Abstract

Vernal pools are small, temporary, forested wetlands of ecological importance with a high sensitivity to changing climate and land-use patterns. These ecosystems are under considerable development pressure in southeastern Georgian Bay, where mapping techniques are required to inform wise land-use decisions. Our mapping approach combines common machine learning techniques [random forest, support vector machines (SVMs)] with object-based image analysis. Using multispectral image segmentation on high-resolution orthoimagery, we first created objects and assigned classes based on field collected data. We then supplied machine learning algorithms with data from freely available sources (Ontario orthoimagery and Sentinel 2) and tested accuracy on a reserved dataset. We achieved producer’s accuracies of 85 and 79% and user’s accuracies of 78 and 84% for random forest and SVMs models, respectively. Difficulty differentiating between small, dark shadows and small, obscured pools accounted for many of the omission and commission errors. Our automated approach of vernal pool classification provides a relatively accurate, consistent, and fast mapping strategy compared to manual photointerpretation. Our models can be applied on a regional basis to help verify the locations of pools in an area of Ontario that is in critical need of more detailed ecological information.

摘要

春季水池是具有生态重要性的小型临时森林湿地，对气候和土地利用模式的变化高度敏感。这些生态系统在乔治亚湾东南部面临着相当大的发展压力，需要绘制地图技术来为明智的土地利用决策提供信息。我们的映射方法将常见的机器学习技术 [随机森林、支持向量机 (SVM)] 与基于对象的图像分析相结合。在高分辨率正射影像上使用多光谱图像分割，我们首先根据现场收集的数据创建对象并分配类。然后，我们为机器学习算法提供了来自免费来源（安大略正射影像和哨兵 2）的数据，并在保留的数据集上测试了准确性。对于随机森林和 SVM 模型，我们分别实现了 85% 和 79% 的生产者准确率以及 78% 和 84% 的用户准确率。难以区分小的、暗的阴影和小的、模糊的水池导致了许多遗漏和错误。与手动照片解释相比，我们的春池分类自动化方法提供了相对准确、一致和快速的映射策略。我们的模型可以在区域基础上应用，以帮助验证安大略地区急需更详细生态信息的地区的水池位置。与手动照片解释相比，我们的春池分类自动化方法提供了相对准确、一致和快速的映射策略。我们的模型可以在区域基础上应用，以帮助验证安大略地区急需更详细生态信息的水池位置。与手动照片解释相比，我们的春池分类自动化方法提供了相对准确、一致和快速的映射策略。我们的模型可以在区域基础上应用，以帮助验证安大略地区急需更详细生态信息的地区的水池位置。