Exploring Precision Farming Scenarios Using Fuzzy Cognitive Maps

Abstract

Abstract:One of the major problems confronted in precision agriculture is uncertainty about how exactly would yield in a certain area respond to decreased application of certain nutrients. One way to deal with this type of uncertainty is the use of scenarios as a method to explore future projections from current objectives and constraints. In the absence of data, soft computing techniques can be used as effective semi-quantitative methods to produce scenario simulations, based on a consistent set of conditions. In this work, we propose a dynamic rule-based Fuzzy Cognitive Map variant to perform simulations, where the novelty resides in an enhanced forward inference algorithm with reasoning that is characterized by magnitudes of change and effects. The proposed method leverages expert knowledge to provide an estimation of crop yield, and hence it can enable farmers to gain insights about how yield varies across a field, so they can determine how to adapt fertilizer application accordingly. It allows also producing simulations that can be used by managers to identify effects of increasing or decreasing fertilizers on yield, and hence it can facilitate the adoption of precision agriculture regulations by farmers. We present an illustrative example to predict cotton yield change, as a response to stimulated management options using proactive scenarios, based on decreasing Phosphorus, Potassium and Nitrogen. The results of the case study revealed that decreasing the three nutrients by half does not decrease yield by more than 10%.

A Systemic Approach to City Image Building. The Case of Katowice City

“…FCM was widely used in participatory modeling (e.g., [97,103]). It can be helpful in supporting planning decisions in engineering and technology management [104] and in scenario building [105,106]. FCM seems to be also a valuable tool in future studies [107].…”

Evaluating poverty alleviation strategies in a developing country

“…The scenarios formed through FCM-based simulations can serve to guide managers and policy-makers during the decision-making process [62][63][64]66,69,82,[88][89][90]]. An FCM is formed out of the adjacency matrix and a state vector, representing the values of the connections between the concepts and the values of the system concepts [62,63,69].…”

“…We have used an increasingly popular activation rule [61][62][63][64]90,91] introduced by Stylios [94], which is as follows:…”

“…Where, n is the total number of concepts, A i (t+1) is the value of concept C i at simulation step t +1, A i (t) is the value of concept C i at simulation step t, A j (t) is the value of concept C j at simulation step t, w ji is the weight of the interconnection between concept C j and concept C i , and f is the transformation function [64,90]. The restriction i 6 ¼ j is used when self-causation is assumed to be impossible [91].…”

“…The simulation outcomes also depend on the type of transformation function used. The most frequently used transformation functions (ƒ) are sigmoid and hyperbolic tangent functions [90][91][92][93]. When the values of concepts can only be positive, i.e.…”