Exploring the suitability of a genetic algorithm as tool for boosting efficiency in monte carlo estimation of leaf area of eelgrass

Abstract

Eelgrass is an important seagrass species that grants ecological services of valuable economic relevance for mankind. On spite of its significance, human activities have infringed a notorious threat to the permanence of this species. Transplanting plays a fundamental role in restoration strategies, and assessing the success of concomitant plots requires non-invasive techniques. The use of allometric scaling and leaf area estimations derived from digital images, have provided simplified and accurate proxies for both standing crop and productivity. For regularly shaped leaves which produce nearly rectangular images, one key approach for the estimation of the involved areas is the use of the Monte Carlo method. Nevertheless, irregularities in the contour of leaves could make the computational time required to achieve a certain accuracy threshold burdensome. In this paper we explored the potential of a genetic algorithm as an agent for boosting the efficiency of the aforementioned technique. Our results show that the addition of the proposed code was able to markedly increasing the accuracy of regular Monte Carlo estimations while simultaneously boosting the computational efficiency of these procedures in a significant way.