Analysis of UAV-Acquired Wetland Orthomosaics Using GIS, Computer Vision, Computational Topology and Deep Learning.

Invasive blueberry species endanger the sensitive environment of wetlands and protection laws call for management measures. Therefore, methods are needed to identify blueberry bushes, locate them, and characterise their distribution and properties with a minimum of disturbance. UAVs (Unmanned Aerial Vehicles) and image analysis have become important tools for classification and detection approaches. In this study, techniques, such as GIS (Geographical Information Systems) and deep learning, were combined in order to detect invasive blueberry species in wetland environments. Images that were collected by UAV were used to produce orthomosaics, which were analysed to produce maps of blueberry location, distribution, and spread in each study site, as well as bush height and area information. Deep learning networks were used with transfer learning and unfrozen weights in order to automatically detect blueberry bushes reaching True Positive Values (TPV) of 93.83% and an Overall Accuracy (OA) of 98.83%. A refinement of the result masks reached a Dice of 0.624. This study provides an efficient and effective methodology to study wetlands while using different techniques.

Nitrogen isotope pattern in Mongolian larch stands at the southern Eurasian boreal forest boundary.

In the last decades a drastic increase in air temperature but a stable precipitation regime in Mongolia has led to gradual drying conditions. Thus, we evaluated the effect of spatial and climatic characteristics on the soil-plant nitrogen dynamics in three representative larch stands (Larix sibirica) with different geographical and climatic conditions using stable nitrogen isotopes. The results showed significant differences in the soil inorganic N content among sites and consequently a different isotopic composition in the plant-soil system. Litter, bark and wood had the lowest δ15N values for all sites, slightly higher δ15N values for needles, while the highest δ15N values were observed for roots and soil. These differences could be the result of the larch stands age themselves, but were in agreement with the spatial and climatic characteristics of the sites. Based on the δ15N value a higher reliance on ectomycorrhizal fungi (ECMF) was observed in the warmest and driest site, while lower dependency was shown in the cooler northern site with higher soil inorganic N content. In both sites, the rate of air temperature increase has been similar in the last decades; however, their soil-plant N dynamics showed different characteristics.

Evaluation of the effect of the 2011 Tsunami on coastal forests by means of multiple isotopic analyses of tree-rings.

The March 2011 Mega-Tsunami in eastern Japan damaged at different degrees the black pine (Pinus thunbergii) forests along the coast. In order to evaluate the recovery of black pine four years later, tree-ring samples from 9 trees for the period 2002-2014 were analyzed for ring growth and stable isotopes (δ13C, δ15N and δ18O). The results showed that annual tree-ring width decreased approximately 70 % from the year 2011 to 2014 compared to the period previous to the tsunami (2002-2010). The multiple isotopic analyses showed that the reduction in growth was caused by soil salinity that prompted stomatal closure and an abrupt increase of tree-ring δ13C. Sea water deposition in the soil did not affect tree-ring δ18O values. Two years after the tsunami, decreasing tree-ring δ13C values caused by apparently photosynthetic recovery did not translate into radial tree-growth, indicating a possible shift in carbon allocation to foliage and mainly roots as a defense mechanism to sodium toxicity. The dual δ13C-δ18O model explains neither the limited growth nor the subsequent recovery in δ13C. Similarly tree-ring δ15N indicated that there was no difference in nitrogen availability before and after the tsunami, suggesting that nutrients were not a limitation but rather soil salinity.

Differential response of two Pinus spp. to avian nitrogen input as revealed by nitrogen isotope analysis for tree rings.

Temporal variations in N concentration and δ(15)N value of annual tree rings (1 year of time resolution) of two Japanese Black Pine (Pinus thunbergii) and three Japanese Red Pine (Pinus densiflora) trees under current breeding activity of the Great Cormorant (Pharacrocorax carbo) and the Black-tailed Gull (Larus crassirostris), respectively, in central and northeastern Japan were studied. Both species from control sites where no avian input occurs show negative values (δ(15)N = around -4 ‰ to -2 ‰) which are common among higher plants growing under high rainfall regimes. The δ(15)N values of P. densiflora show uniformly positive values several years before and after the breeding event, indicating N translocation that moved the absorbed N of a given growth year to tree rings of the previous year while a clear historical value of soil N dynamics was kept intact in the annual rings of P. thunbergii. Long-term N trends inferred from tree rings must take into account tree species with limited translocation rates that can retain actual N annual acquisition.