Abstract

This study aims to predict channel unit types (CUT) by combining remotely sensed data with morphological variables using machine learning algorithms (Random Forest, Support Vector Machines, Multiple Adaptive Regression Splines, Extreme Gradient Boosting, and Adaptive Boosting) within the Upper Ogun River Basin, Southwestern Nigeria. In achieving the aim of this study, the study identified the most important variable(s) in CUT discrimination using the random forest – recursive feature elimination (RF-RFE). A total of 249 cross-sections across 83 reaches were sampled during the fieldwork. Landsat 8 and Sentinel-1 bands were retrieved for days the fieldwork was carried and mosaiced using the Google Earth Engine platform. The RF-RFE identified five top variables (accuracy: 0.79 ±0.14; Kappa: 0.39) discriminating the CUT as dimensionless stream power, slope, width, wetted perimeter and band 4. In essence, there is so much hope in the use of remote sensing in CUT mapping at the reach-scale.

摘要

本研究旨在通过在上奥贡河流域内使用机器学习算法（随机森林、支持向量机、多重自适应回归样条、极端梯度提升和自适应提升）将遥感数据与形态变量相结合来预测渠道单元类型 (CUT) ，尼日利亚西南部。为了实现本研究的目标，该研究使用随机森林确定了 CUT 判别中最重要的变量——递归特征消除 (RF-RFE)。在实地工作期间，共对 83 个河段的 249 个横截面进行了采样。Landsat 8 和 Sentinel-1 波段被检索了几天，使用 Google Earth Engine 平台进行实地工作并进行镶嵌。RF-RFE 确定了五个将 CUT 区分为无量纲流功率的顶级变量（准确度：0.79 ±0.14；Kappa：0.39），