Mapping Alkaline Fens, Transition Mires and Quaking Bogs Using Airborne Hyperspectral and Laser Scanning Data

Abstract

The aim of this study is to evaluate the effectiveness of the identification of Natura 2000 wetland habitats (Alkaline fens—code 7230, and Transition mires and quaking bogs—code 7140) depending on various remotely sensed (RS) data acquired from an airborne platform. Both remote sensing data and botanical reference data were gathered for mentioned habitats in the Lower (LB) and Upper Biebrza (UB) River Valley and the Janowskie Forest (JF) in different seasonal stages. Several different classification scenarios were tested, and the ones that gave the best results for analyzed habitats were indicated in each campaign. In the final stage, a recommended term of data acquisition, as well as a list of remote sensing products, which allowed us to achieve the highest accuracy mapping for these two types of wetland habitats, were presented. Designed classification scenarios integrated different hyperspectral products such as Minimum Noise Fraction (MNF) bands, spectral indices and products derived from Airborne Laser Scanning (ALS) data representing topography (developed in SAGA), or statistical products (developed in OPALS—Orientation and Processing of Airborne Laser Scanning). The image classifications were performed using a Random Forest (RF) algorithm and a multi-classification approach. As part of the research, the correlation analysis of the developed remote sensing products was carried out, and the Recursive Feature Elimination with Cross-Validation (RFE-CV) analysis was performed to select the most important RS sub-products and thus increase the efficiency and accuracy of developing the final habitat distribution maps. The classification results showed that alkaline fens are better identified in summer (mean F1-SCORE equals 0.950 in the UB area, and 0.935 in the LB area), transition mires and quaking bogs that evolved on/or in the vicinity of alkaline fens in summer and autumn (mean F1-SCORE equals 0.931 in summer, and 0.923 in autumn in the UB area), and transition mires and quaking bogs that evolved on dystrophic lakes in spring and summer (mean F1-SCORE equals 0.953 in spring, and 0.948 in summer in the JF area). The study also points out that the classification accuracy of both wetland habitats is highly improved when combining selected hyperspectral products (MNF bands, spectral indices) with ALS topographical and statistical products. This article demonstrates that information provided by the synergetic use of data from different sensors can be used in mapping and monitoring both Natura 2000 wetland habitats for its future functional assessment and/or protection activities planning with high accuracy.

The utility of airborne hyperspectral and satellite multispectral images in identifying Natura 2000 non-forest habitats for conservation purposes

“…For both sensors, similar types of data were compared. These datasets were chosen based on previous studies conducted on Natura 2000 habitats identification 15 , 19 and data dimensionality reduction for classification 36 , 37 .…”

“…The resampling was performed in ENVI 5.3 software using Resize Data tool, where the size of the output pixel was defined as 10 m. The images were calculated using nearest neighbour resampling. For the 10 m HS images, MNF transformation was performed and 30 first bands were chosen based on the eigenvalues, visual analysis, and previous studies 15 , 19 . Next, 65 indices (SI) were calculated in ENVI 5.3 using the Spectral Indices tool 39 .…”

“…The classifications performed in different studies resulted in very different accuracies, from F1 = 0 for habitat code 6230 21 to F1 = 0.95 for mires 7140 19 . It is worth mentioning that better results are obtained by using a multi-time image series compared to one date, so it can be stated that using multitemporal images improves the accuracy of classification 15 .…”

“…One of the key elements in classification, including Natura 2000 habitats mapping, is choosing the optimal dataset 18 , 19 . It was performed using data obtained from the satellite level 6 , 20 and aerial level 15 , 21 .…”

“…It is worth mentioning that better results are obtained by using a multi-time image series compared to one date, so it can be stated that using multitemporal images improves the accuracy of classification 15 . Among the classifiers, one of the most effective was the Random Forest (RF) machine learning algorithm 19 .…”