Search

This paper aims to find patterns in nest site selection by Little Terns Sterna albifrons, in the Nakdong estuary in South Korea. This estuary is important waterfowl stopover and breeding habitat, located in the middle of the East Asia-Australasian Flyway. The Little Tern is a common species easily observed near the seashore but their number is gradually declining around the world. We investigated their nests and eggs on a barrier islet in the Nakdong estuary during the breeding season (May to June, 2007), and a pattern for the nest site selection was identified using genetic programming (GP). The GP generated a predictive rule-set model for the number of Little Tern nests (training: R 2 =0.48 and test: 0.46). The physical features of average elevation, variation of elevation, plant coverage, and average plant height were estimated to determine the influence on nest numbers for Little Tern. A series of sensitivity analyses stressed that mean elevation and vegetation played an important role in nest distribution for Little Tern. The influence of these two variables could be maximized when elevation changed moderately within the sampled quadrats. The study results are regarded as a good example of applying GP to vertebrate distribution patterning and prediction with several important advantages compared to conventional modeling techniques, and can help establish a management or restoration strategy for the species. [Copyright &y& Elsevier]

• Machine learning (ML) was applied to model tree mortality and growth reduction. • Biogeochemical model produced ecophysiological variables for the ML modeling. • Random forest (RF) showed the best performance among the MLs. • Sugar and starch contents were identified as key parameters in the ML models. Massive tree diebacks and abnormal growth reduction have been more reported across continents, which calls an attention for methods that can assess the physiological stress of tree growth. This study aims to develop machine learning models (MLM) to explain tree mortality and growth reduction in terms of the key parameters of climate and tree ecophysiology in temperate forests of Korea. For this, we produced various ecophysiological parameters with a process-based vegetation model that was used as inputs to multiple machine learning algorithms and the conventional multiple linear regression (MLR). As a result, the MLMs outperformed the MLR. Among the MLMs, random forest (RF) showed the highest overall accuracy and AUC for both tree mortality (79% and 0.84±0.09, respectively) and growth reduction (61% and 0.63 ± 0.09). Winter temperature along with previous-year autumn soluble sugar content and precipitation were the most important in determining the tree mortality, while the growth reduction was largely regulated by current-year conditions such spring and autumn precipitation and summer starch content. Also, in the proportion of variance (communalities) of PCA, the precipitation and soluble sugar showed low values 0.15 and 0.29, respectively, which low communalities (<0.3) indicate that these variables have limited shared variance with other variables in the analysis. This study indicates the combined use of vegetation model and MLM can give reciprocal benefits to each other by providing ecophysiological parameters for MLM, otherwise hard to get, and coping with convoluted process of tree vitality undescribed yet in the vegetation model, respectively. [ABSTRACT FROM AUTHOR]