SciTech Environmental Consulting, Vancouver, British Columbia, Canada.
Institute for Resources, Environment, and Sustainability, University of British Columbia, Vancouver, British Columbia, Canada.
PLoS One. 2021 Oct 29;16(10):e0259156. doi: 10.1371/journal.pone.0259156. eCollection 2021.
Maps of bottom type are essential to the management of marine resources and biodiversity because of their foundational role in characterizing species' habitats. They are also urgently needed as countries work to define marine protected areas. Current approaches are time consuming, focus largely on grain size, and tend to overlook shallow waters. Our random forest classification of almost 200,000 observations of bottom type is a timely alternative, providing maps of coastal substrate at a combination of resolution and extents not previously achieved. We correlated the observations with depth, depth-derivatives, and estimates of energy to predict marine substrate at 100 m resolution for Canada's Pacific shelf, a study area of over 135,000 km2. We built five regional models with the same data at 20 m resolution. In addition to standard tests of model fit, we used three independent data sets to test model predictions. We also tested for regional, depth, and resolution effects. We guided our analysis by asking: 1) does weighting for prevalence improve model predictions? 2) does model resolution influence model performance? And 3) is model performance influenced by depth? All our models fit the build data well with true skill statistic (TSS) scores ranging from 0.56 to 0.64. Weighting models with class prevalence improved fit and the correspondence with known spatial features. Class-based metrics showed differences across both resolutions and spatial regions, indicating non-stationarity across these spatial categories. Predictive power was lower (TSS from 0.10 to 0.36) based on independent data evaluation. Model performance was also a function of depth and resolution, illustrating the challenge of accurately representing heterogeneity. Our work shows the value of regional analyses to assessing model stationarity and how independent data evaluation and the use of error metrics can improve understanding of model performance and sampling bias.
底质图对于海洋资源和生物多样性的管理至关重要，因为它们是描述物种栖息地的基础。随着各国努力划定海洋保护区，这些地图也急需绘制。目前的方法耗时耗力，主要集中在粒度上，往往忽略了浅水区。我们使用随机森林对近 20 万条底质类型观测数据进行分类，这是一种及时的替代方法，可以提供以前无法达到的分辨率和范围的沿海底质图。我们将这些观测结果与深度、深度导数和能量估计相关联，以预测加拿大太平洋大陆架的海洋底质，该研究区域超过 135000 平方公里，分辨率为 100 米。我们使用相同的数据在 20 米的分辨率下构建了五个区域模型。除了对模型拟合进行标准测试外，我们还使用了三个独立的数据集来测试模型预测。我们还测试了区域、深度和分辨率的影响。我们通过以下问题指导我们的分析：1）是否通过流行度加权提高模型预测？2）模型分辨率是否影响模型性能？3）模型性能是否受深度影响？我们所有的模型都很好地拟合了构建数据，真实技能统计量（TSS）得分在 0.56 到 0.64 之间。通过对类流行度进行加权，模型拟合度和与已知空间特征的对应关系都得到了提高。基于分辨率和空间区域的分类指标显示出差异，表明这些空间类别存在非平稳性。基于独立数据评估，预测能力较低（TSS 从 0.10 到 0.36）。模型性能也是深度和分辨率的函数，这表明准确表示异质性具有挑战性。我们的工作表明，区域分析对于评估模型稳定性具有重要意义，并且独立的数据评估和使用误差指标可以提高对模型性能和采样偏差的理解。
