ABSTRACT

Galaxiid post-larvae constitute five of the six species in New Zealand’s iconic whitebait fishery. Distinguishing the five species needs to occur at a younger age than is convenient for easy identification. Traditional identification uses subjective characteristics such as colouration of fresh specimens and fin position, but supervised classification methods could be more accurate and less labour-intensive. We compared the accuracy of six methods (multinomial logistic regression, linear discriminant analysis, quadratic discriminant analysis, naive Bayes, decision tree, and random forest) using total length, wet weight, body depth, and date, latitude and longitude of capture as predictive variables. Four of the galaxiid species were represented in 17,546 observations, but the other species was too rare to analyse. The best method, determined using 10-fold cross-validation classification accuracy (95.2% overall), was random forest across all species. The most difficult species to classify correctly (giant kōkopu) was the rarest species included in data with 66.1% accuracy at best. In addition to examining overall accuracy, we show how use of a cost function can improve classification performance with respect to rare species. This research could improve the efficiency of monitoring the composition of the whitebait fishery, and thus management of this occasionally overfished group of fish.

摘要

Galaxiid 后期幼体构成新西兰标志性银鱼渔业六种中的五种。区分这五种物种需要在更年轻的时候进行，而不是便于识别。传统的识别使用主观特征，例如新鲜标本的颜色和鳍的位置，但有监督的分类方法可能更准确，劳动强度更低。我们比较了六种方法（多项逻辑回归、线性判别分析、二次判别分析、朴素贝叶斯、决策树和随机森林）的准确性，使用总长度、湿重、身体深度和捕获日期、纬度和经度作为预测变量。在 17,546 次观测中代表了四种星系物种，但其他物种太稀有而无法分析。最好的方法，使用 10 倍交叉验证分类准确度（总体为 95.2%）确定，是所有物种的随机森林。最难正确分类的物种（巨型 kōkopu）是数据中包含的最稀有物种，准确率最高为 66.1%。除了检查整体准确性之外，我们还展示了使用成本函数如何提高稀有物种的分类性能。这项研究可以提高监测银鱼渔业组成的效率，从而提高对这种偶尔过度捕捞的鱼群的管理。我们展示了使用成本函数如何提高稀有物种的分类性能。这项研究可以提高监测银鱼渔业组成的效率，从而提高对这种偶尔过度捕捞的鱼群的管理。我们展示了使用成本函数如何提高稀有物种的分类性能。这项研究可以提高监测银鱼渔业组成的效率，从而提高对这种偶尔过度捕捞的鱼群的管理。