A labor-free index-guided semantic segmentation approach for urban vegetation mapping from high-resolution true color imagery

Accurate and timely information on urban vegetation(UV)can be used as an important indicator to estimate the health of cities.Due to the low cost of RGB cameras,true color imagery(TCI)has been widely used for high spatial resolution UV mapping.However,the current index-based and classifier-based UV mapping approaches face problems of the poor ability to accurately distinguish UV and the high reliance on massive annotated samples,respectively.To address this issue,an index-guided semantic segmentation(IGSS)framework is proposed in this paper.Firstly,a novel cross-scale vegetation index(CSVI)is calculated by the combination of TCI and Sentinel-2 images,and the index value can be used to provide an initial UV map.Secondly,reliable UV and non-UV samples are automatically generated for training the semantic segmentation model,and then the refined UV map can be produced.The experimental results show that the proposed CSVI outperformed the existingfive RGB vegetation indices in highlighting UV cover and suppressing complex backgrounds,and the proposed IGSS workflow achieved satisfactory results with an OA of 87.72%∼88.16%and an F1 score of 87.73%∼88.37%,which is comparable with the fully-supervised method.

Screening Tree Species for Carbon Storage Potential through Urban Tree Inventory in Planted Vegetation

Urban tree inventory is a great tool for gathering data that can be used by different end users. This study attempted to chart the species diversity in planted areas and measure their tree diameter at breast height to screen them for the carbon storage potential. A total of 2860 trees belonging to 36 species were recorded in the planted vegetation in parks and avenue plantation. The dominant species were Azadirachta indicia (25.5%), Conocarpus erectus (19.2%), Ficus spp. (15.5%), Tabebuia rosea (9.2%), Peitophorum pterocarpum (9.0%) and the remaining represents (21.6%) of the tree identified in this study. It was found that the highest contribution of carbon sequestration (CO2 equivalent) is dominated by the Ficus spp. (30.3%) with a total of 3399.3 tCO2eq, followed by Azadirachta indicia (25.4%) with a total of 2845.2 tCO2eq and Conocarpus erectus (20.4%) with a total of 2286 tCO2eq. The entire area has the capability to sequester around 11,213.3 tCO2eq and on average of 3.9 ± 0.1 tCO2eq. In accordance with the findings, it is imperative for the preservation of a sustainable environment to have vegetation that has the capacity to store carbon. The study suggests, there is potential to increase carbon sequestration in urban cities through plantation programs on existing and new land uses and along roads.

Variability of urban fractional vegetation cover and its driving factors in 328 cities in China

Urban green space promotes the health of urban residents,enhances urban ecosystem biodiversity,mitigates environmental pollution,and attenuates urban heat island effect.However,urban vegetation cover is highly heterogeneous and difficult to quantify.In this study,the variation of urban fractional vegetation cover(FVC)in 328 cities in China from 1990 to2022 was quantified based on Landsat satellite data at a 30-m resolution.It was found that from 1990 to 2005,due to increases in building density and impervious surfaces in cities,the national mean urban vegetation cover decreased from 0.38 to 0.35.After2005,urban vegetation cover began to reverse,reaching 0.45 in 2022.This increasing trend was most pronounced in newly built urban districts.The decrease in average urban vegetation cover before 2005 was mainly due to the expansion of low vegetation cover areas,while the increase in urban vegetation cover after 2005 manifested as the expansion of high vegetation cover areas.The reversal in the trend of urban vegetation cover change after 2004 is related to the gradual implementation of national policies requiring increased urban green space coverage.The urban gross domestic product(GDP)showed the highest correlation with changes in urban vegetation cover.For large and medium-sized cities,the top three factors influencing vegetation cover were GDP,urban population,and temperature.However,for cities in arid/semi-arid regions,changes in vegetation cover were more sensitive to climatic factors(such as precipitation).Although the urban vegetation cover in China has substantially increased in recent years,the urban green space in small-sized cities and in the old urban districts of large-sized cities still have room to improve.

i-Tree Eco Analysis of Landscape Vegetation on Remediated Areas of Oak Ridge National Laboratory

The Oak Ridge National Laboratory (ORNL) is the largest and most diverse energy, research, and development institution within the Department of Energy (DOE) system in the United States. As such, the site endures constant land development that creates rigorous growing conditions for urban vegetation. Natural resource managers at ORNL recognize that trees are an integral component of the landscape and are interested in characterizing the urban forest and their associated ecosystem services benefits. We evaluated the urban forest structure, quantified ecosystem services and benefits, and estimated economic value of resources using i-Tree Eco at ORNL. While this assessment captured over 1100 landscape trees, the ORNL Natural Resources Management for landscape vegetation can be expanded to include unmanaged landscapes, e.g. riparian areas, greenspace, and other vegetative attributes to increase ecosystem services benefits. Assigning a monetary value to urban forest benefits help to inform decisions about urban forest management, ideally on cost-benefit analysis.

Extracting subpixel vegetation NDVI time series for evaluating the mixed pixel effect on GPP estimation in urban areas

The normalized difference vegetation index(NDVI)is the most widely used vegetation index for monitoring vegetation vigor and cover.As NDVI time series are usually derived at coarse or medium spatial resolutions,pixel size often represents a mixture of vegetated and non-vegetated surfaces.In heterogeneous urban areas,mixed pixels impede the accurate estimation of gross primary productivity(GPP).To address the mixed pixel effect on'NDVI time series and GPP estimation,we proposed a framework to extract subpixel vegetation NDVI(NDVI_(vege))from Landsat OLI images in urban areas,using endmember fractions,mixed NDVI(NDVI_(mix)),and NDVI.of non-vegetation,endmembers.Results demonstrated that the NDVI_(vege) extracted by this framework agreed well with the true NDVI_(vege) cross seasons and vegetation fractions,with R^(2) ranging from 0.74 to 0.82 and RMSE ranging from 0.03 to 0.04.The NDVI_(vege) time series was applied to evaluate vegetation GP in Wuhan,China.The total annual GPp estimated with NDVI_(vege) was 28-35%higher than the total annual GPP estimated with NDVI_(mix) implying uncertainty in the GPP estimations caused by mixed pixels.This study showed the potential of the proposed framework to resolve NDVI_(vege) for characterizing vegetation dynamics in heterogeneous areas.

Does the ecological concept of disturbance have utility in urban social-ecological-technological systems?

The ecological concept of disturbance has scarcely been applied in urban systems except in the erroneous but commonplace assumption that urbanization itself is a disturbance and cities are therefore perennially disturbed systems.We evaluate the usefulness of the concept in urban ecology by exploring how a recent conceptual framework for disturbance(Peters et al.2011,Ecosphere,2,art 81)applies to these social-ecological-technological systems(SETS).Case studies,especially from the Long-Term Ecological Research sites of Baltimore and Phoenix,are presented to show the applicability of the framework for disturbances to different elements of these systems at different scales.We find that the framework is easily adapted to urban SETS and that incorporating social and technological drivers and responders can contribute additional insights to disturbance research beyond urban systems.

Assessment of terrace gardens as modifiers of building microclimate

Hard concrete roofs cause excessive heat gain impacting thermal comfort in buildings.Terrace gardens promoting greening at higher levels of built structures are seen as one of the key mitigating strategies for modifying building microclimate and improving urban health.We have undertaken a research project to quantitatively assess the value of a terrace garden in a residential scale.A garden patch of about 15 m 2 in area,a typical size available in most urban terraces is developed.Surface temperatures are measured over a period of 15 months between July 2018 to January 2020 using four thermocouple sensors,placed within and outside the garden bed,on and below the roof.We compare the thermal performance of the terrace garden across years,seasons,time of the day,presence or absence of garden bed and type and height of vegetation.The surface temperature data was found to correlate well with the ambient air temperature values.The results show that the terrace garden moderates and stabilises the ceiling temperatures and reduces it by about 2-3°C in winter months and 5-7°C in hot summers.The garden also provided nearly 400 g of fresh monthly vegetable harvest per m 2 of garden.Further,the cooling impact of the terrace garden with natural,tall,wild vegetation is higher as compared to planted vegetation.The study demonstrates a sustainable approach to terrace garden design at residential scale through quantified dual benefits of temperature control within buildings and urban farming.