Neural network and state-space models for studying relationships among soil properties

Luís Carlos Timm,Emanuel Pimentel Barbosa,Manoel Dornelas De Souza,José Flávio Dynia,Klaus Reichardt,Daniel Takata Gomes

doi:10.1590/s0103-90162006000400010

Luís Carlos Timm, Emanuel Pimentel Barbosa + Show 4 more

Open Access

https://doi.org/10.1590/s0103-90162006000400010

Copy DOI

Abstract

The study of soil property relationships is of great importance in agronomy aiming for a rational management of environmental resources and an improvement of agricultural productivity. Studies of this kind are traditionally performed using static regression models, which do not take into account the involved spatial structure. This work has the objective of evaluating the relation between a time-consuming and "expensive" variable (like soil total nitrogen) and other simple, easier to measure variables (as for instance, soil organic carbon, pH, etc.). Two important classes of models (linear state-space and neural networks) are used for prediction and compared with standard uni- and multivariate regression models, used as reference. For an oat crop cultivated area, situated in Jaguariuna, SP, Brazil (22º41' S, 47º00' W) soil samples of a Typic Haplustox were collected from the plow layer at points spaced 2 m apart along a 194 m spatial transect. Recurrent neural networks and standard state-space models had a better predictive performance of soil total nitrogen as compared to the standard regression models. Among the standard regression models the Vector Auto-Regression model had a better predictive performance for soil total nitrogen.

Highlights

The relationships among soil properties can be of great advantage in agronomy as a tool for a more rational and adequate management of environmental resources and improvement of agricultural productivity
The study of soil property relationships is of great importance in agronomy aiming for a rational management of environmental resources and an improvement of agricultural productivity
The development of models which simulate soil processes expanded rapidly in the last years. They are meant for the improvement and understanding of important processes and act as a tool for clarifying problems related to agricultural activities and the environment (McBratney et al, 2002)

Summary

Introduction

The relationships among soil properties can be of great advantage in agronomy as a tool for a more rational and adequate management of environmental resources and improvement of agricultural productivity. The development of models which simulate soil processes expanded rapidly in the last years. They are meant for the improvement and understanding of important processes and act as a tool for clarifying problems related to agricultural activities and the environment (McBratney et al, 2002). An example of this is the application of the state-space methodology to describe relations between soil and plant The artificial neural networks were introduced for studying spatial relationships among such agronomic variables (Pachepsky et al, 1996; Schaap et al, 1998; Minasny et al, 1999; and more recently Nemes et al, 2003)

Methods

Results

Conclusion