From ecology to remote sensing: using animals to map land cover

Abstract

Land cover is a key variable in monitoring applications and new processing technologies made deriving this information easier. Yet, classification algorithms remain dependent on samples collected on the field and field campaigns are limited by financial, infrastructural and political boundaries. Here, animal tracking data could be an asset. Looking at the land cover dependencies of animal behaviour, we can obtain land cover samples over places that are difficult to access. Following this premise, we evaluated the potential of animal movement data to map land cover. Specifically, we used 13 White Storks (Cicona cicona) individuals of the same population to map agriculture within three test regions distributed along their migratory track. The White Stork has adapted to foraging over agricultural lands, making it an ideal source of samples to map this land use. We applied a presence–absence modelling approach over a Normalized Difference Vegetation Index (NDVI) time series and validated our classifications, with high‐resolution land cover information. Our results suggest White Stork movement is useful to map agriculture, however, we identified some limitations. We achieved high accuracies (F1‐scores > 0.8) for two test regions, but observed poor results over one region. This can be explained by differences in land management practices. The animals preferred agriculture in every test region, but our data showed a biased distribution of training samples between irrigated and non‐irrigated land. When both options occurred, the animals disregarded non‐irrigated land leading to its misclassification as non‐agriculture. Additionally, we found difference between the GPS observation dates and the harvest times for non‐irrigated crops. Given the White Stork takes advantage of managed land to search for prey, the inactivity of these fields was the likely culprit of their underrepresentation. Including more species attracted to agriculture – with other land‐use dependencies and observation times – can contribute to better results in similar applications.

Comparative Assessment of Machine Learning Methods for Urban Vegetation Mapping Using Multitemporal Sentinel-1 Imagery

“…Mapping of vegetation in built-up areas (i.e., forest, low vegetation) showed a better classification accuracy based on MT imagery (Table 3 and Figure 4). We used F1 and FoM accuracy metrics as macro-averaged measures that were suitable for evaluating the accuracy of various land-cover classes [69,75,94]. Table 3 shows an improvement in different classification scenarios for discriminating various land-cover classes, especially forest and low vegetation (i.e., grassland, shrubs).…”

Eco-Environmental Quality Monitoring in Beijing, China, Using an RSEI-Based Approach Combined With Random Forest Algorithms

“…For researchers who monitor ecological environment quality (EEQ), the information is a very useful data source. A previous study suggested that remote sensing technology plays an important role in monitoring atmospheric pollutants in natural or anthropogenic ecosystems [14]. In Sweden, remote sensing technology was also used to quantitatively evaluate urban growth impacts on the provisioning of urban ecosystem services [15].…”