up to 0.20 m with the introduction of stylosanthes, regardless of the adopted management.Recuperação de pastagem utilizando Estilosantes cv. Campo Grande: efeito na qualidade do solo RESUMO: Objetivou-se estudar atributos físicos e a matéria orgânica de um Latossolo Vermelho Amarelo cultivado com pastagem de Urochloa decumbens em recuperação com diferentes formas de introdução de estilosantes cv. Campo Grande. O experimento foi realizado na Agência Paulista de Tecnologia dos Agronegócios (APTA), no município de Andradina/SP, entre outubro de 2016 e setembro de 2017. O delineamento experimental foi em blocos ao acaso, com quatro repetições e os tratamentos foram compostos por seis estratégias (dessecação parcial, dessecação total, escarificação, gradagem rome e aração +gradagem) em plantio direto da leguminosa na pastagem, além da testemunha. Foram avaliados a estabilidade de agregados, floculação, porosidade, matéria orgânica e textura do solo, em três camadas: 0-0,10; 0,10-0,20 e de 0,20-0,40 m. O teor de matéria orgânica no solo foi superior nas camadas superficiais (15,75 a 17,75 mg dm -3 ) e diminuiu em profundidade (10,50 a 11,50 mg dm -3 ). A macroporosidade indicada ficou abaixo do valor considerado ideal para o desenvolvimento das plantas. Os tratamentos estudados não influenciaram o teor de matéria orgânica, a porosidade e densidade do solo. A qualidade do solo foi influenciada até 0,20 m com a introdução do estilosantes, independente do manejo adotado. Palavras-chave: área degradada; matéria orgânica; atributos físicosPasture recovery using Stylosanthes cv. Campo Grande: effect on soil quality Rev. Bras.
RESUMORedes neurais artificiais são modelos computacionais que consistem na semelhança da maneira como um organismo vivo manipula as informações recebidas e com isso, possuem capacidade de aprendizado, adaptabilidade e generalização do conhecimento. Além disso, o modelo de processamento de uma Rede Neural Artificial é baseado no paralelismo, assemelhando-se como o cérebro lida com as informações recebidas por seus neurônios. O presente trabalho foi dividido em duas partes, em que nesta primeira descreve o estudo da rede neural artificial Retropropagação (backpropagation) como um classificador de grupos, utilizando dois processos básicos desempenhados por uma rede neural artificial, as fases de treinamento ou aprendizado e a fase de operação. O objetivo principal é mostrar o processo de funcionamento dessas fases. Na parte II, é apresentado aplicações da metodologia para classificar grupos, tipos de frutas e solos. PALAVRAS-CHAVE:Neurônio artificial, Classificação de grupos, Retropropagação, Treinamento. ARTIFICIAL NEURAL NETWORKS: ALGORITHM BACKPROPAGATION USE FOR CLASSIFICATION OF GROUPS IN BIOSYSTEMS, PART 1: INTRODUCTION THEORY.ABSTRACT Artificial neural networks are computational models that consist of similarity with a organism and thus, have learning ability, adaptability and generalization of knowledge. In addition, the processing model of an Artificial Neural Network is based on parallelism, resembling how the brain handles the information received by your neurons. This study was divided into two parts, where this first describes the study of artificial neural network Backpropagation as a classifier of groups using two basic processes performed by an artificial neural network, the phases of training or learning and operation phase. The main objective is to show the functioning process of these phases. In Part II, methodology of applications is presented to classify groups, types of fruits and soils.
Proper soil management techniques are essential to keep the soil healthy and without degradation. When this is not possible, this soil must be recovered, taking into account the attributes of the soil and its regenerative power, with this, several techniques are being used. In this context, this work aims to develop an interactive program (analyze and classify) using Artificial Neural Networks (ANN) to estimate soil recovery levels (recovered (R), partially recovered (PR) and not recovered (NR) as a function of physical attributes. The experiment was carried out at the São Paulo Agribusiness Technology Agency - APTA do Extremo Oeste, in Andradina / SP from 2015 to 2017, in soil classified as Ultisol cultivated with Urochloa pasture, with different ways of introducing Estilosantes cv. Campo Grande. The soil attributes studied were: soil density, soil porosity, mechanical resistance to penetration, water infiltration in the soil and weighted average diameter in the soil layers: 0-10; 0.10-0.20 and 0.20-0.40 m The program was developed in the MATLAB environment and the simulation was performed using a graphical interface. and work was the multilayer Perceptron (MLP). It was found that the network achieved adequate training, with a low mean square error, which could generate an interesting and automatic alternative for the classification and analysis of recovering soils. The results were printed on a self-explanatory graphical interface, with graphs and metadata of the physical indexes and their classifications regarding ANN.
RESUMOAs Redes Neurais Artificiais (RNA) são modelos computacionais que se assemelham aos neurônios biológicos, capaz de realizar aprendizado e manipular informações recebidas. O trabalho foi dividido em duas partes, em que a primeira descreve o estudo da rede neural artificial Retropropagação (backpropagation) enessa segunda partesão apresentadas suasaplicações. A primeira aplicação é uma classificação do tipo de frutas, laranja (Citrus sinensis Osbeck) ou tangerina "Ponkan" (Citrus reticulate Blanco), ou seja, com três entradas para cada amostra (P, pH e Ca), a rede neural é capaz de classificar qual é o tipode fruta referente aquela amostra, a ideia desta aplicação é apenas mostrar o funcionamento da rede. Já a segunda aplicação euma classificadora de níveis de solos degradados de acordo com seus atributos químicos.Com os resultados obtidos via RNA, observou-se que os solos analisados apresentam fertilidade aparente muito baixaindicando sua degradação e também mostrou que quanto mais profundo o solo, menor é sua fertilidade aparente, o que é esperado. PALAVRAS-CHAVE:Neurônio artificial, Classificação de grupos, Retropropagação, Aplicação em Biossistemas. ARTIFICIAL NEURAL NETWORKS : ALGORITHM BACKPROPAGATION USE FOR CLASSIFICATION OF GROUPS IN BIOSYSTEMS , PART 2 : APPLICATION ABSTRACTThe Artificial Neural Networks (ANN) are computer models that resemble biological neurons, able to perform learning and manipulate information received. The study was divided into two parts, wherein the first part describes the study of Backpropagation neural network and this second part the applications. The first application is a classification of the type of fruit, orange (Citrus sinensis Osbeck)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.