{"title":"Fusion of multi-temporal PlanetScope data and very high-resolution aerial imagery for urban tree species mapping","authors":"","doi":"10.1016/j.ufug.2024.128410","DOIUrl":null,"url":null,"abstract":"<div><p>Detailed assessment of the ecosystem services provided by urban green spaces requires data on urban tree species. While many approaches for mapping of urban trees from remotely sensed data have been proposed, the fusion of multi-temporal satellite imagery with very high resolution orthophotos remains relatively underexplored. In this research, we assess the potential of a multimodal deep learning approach with intermediate data fusion for classifying common tree species found in the Brussels Capital Region. Our method combines two image sources: (a) multi-temporal PlanetScope data and (b) high-resolution aerial imagery. To evaluate the contribution of each image source, we separately train and assess each branch of the network. Both image sources demonstrate the ability to predict prevalent tree species with high accuracy. However, the fusion of the two image sources yields the best results, achieving an overall accuracy of 0.88 for the five most common tree species in the region. Our approach is compared to two conventional machine learning methods: a random forest (RF) and a support vector machine classifier (SVM) and outperforms both with a 11 percentage point increase in overall accuracy over RF and a 10 percentage point increase over SVM. Increasing the number of species from five to thirteen, including all species with more than 500 tree samples, results in a marginal decrease in accuracy (from 0.88 to 0.84). Overall, our deep learning approach demonstrates its efficacy in classifying common tree species in urban settings and provides a foundation for a comprehensive quantification of ecosystem services offered by urban trees through remote sensing data.</p></div>","PeriodicalId":49394,"journal":{"name":"Urban Forestry & Urban Greening","volume":null,"pages":null},"PeriodicalIF":6.0000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1618866724002085/pdfft?md5=fd1aa96c17b5b5802abaa7d620c85af0&pid=1-s2.0-S1618866724002085-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Urban Forestry & Urban Greening","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1618866724002085","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}
引用次数: 0
Abstract
Detailed assessment of the ecosystem services provided by urban green spaces requires data on urban tree species. While many approaches for mapping of urban trees from remotely sensed data have been proposed, the fusion of multi-temporal satellite imagery with very high resolution orthophotos remains relatively underexplored. In this research, we assess the potential of a multimodal deep learning approach with intermediate data fusion for classifying common tree species found in the Brussels Capital Region. Our method combines two image sources: (a) multi-temporal PlanetScope data and (b) high-resolution aerial imagery. To evaluate the contribution of each image source, we separately train and assess each branch of the network. Both image sources demonstrate the ability to predict prevalent tree species with high accuracy. However, the fusion of the two image sources yields the best results, achieving an overall accuracy of 0.88 for the five most common tree species in the region. Our approach is compared to two conventional machine learning methods: a random forest (RF) and a support vector machine classifier (SVM) and outperforms both with a 11 percentage point increase in overall accuracy over RF and a 10 percentage point increase over SVM. Increasing the number of species from five to thirteen, including all species with more than 500 tree samples, results in a marginal decrease in accuracy (from 0.88 to 0.84). Overall, our deep learning approach demonstrates its efficacy in classifying common tree species in urban settings and provides a foundation for a comprehensive quantification of ecosystem services offered by urban trees through remote sensing data.
期刊介绍:
Urban Forestry and Urban Greening is a refereed, international journal aimed at presenting high-quality research with urban and peri-urban woody and non-woody vegetation and its use, planning, design, establishment and management as its main topics. Urban Forestry and Urban Greening concentrates on all tree-dominated (as joint together in the urban forest) as well as other green resources in and around urban areas, such as woodlands, public and private urban parks and gardens, urban nature areas, street tree and square plantations, botanical gardens and cemeteries.
The journal welcomes basic and applied research papers, as well as review papers and short communications. Contributions should focus on one or more of the following aspects:
-Form and functions of urban forests and other vegetation, including aspects of urban ecology.
-Policy-making, planning and design related to urban forests and other vegetation.
-Selection and establishment of tree resources and other vegetation for urban environments.
-Management of urban forests and other vegetation.
Original contributions of a high academic standard are invited from a wide range of disciplines and fields, including forestry, biology, horticulture, arboriculture, landscape ecology, pathology, soil science, hydrology, landscape architecture, landscape planning, urban planning and design, economics, sociology, environmental psychology, public health, and education.