Estimation of Physical and Chemical Soil Properties by Artificial Neural Networks

Abstract

Soil physical and chemical analyses are relatively high-cost and time-consuming procedures. In the search for alternatives to predict these properties from a reduced number of soil samples, the use of Artificial Neural Networks (ANN) has been pointed out as a great computational technique to solve this problem by means of experience. This tool also has the ability to acquire knowledge and then apply it. This study aimed at using ANNs to estimate the physical and chemical properties of soil. The data came from the physical and chemical analysis of 120 sampling points, which were submitted to descriptive analysis, geostatistical analysis, and ANNs training and analysis. In the geostatistical analysis, the semivariogram model that best fitted the experimental variogram was verified for each soil property, and the ordinary kriging was used as an interpolation method. The ANNs were trained and selected based on their assertiveness in the mapping of considered standards, and then used to estimate all soil properties. The mean errors of ordinary kriging estimates were compared to those of ANNs and then compared to the original values using Student's t-Test. The results showed that the ANN had an assertiveness compatible with ordinary kriging. Therefore, such technique is a promising tool to estimate soil properties using a reduced number of soil samples.

Application of artificial neural networks in the study of Mozzarella cheese salting

“…For this reason, there is a need for highly efficient methods and applications to treat the results. A tool that has been shown to be suitable for treatments, in data that have nonlinear behaviors, are the Artificial Neural Networks (ANNs) (Borsato et al, 2011;Bittar et al, 2018).…”

Estimativa Da Necessidade De Fósforo E Potássio Para O Tomate Industrial Utilizando Redes Neurais Artificiais

“…Os dados foram coletados em uma grade amostral de 60x60m (Figura 1a) de acordo com metodologia descrita por Bittar et al (2018), totalizando 120 pontos amostrais. Cada ponto foi georreferenciado utilizando aparelho de Sistema de Posicionamento Global (GPS), da marca Garmin modelo Etrex Legend RoHs (erro ± 3m), com sistema de correção diferencial em tempo real via satélite e com o datum ajustado ao sistema SIRGAS 2000.…”

Gestão no meio agrícola com o apoio da Inteligência Artificial: uma análise da digitalização da agricultura

“…ANN é derivada do caráter de modelo de rede, ou seja, sua capacidade de aproximação geral a um método com simplicidade em sua teoria, facilidade de programação e bons resultados (BITTAR; ALVES;MELO, 2018;BONIECKI et al, 2014). Um passo importante para a construção do modelo de ANN é a seleção do tipo de rede (sua topologia), juntamente com a escolha de uma função de ativação ao algoritmo de aprendizado de máquina (SIMONE; RIVERA; GUIDA, 2018; TOPUZ, 2010).…”