A Machine Learning Framework for the Classification of Natura 2000 Habitat Types at Large Spatial Scales Using MODIS Surface Reflectance Data
A Machine Learning Framework for the Classification of Natura 2000 Habitat Types at Large Spatial Scales Using MODIS Surface Reflectance Data
复制标题
使用 MODIS 表面反射率数据对大空间尺度的 Natura 2000 栖息地类型进行分类的机器学习框架
DOI：
10.3390/rs14040823
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Michael Vohland
中科院分区：
文献类型：
--
作者：
Fabian Sittaro;Christopher Hutengs;Sebastian Semella;Michael Vohland
人为气候和土地使用的变化正在导致生境的分布和构成发生迅速变化，对生态系统的生物多样性产生深远影响。生态系统的可持续管理需要能够在大的空间尺度上发现生境分布和构成的变化的监测方案。遥感观测促进了这类努力，因为它们能够采用具有成本效益的建模方法，利用公开的数据集，并能够评估长期的生境状况。在这项研究中，我们介绍了一个模型框架，在德国的栖息地监测使用现成的MODIS表面反射率数据。我们开发了监督分类模型，根据其与Natura 2000栖息地类型的相似性将（半）自然区域分配到18个类别中的一个。三个机器学习分类器，即，支持向量机（SVM），随机森林（RF），和C5.0，和集成的方法来预测栖息地类型使用光谱特征，从中分辨率成像光谱仪在可见光到近红外和短波红外。这些模型是在同质的特殊保护区进行训练的，这些保护区主要由单一栖息地类型覆盖，参考数据来自2013年，2014年和2016年，并根据2010年和2019年的地面实况数据进行测试，以进行独立的模型验证。单独地，SVM和RF方法实现了更好的整体分类精度（SVM：0.72- 0.93%，RF：0.72-0.94%）（0.66-0.93%），而由单个模型开发的集成分类器的性能最好，2010年和2012年的总体准确率分别为94.23%和80.34%，并且还允许对不可分类像素进行鲁棒检测。我们检测到强大的变异性，在覆盖的个人栖息地类型，这是减少汇总时，基于它们的相似性。我们的方法能够提供栖息地的空间分布的定量信息，区分干扰事件和生态系统组成的逐渐变化，并可以成功地分配自然区域的Natura 2000栖息地类型。
Anthropogenic climate and land use change is causing rapid shifts in the distribution and composition of habitats with profound impacts on ecosystem biodiversity. The sustainable management of ecosystems requires monitoring programmes capable of detecting shifts in habitat distribution and composition at large spatial scales. Remote sensing observations facilitate such efforts as they enable cost-efficient modelling approaches that utilize publicly available datasets and can assess the status of habitats over extended periods of time. In this study, we introduce a modelling framework for habitat monitoring in Germany using readily available MODIS surface reflectance data. We developed supervised classification models that allocate (semi-)natural areas to one of 18 classes based on their similarity to Natura 2000 habitat types. Three machine learning classifiers, i.e., Support Vector Machines (SVM), Random Forests (RF), and C5.0, and an ensemble approach were employed to predict habitat type using spectral signatures from MODIS in the visible-to-near-infrared and short-wave infrared. The models were trained on homogenous Special Areas of Conservation that are predominantly covered by a single habitat type with reference data from 2013, 2014, and 2016 and tested against ground truth data from 2010 and 2019 for independent model validation. Individually, the SVM and RF methods achieved better overall classification accuracies (SVM: 0.72–0.93%, RF: 0.72–0.94%) than the C5.0 algorithm (0.66–0.93%), while the ensemble classifier developed from the individual models gave the best performance with overall accuracies of 94.23% for 2010 and 80.34% for 2019 and also allowed a robust detection of non-classifiable pixels. We detected strong variability in the cover of individual habitat types, which were reduced when aggregated based on their similarity. Our methodology is capable to provide quantitative information on the spatial distribution of habitats, differentiate between disturbance events and gradual shifts in ecosystem composition, and could successfully allocate natural areas to Natura 2000 habitat types.
影响因子：
2.8
作者：
Bittner, Torsten;Jaeschke, Anja;Beierkuhnlein, Carl
通讯作者：
Beierkuhnlein, Carl
影响因子：
2.8
作者：
Feilhauer, Hannes;Dahlke, Carola;Stenzel, Stefanie
通讯作者：
Stenzel, Stefanie