Comparison of Three Computational Approaches for Tree Crop Irrigation Decision Support

Abstract

This paper explores methodologies for developing intelligent automated decision systems for complex processes that contain uncertainties, thus requiring computational intelligence. Irrigation decision support systems (IDSS) promise to increase water efficiency while sustaining crop yields. Here, we explored methodologies for developing intelligent IDSS that exploit statistical, measured, and simulated data. A simple and a fuzzy multicriteria approach as well as a Decision Tree based system were analyzed. The methodologies were applied in a sample of olive tree farms of Heraklion in the island of Crete, Greece, where water resources are scarce and crop management is generally empirical. The objective is to support decision for optimal financial profit through high yield while conserving water resources through optimal irrigation schemes under various (or uncertain) intrinsic and extrinsic conditions. Crop irrigation requirements are modelled using the FAO-56 equation. The results demonstrate that the decision support based on probabilistic and fuzzy approaches point to strategies with low amounts and careful distributed water irrigation strategies. The decision tree shows that decision can be optimized by examining coexisting factors. We conclude that irrigation-based decisions can be highly assisted by methods such as decision trees given the right choice of attributes while keeping focus on the financial balance between cost and revenue.

A Machine Learning Framework for Olive Farms Profit Prediction

“…Olive tree farms are the major agricultural activity. Irrigation strategies are usually absent, and the number of water resources spent are based on the empirical knowledge of the farmers [28]. For our research, real data coming from olive farms in Crete were used.…”

“…Total yield records were examined along with irrigation amounts as well as water and olive prices to calculate the profit for a season. Modeling was conducted to enrich those historical records with information regarding the effect of applying irrigation patterns [28]. Based on soil and tree characteristics and the climate conditions, necessary humidity to keep the farm in productive development was defined.…”

“…The financial trends and the olive oil market tendency are out of the scope of this article, but the participating factors are combined into forming a powerful decision tool. Stochastic and more sophisticated decision approaches like fuzzy logic can enhance simplistic rule-based systems [28]. Although multiple criteria can participate, those methods reach a certain point and cannot further extract valuable interconnections among them, due to the probabilistic nature of the methodologies [28] Knowledge extraction and reliable prediction for future unseen scenarios are feasible when combining different (in scope) but relevant in interdependency variables.…”

“…Stochastic and more sophisticated decision approaches like fuzzy logic can enhance simplistic rule-based systems [28]. Although multiple criteria can participate, those methods reach a certain point and cannot further extract valuable interconnections among them, due to the probabilistic nature of the methodologies [28] Knowledge extraction and reliable prediction for future unseen scenarios are feasible when combining different (in scope) but relevant in interdependency variables. Training on historical data and prediction performance can be explored via Machine Learning methods to take advantage of relations among input historical data [29].…”

“…This paper is based upon previous work [28] where an irrigation decision set of strategies was examined. Our case study deals with olive farms on the island of Crete facing challenges like low water availability combined with high agricultural demand and extreme climatic droughts [32].…”