Quantification of carbon sequestration by urban forest using Landsat 8 OLI and machine learning algorithms in Jodhpur, India

Uniyal, Swati; Purohit, Saurabh; Chaurasia, Kuldeep; Rao, S. S.; Amminedu, E.

doi:10.1016/j.ufug.2021.127445

Cited by 22 publications

(6 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Biomass and carbon stocks are crucial quantitative aspects of forest ecology. The average aboveground biomass in this study was comparably higher than the other studies, For example, reported values are 9.58 ton/ha in Tripura University Campus, Northeast (Deb et al, 2016), 79.125 ton/ha in an urban forest, Jodhpur city, Rajsthan (Uniyal et al, 2022), 64.92 ton/ha in an soil organic carbon stock, in urban green site foothill was 50.82 ton/ha (Pradhan et al, 2022), in main land use of Allada plateau, Southern Benin, West Africa, it was 83 ton/ha (Houssoukpevi et al, 2022), and the value of soil organic carbon stock in an urban park under cold climate conditions, Finland was 104 ton/ha (Linden et al, 2020) (Table 7).…”

Section: Carbon Stocksupporting

confidence: 45%

Quantifying carbon Stock and tree species diversity of green infrastructure of Varanasi, India

Singh,

Singh

et al. 2023

IJPE

View full text Add to dashboard Cite

The world is undergoing rapid urbanization and experiencing its negative impacts, often due to the loss of urban green infrastructure. This study focuses on the green infrastructure of Varanasi city, India, and analyses current tree species diversity, and carbon storage in aboveground and belowground biomass and soil. The study calculated the biomass of urban green infrastructure because it serves as a carbon stock reservoir. As random sampling, data were collected from 24 sample plots across various urban green infrastructure sites via rigorous fieldwork. The biomass was then recorded using a non-destructive approach and a standard equation by King et al.2006. The diversity of tree species was recorded across urban green infrastructure sites, and was found to be higher in the BHU site, and lower in the MA site. The Pielou’s evenness index and Margellef’s richness index were found to be higher in the BHU site, while they were found to be lower in UPAC and MA sites, respectively. Aboveground biomass and total carbon stock were found to be high in the BLW site, with values of 1939.84 ton/ha and 7806 ton/ha, respectively, with trees having a larger girth circumference being the primary contributors. The findings of this study prove a better understanding of tree species diversity, biomass, and carbon stock of different green infrastructure sites of Varanasi city and generate evidence on how urban green space preservation and green infrastructure development may help to the countries' green economic transformation and sustainable, resilient, and low-carbon cities.

show abstract

Section: Carbon Stocksupporting

confidence: 45%

Quantifying carbon Stock and tree species diversity of green infrastructure of Varanasi, India

Singh,

Singh

et al. 2023

IJPE

View full text Add to dashboard Cite

show abstract

“…In three algorithms, the accuracy of ERT algorithm is significantly better than that of RF, indicating the importance of ERT in the estimation of surface parameters, especially the forest biomass. XGBoost is also showed excellent performance in the AGB model in other studies [24]. From the perspective of R² and RMSE, the best model of the XGBoost with all variables performed the best.…”

Section: Feature Importance In Agb Modelingmentioning

confidence: 54%

Comparing different methods for biomass modeling over tropical region based on Landsat data

2023

International Conference on Geographic Information and Remote Sensing Technology (GIRST 2022)

View full text Add to dashboard Cite

Forest biomass is an important ecological parameter for forest research, which is greatly important to the understanding and analysis of global carbon cycle. Landsat Time Series (LTS) data, as medium optical resolution data, have the merits of long time–span and appropriate spatial resolution. Forest biomass research based on this data can better guide human understanding of forest ecosystem. In this study, LTS data and sample biomass data were used to study the forest biomass modeling. This study explored the effects of forest biomass modeling based on features extracted from two LTS processing methods and three algorithms including random forest (RF), extremely randomized trees (ERT), and eXtreme Gradient Boosting (XGBoost). Among these models, the accuracy of the models based on the features extracted by Best Available Pixel (BAP) image composite and three algorithms is generally higher. Among the models constructed by combining feature groups extracted from BAP image composite and three algorithms, the models constructed by ERT were stable in most situations from the perspective of coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and bias. However, the XGBoost model that combines all variables performed best in perspective of R2 and RMSE, where R2 can reach 0.87, and the RMSE, MAE, and bias were 34.84 Mg/ha, 19.26 Mg/ha, and 2.29 Mg/ha, respectively. The textures and Tasseled Cap (TC) indices also show favorable performances in different models in the feature importance analysis.

show abstract

“…A UV apresentou forte dependência na profundidade de 20-40 cm, enquanto, a DS apresentou forte dependência na profundidade de 0-20cm e moderada dependência na profundidade de 20-40 cm. Araújo et al (2014) Tanto a área de Mata Nativa quanto a área de Pousio apresentaram valores baixos de RMSE e MAE, indicando melhor desempenho de estimativa do modelo de semivariograma escolhido (Uniyal, et al, 2021). Em relação ao índice de concordância de Willmott, foram observados altos valores tanto nos atributos estudados na área de Mata Nativa quanto na área de Pousio, indicando boa concordância dos valores obtidos (Santana, et al, 2015).…”

Section: Resultsunclassified

Relação entre a entomofauna edáfica e atributos físicos do solo através de análise multivariada e geoestatística

Santos

Sacramento

Pires

et al. 2022

RSD

View full text Add to dashboard Cite

Este estudo objetivou avaliar a influência que os atributos físicos do solo podem exercer sobre a entomofauna edáfica, considerando uma área de Pousio e outra de Mata Nativa, coletando-se amostras de solo nas profundidades 0 – 20 cm e 20 – 40 cm, totalizando 49 amostras por profundidade, totalizando 98 amostras por área, avaliando-se: densidade do solo (DS), macroporosidade (MAC), microporosidade (MIC), porosidade total (PT), umidade gravimétrica (UG) e volumétrica (UV) e resistência à penetração do solo (RPS), com coleta da entomofauna em cada ponto amostral. Coletou-se 3.098 insetos, apresentando maior número de indivíduos a família Formicidae e, maior número de famílias a ordem Coleóptera. Na Análise de Componentes Principais encontrou-se relação das famílias Staphylinidae, Cleridae, Scarabaeidae, Bostrichidae, Culicidae, Blattidae, Scolytidae e Termitidae à PT e UG na área de Mata Nativa. Na área de Pousio, Staphylinidae, Curculionidae, Tenebrionidae, Scarabaeidae e Blattidae apresentaram maior proximidade com UV, UG, MAC e PT. Na análise geoestatística os modelos de semivariogramas matern, esférico, gaussiano, exponencial e cúbico foram ajustados aos atributos de solo. Na fauna edáfica, ajustaram-se os modelos de covariogramas circular, exponencial, cúbico, esférico e gaussiano. Os resultados indicam a importância das características físicas do solo, que interferem no estabelecimento da entomofauna edáfica.

show abstract

Quantification of carbon sequestration by urban forest using Landsat 8 OLI and machine learning algorithms in Jodhpur, India

Cited by 22 publications

References 55 publications

Quantifying carbon Stock and tree species diversity of green infrastructure of Varanasi, India

Quantifying carbon Stock and tree species diversity of green infrastructure of Varanasi, India

Comparing different methods for biomass modeling over tropical region based on Landsat data

Relação entre a entomofauna edáfica e atributos físicos do solo através de análise multivariada e geoestatística

Contact Info

Product

Resources

About