Eduardo F. P. da Luz

Firefly optimization to determine the precipitation field on South America

A model simulation of an intense rainfall associated with a case of South Atlantic Convergence Zone that occurred during 21–24 February 2004 using the Brazilian developments on the Regional Atmospheric Modelling System was performed. The convective parameterization scheme of Grell and Dévényi was used to represent clouds of the sub-grid scale and their interaction with the large-scale environment. This method is a convective parameterization that can make use of a large variety of approaches previously introduced in earlier formulations, considering an ensemble of several hypotheses and closures. The rainfall was evaluated by six experiments, using different choices of rainfall parameterizations, providing six different simulated responses for the rainfall field. The sixth experiment ran with an average among five closures (ensemble mean). The purpose of this study was to generate a set of weights to compute a best combination of the ensemble members. This inverse problem of parameter estimation is solved as an optimization problem. The objective function was computed with the quadratic difference between five simulated precipitation fields and observation. The precipitation field estimated by the Tropical Rainfall Measuring Mission satellite was used as observed data. Weights were obtained using the firefly optimization algorithm and it was included in the cumulus parameterization code to simulate precipitation. The results indicated the better skill of the model with the new methodology compared with the old ensemble mean calculation.

Multiple Particle Collision Algorithm Applied to Radiative Transference and Pollutant Localization Inverse Problems

The Multiple Particle Collision Algorithm (MPCA) is a nature-inspired stochastic optimization method developed specially for high performance computational environments. Its advantages resides in the intense use of computational power provided by multiple processors in the task of search the solution space for a near optimum solution. This work presents the application of MPCA in solving two inverse problems written as optimization problems, its advantages and disadvantages are also described, so are the obtained results.

New learning strategy for supervised neural network: MPCA meta-heuristic approach

The problem of parameter optimization for a feedforward artificial neural network (ANN) to determined its best architecture is addressed. A new metaheuristic called Multiple Particle Collision Algorithm (MPCA), introduced by Luz et al. [12], was applied to design an optimum architecture for two models of supervised neural network: the Multilayer Perceptron (MLP), and recurrent Elman network. The NN obtained using this approach is said to be self-configurable. In addition, two strategies are employed for calculating the connection weights to the MLP and Elman networks: MPCA, and backpropagation algorithm. The resulting ANNs were applied to predict the monthly mesoscale climate for the precipitation field. The comparison is performed between the ANN configuration obtained by automatic process and another configuration proposed by a human specialist.

Evaluating Volunteers' Contributions in a Citizen Science Project

Today, with freely available data coming from different satellites and instruments, efficient algorithms for image classification, and increased connectivity and computing power, together with international policy initiatives, such as the United Nations Framework Convention of Climate Change Reducing Emissions from Deforestation and Forest Degradation (REDD) program, more and more countries are starting to invest in their own national forest monitoring schemes. Still, tropical forests remain under threat worldwide. Recently a citizen science project that enables citizens around the globe to be involved in forest monitoring tasks has been proposed. Called Forest Watchers (www.forestwatchers.net), its main goal is to allow volunteers (many of them with no scientific training) around the globe, with their own smartphones, tablets and notebooks, to review satellite images of forested regions, and confirm whether automatic assignments of forested and deforested regions are correct. Inspected images are then sent to a central database where results are integrated to generate up-to-date deforestation maps. This approach offers a low-cost way to both strengthen the scientific infrastructure and engage members of the public in science. Here we describe the procedures developed within the scope of the Forest Watchers project to assess the tasks performed by the volunteers. These procedures have been evaluated with data of one of the projects preliminary applications. Called BestTile, it asks volunteers to select among several images of the same area, which one has the least cloud cover. Results from more than 500 volunteers show that with simple statistical tests it is possible to attain a triple goal: to increase the overall efficiency of the data collecting tasks, by reducing the required number of volunteers per task, to identify malicious behavior and outliers, and to motivate volunteers, to continue their contributions.

A Multi-objective Version of the Multiple Particle Collision Algorithm

A multi-objective version of a meta-heuristic, loosely inspired on the behaviour of particles inside a nuclear reactor, is presented. The Multi-objective Multiple Particle Collision Algorithm (MMPCA) uses the Pareto based fitness assignment, which uses the concept of dominance, to generate new solutions and build the Pareto set. The original population is duplicated, with purpose of classification and for applying the crowding distance approach. The latter procedures are also used in the NSGA-II.

Multi-Particle Collision Algorithm with Reflected Points

New versions for the MPCA (Multi-Particle Collision Algorithm) meta-heuristic are presented. In order to provide more effective candidate solutions for an optimization problem, the concept of opposition and reflection is introduced to improve the capacity of search space for the MPCA. Four different strategies to compute the reflected and/or opposited points are implemented. The performance of all implementation are evaluated with four objective functions.

Multi-Particle Collision Algorithm for Solving an Inverse Radiative Problem

An inverse radiative transfer problem formulated as a finite dimensional optimization problem, using Multi-Particle Collision Algorithm with a pre-regularization strategy. The radiation propagation in a finite space domain, under isotropic-scattering, assuming plane-parallel geometry is considered. The optical properties, absorption and scattering coefficients, have space dependency. The problem is described by linear Boltzmann equation, considering polar angle discretization and azimuthal symmetry. The forward problem is solved using the discrete ordinates. The inverse problem, reconstruction of the albedo profile, is performed minimizing the square difference between measured radiance and the photon concentration computed from the mathematical forward model emerging from the body. A large number of particles is generated, and those smoother particles are selected. This scheme is called intrinsic regularization. Multi-Particle Collision Algorithm is a stochastic method for global optimization, also called meta-heuristic, and is used to solve the inverse problem. Noiseless and noisy data of the emergent radiation intensities were employed to compute the albedo profile. Good inverse solutions are obtained with the proposed approach.

Strategies for Estimation of Gas Mass Flux Rate Between Surface and the Atmosphere

A relevant issue nowadays is the monitoring and identification of the concentration and rate flux of the gases from the greenhouse effect. Most of these minority gases belong to important bio-geochemical cycles between the planet surface and the atmosphere. Therefore, there is an intense research agenda on this topic. Here, we are going to describe the effort for addressing this challenging. This identification problem can be formulated as an inverse problem. The problem for identifying the minority gas emission rate for the system ground-atmosphere is an important issue for the bio-geochemical cycle, and it has being intensively investigated. This inverse problem has been solved using regularized solutions (Kasibhatla, 2000), Bayes estimation (Enting, 2002; Gimson & Uliasz, 2003), and variational methods (Elbern et al., 2007) – the latter approach coming from the data assimilation studies.