Triple Bottomline Many-Objective-Based Decision Making for a Land Use Management Problem

Abstract

A land use many-objective optimization problem for a 1500-ha farm with 315 paddocks was formulated with 14 objectives (maximizing sawlog production, pulpwood production, milksolids, beef, sheep meat, wool, carbon sequestration, water production, income and Earnings Before Interest and Tax; and minimizing costs, nitrate leaching, phosphorus loss and sedimentation). This was solved using a modified Reference-point-based Non-dominated Sorting Genetic Algorithm II augmented by simulated epigenetic operations. The search space had complex variable interactions and was based on economic data and several interoperating simulation models. The solution was an approximation of a Hyperspace Pareto Frontier (HPF), where each non-dominated trade-off point represented a set of land-use management actions taken within a 10-year period and their related management options, spanning a planning period of 50 years. A trade-off analysis was achieved using Hyper-Radial Visualization (HRV) by collapsing the HPF into a 2-D visualization capability through an interactive virtual reality (VR)-based method, thereby facilitating intuitive selection of a sound compromise solution dictated by the decision makers' preferences under uncertainty conditions. Four scenarios of the HRV were considered emphasizing economic, sedimentation and nitrate leaching aspects-giving rise to a triple bottomline (i.e. the economic, environmental and social complex, where the social aspect is represented by the preferences of the various stakeholders). Highlights of the proposed approach are the development of an innovative epigenetics-based multi-objective optimizer, uncertainty incorporation in the search space data and decision making on a multi-dimensional space through a VR-simulation-based visual steering process controlled at its core by a multi-criterion decision making-based process. This approach has widespread applicability to many other 'wicked' societal problem-solving tasks.

Optimal Clustering and Cluster Identity in Understanding High-Dimensional Data Spaces with Tightly Distributed Points

“…Therefore, we switch our focus to the 100th generation Pareto front, PF10, which was the final Pareto front solution to the New Zealand farming problem. The reason for this switch is because this Pareto front has been thoroughly investigated using a bevy of visualization techniques, such as Parallel Coordinates Plots, Andrew plots, 3D Andrews plots, Permutation Tours, Grand Tours, and DMS [26], a visualization virtual-reality or desktop based visual-steering technique derived from the concepts of Design by Shopping [39], and Hyper Radial Visualization [37], as described earlier. Therefore, we do have an idea of what the very best solutions are.…”

“…The current modifications satisfy the spatial constraints and convergence is tracked while using an average Minkowski's distance [27] for each generation based on parallel coordinate plots of the 14 fitness functions. A clearly exponential decay trend of the average Minkowski's distance is observed, something that could not be achieved by [26], and it is now taking under two hours to solve on the same 6-core processor Mac pro. We avoid a full description here and also the improvements, because this is outside the scope of this manuscript and it would be in breach of Living PlanIT trade secrets.…”

“…Therefore, the modifications of the many-objective evolutionary algorithm were based on cues that were taken from nature with a mathematical foundation, as described in the 2013 Wiley Practical Prize Award winning paper [26], which used to take 10 hours to solve on a Mac pro with a 6-core processor, but still without successfully resolving the spatial constraints. The current modifications satisfy the spatial constraints and convergence is tracked while using an average Minkowski's distance [27] for each generation based on parallel coordinate plots of the 14 fitness functions.…”

“…The best solutions tend to be the ones that do not change over a wide range of preference weights. This is the Decision Making by Shopping (DMS) visualization [26]. Experience shows that DMS is reliable but also time consuming.…”

Software review: the GPTIPS platform

“…GPTIPS has been used widely in this field to model material and structural problems [4,5] as well as geotechnical and earthquake engineering problems [6,7]. Other examples of GPTIPS applications include solving multi-objective management problems [8], energy forecasting [9], and biotechnology and bioprocess optimization [10,11].…”