High resolution remote sensing for reducing uncertainties in urban forest carbon offset life cycle assessments

Abstract

Background: Urban forests reduce greenhouse gas emissions by storing and sequestering considerable amounts of carbon. However, few studies have considered the local scale of urban forests to effectively evaluate their potential long-term carbon offset. The lack of precise, consistent and up-to-date forest details is challenging for long-term prognoses. Therefore, this review aims to identify uncertainties in urban forest carbon offset assessment and discuss the extent to which such uncertainties can be reduced by recent progress in high resolution remote sensing. We do this by performing an extensive literature review and a case study combining remote sensing and life cycle assessment of urban forest carbon offset in Berlin, Germany.

Main text: Recent progress in high resolution remote sensing and methods is adequate for delivering more precise details on the urban tree canopy, individual tree metrics, species, and age structures compared to conventional land use/cover class approaches. These area-wide consistent details can update life cycle inventories for more precise future prognoses. Additional improvements in classification accuracy can be achieved by a higher number of features derived from remote sensing data of increasing resolution, but first studies on this subject indicated that a smart selection of features already provides sufficient data that avoids redundancies and enables more efficient data processing. Our case study from Berlin could use remotely sensed individual tree species as consistent inventory of a life cycle assessment. However, a lack of growth, mortality and planting data forced us to make assumptions, therefore creating uncertainty in the long-term prognoses. Regarding temporal changes and reliable long-term estimates, more attention is required to detect changes of gradual growth, pruning and abrupt changes in tree planting and mortality. As such, precise long-term urban ecological monitoring using high resolution remote sensing should be intensified, especially due to increasing climate change effects. This is important for calibrating and validating recent prognoses of urban forest carbon offset, which have so far scarcely addressed longer timeframes. Additionally, higher resolution remote sensing of urban forest carbon estimates can improve upscaling approaches, which should be extended to reach a more precise global estimate for the first time.

Conclusions: Urban forest carbon offset can be made more relevant by making more standardized assessments available for science and professional practitioners, and the increasing availability of high resolution remote sensing data and the progress in data processing allows for precisely that.

Keywords: Carbon offset; Change detection; Climate change mitigation; High resolution; Individual tree detection; Life cycle assessment; Tree species; Uncertainty; Urban forests; Urban remote sensing.

Fig. 1

LCA inventory of remotely sensed trees in Berlin, Germany. Spatial distribution of a dominant tree species and b tree density per unit of land cover [15]. Class “mix” refers to difficult-to-classify tree species in the tree canopy. Approximately 1.4 million trees were classified with a mean tree height of 15 m and a mean DBH of 36 cm. No data was available for the outer black areas, which are mostly covered by forests

Fig. 2

LCA of 60 years on urban forest carbon offset in Berlin. The carbon weight for alive and accumulated dead biomass is presented in kilotons (ktC) for our land use classes (streets, mixed, parks). The absolute tree population, the assumed mortality rate of each land use class and its average age is indicated for the LCA start in 2008. A red border marks a tree population of an unlikely very high average age (> 80 years)

Fig. 3

Potential tree planting initiative of 100,000 trees. Calculations of alive biomass were based on a mixture of dominant tree species in Berlin (Class mix, Table 1) with a 70-year growth period. The carbon weight is presented in kilotons (ktC). Tree population half-life is shown for high, moderate and low annual mortality. High uncertainty (red border) is generally assumed due to lack of knowledge concerning factors such as young tree mortality and other natural and anthropogenic disturbances