A nested drone-satellite approach to monitoring the ecological conditions of wetlands

Monitoring wetlands is necessary in order to understand and protect their ecohydrological balance. In Ireland, traditionally wetland-monitoring is carried out by manual field visits which can be very time-consuming. To automate the process, this study extends the ability of remote sensing-based monitoring of wetlands by combining RGB image processing, machine learning algorithms, and satellite data analysis to create seasonal maps of vegetation communities within the wetlands. The methodology matches multispectral and broad coverage of open-source Sentinel-2 (S2) imagery with the high spatial granularity of Unmanned Aerial Vehicles (UAV) or drone images. Single sensor drone imagery was captured, colour corrected and classified using random forest (RF) classifier for a subset of the wetland. The classified imagery was upsampled to satellite imagery scale to create training data for vegetation-segmentation in the entire wetland. The process was repeated for multiple seasons, and an annual map was created utilising the majority voting. The proposed framework has been evaluated on various wetlands across Ireland, with results presented herein for an ombrotrophic peatland complex, Clara Bog. The accuracy of the maps was checked utilising a set of area-based performance metric. The application of this method thereby reduces the number of field surveys typically required to assess the long-term ecological change of such wetland habitats. The performance of the proposed method demonstrates that the technique is a robust, quick, and cost-effective way to map wetland habitats seasonally and to explore their ecohydrological synergies.

Automated summary

This study automates the creation of seasonal wetland vegetation community maps by combining remote sensing, image processing, and machine learning techniques, reducing the time-consuming traditional manual field surveys in wetland monitoring.