We present a comparative study between predictive monthly rainfall models for islands of complex orography using machine learning techniques. The models have been developed for the island of Tenerife (Canary Islands). Weather forecasting is influenced both by the local geographic characteristics as well as by the time horizon comprised. Accuracy of mid-term rainfall prediction on islands with complex orography is generally low when carried out with atmospheric models. Predictive models based on algorithms such as Random Forest or Extreme Gradient Boosting among others were analyzed. The predictors used in the models include weather predictors measured in two main meteorological stations, reanalysis predictors from the National Oceanic and Atmospheric Administration, and the global predictor North Atlantic Oscillation, all of them obtained over a period of time of more than four decades. When comparing the proposed models, we evaluated accuracy, kappa and interpretability of the model obtained, as well as the relevance of the predictors used. The results show that global predictors such as the North Atlantic Oscillation Index (NAO) have a very low influence, while the local Geopotential Height (GPH) predictor is relatively more important. Machine learning prediction models are a relevant proposition for predicting medium-term precipitation in similar geographical regions.
We present an optimization procedure based on a hybrid version of an evolutionary multiobjective decision-making algorithm for its application in urban freight transportation planning problems. This tool is intended to solve the planning problems of a merchandise distribution firm that dispatches small volume fractional loads of fresh foods on daily schedules. The firm owns a network of distribution centers supplying a large number of small businesses in Buenos Aires and its surroundings. The recombination operator of the evolutionary algorithm used here has been designed specifically for this problem. It is intended to embody a strategy that takes into account constraints like temporary closeness, closeness time window and connectivity in order to improve its performance in the clustering phase. The representation allows incorporating specific information about the actual instances of the problem and uses adaptive control of the parameters in the calibration stage. The performance of the proposed optimizer was tested against the results obtained by two evolutionary algorithms, NSGA II and SPEA 2, widely used in similar problems. We use hypervolume as a measure of convergence and dispersion of Pareto fronts. The statistical analysis of the results obtained with the three algorithms uses the Wilcoxon rank sum test, which yields evidence that our procedure provides good results.
A common technique used to solve multi-objective optimization problems consists of first generating the set of all Pareto-optimal solutions and then ranking and/or choosing the most interesting solution for a human decision maker (DM). Sometimes this technique is referred to as generate first–choose later. In this context, this paper proposes a two-stage methodology: a first stage using a multi-objective evolutionary algorithm (MOEA) to generate an approximate Pareto-optimal front of non-dominated solutions and a second stage, which uses the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) devoted to rank the potential solutions to be proposed to the DM. The novelty of this paper lies in the fact that it is not necessary to know the ideal and nadir solutions of the problem in the TOPSIS method in order to determine the ranking of solutions. To show the utility of the proposed methodology, several original experiments and comparisons between different recognized MOEAs were carried out on a welded beam engineering design benchmark problem. The problem was solved with two and three objectives and it is characterized by a lack of knowledge about ideal and nadir values.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.