Appalachian Laboratory, University of Maryland Center for Environmental Science, Frostburg, MD 21532, USA.
College of Engineering, University of Georgia, Athens, GA 30602, USA.
Sensors (Basel). 2021 Jun 27;21(13):4408. doi: 10.3390/s21134408.
Remotely sensed data from both in situ and satellite platforms in visible, near-infrared, and shortwave infrared (VNIR-SWIR, 400-2500 nm) regions have been widely used to characterize and model soil properties in a direct, cost-effective, and rapid manner at different scales. In this study, we assess the performance of machine-learning algorithms including random forest (RF), extreme gradient boosting machines (XGBoost), and support vector machines (SVM) to model salt marsh soil bulk density using multispectral remote-sensing data from the Landsat-7 Enhanced Thematic Mapper Plus (ETM+) platform. To our knowledge, use of remote-sensing data for estimating salt marsh soil bulk density at the vegetation rooting zone has not been investigated before. Our study reveals that blue (band 1; 450-520 nm) and NIR (band 4; 770-900 nm) bands of Landsat-7 ETM+ ranked as the most important spectral features for bulk density prediction by XGBoost and RF, respectively. According to XGBoost, band 1 and band 4 had relative importance of around 41% and 39%, respectively. We tested two soil bulk density classes in order to differentiate salt marshes in terms of their capability to support vegetation that grows in either low (0.032 to 0.752 g/cm) or high (0.752 g/cm to 1.893 g/cm) bulk density areas. XGBoost produced a higher classification accuracy (88%) compared to RF (87%) and SVM (86%), although discrepancies in accuracy between these models were small (<2%). XGBoost correctly classified 178 out of 186 soil samples labeled as low bulk density and 37 out of 62 soil samples labeled as high bulk density. We conclude that remote-sensing-based machine-learning models can be a valuable tool for ecologists and engineers to map the soil bulk density in wetlands to select suitable sites for effective restoration and successful re-establishment practices.
从原位和卫星平台获取的可见、近红外和短波红外（VNIR-SWIR，400-2500nm）区域的遥感数据，已被广泛用于在不同尺度上直接、经济高效和快速地描述和模拟土壤特性。在本研究中，我们评估了机器学习算法（包括随机森林（RF）、极端梯度提升机（XGBoost）和支持向量机（SVM））的性能，以使用 Landsat-7 增强型专题制图仪加（ETM+）平台的多光谱遥感数据来模拟盐沼土壤容重。据我们所知，以前尚未使用遥感数据来估算植被根系区的盐沼土壤容重。我们的研究表明，Landsat-7 ETM+的蓝色（波段 1；450-520nm）和近红外（波段 4；770-900nm）波段是 XGBoost 和 RF 分别预测容重的最重要光谱特征。根据 XGBoost，波段 1 和波段 4的相对重要性分别约为 41%和 39%。我们测试了两个土壤容重类别，以便根据支持生长在低容重（0.032 至 0.752g/cm）或高容重（0.752g/cm 至 1.893g/cm）区域的植被的能力来区分盐沼。与 RF（87%）和 SVM（86%）相比，XGBoost 产生了更高的分类精度（88%），尽管这些模型之间的精度差异较小（<2%）。XGBoost 正确分类了 186 个低容重土壤样本中的 178 个，以及 62 个高容重土壤样本中的 37 个。我们得出结论，基于遥感的机器学习模型可以成为生态学家和工程师的有价值工具，用于绘制湿地土壤容重图，以选择合适的地点进行有效恢复和成功重建实践。
