The surface water table level is a crucial factor for the existence of wetland habitats, and valuable from the point of view of environmental protection. In particular, surface water table in a hydrological year play an important role, affecting the seasonal changes in conditions of the development of species inhabiting a given patch of vegetation. The occurrence of floods often determines the possibility of survival of a given plant community. Information on the seasonal variability of surface waters, and above all the range of seasonal floods, is very important from the point of view of planning protection activities in National Parks in order to preserve wetland habitats. Nowadays, remote sensing data is an important source of spatial information, particularly those characterized by low cost data acquisition and processing. One such source is imagery collected from satellites, along with products freely distributed by the European Space Agency. Satellites of the Sentinel constellation provide multi-spectral optical remote sensing images recorded at visible and infrared wavelengths. Due to the short satellite revisit time of the Sentinel, the images from this satellite constitute a potential source of information for the monitoring of moisture on wetlands with a high temporal resolution. In this study, the authors aim to demonstrate the possibilities associated with the use of satellite images to monitor the range of a free surface water table in the pilot area located within the basin of the Łasica Channel, located in the Kampinos National Park (Poland). The accuracy of the results of the remote sensing transformations will be assessed using high resolution RGB images obtained with the use of unmanned aerial vehicles (UAV) and control points measurements. The maps of free water table has been acquired as an result of ensemble regressors (Random Forest, Extra Trees, Bagging). Regressors has been learned and applied for two sessions. Promising results were obtained indicating the possibility of using the proposed method on a similar scale.
Brokvina A., Cienciala E., Surový P., Janata P., 2018, Unmanned aerial vehicles (UAV) for assessment of qualitative classification of Norway spruce in temperate forest stands, Geospatial Information Science, 21 (1), DOI: 10.1080/10095020.2017.1416994.
Candiago S., Remondido F., De Giglio M., Dubbini M., Gattelli M., 2015, Evaluating multispectral images and vegetation indices for precision farming applications from UAV images, Remote Sensing, 7 (4), 4026-4047, DOI: 10.3390/rs70404026.
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.