National-Scale Detection of New Forest Roads in Sentinel-2 Time Series

被引:0
|
作者
Trier, Oivind Due [1 ]
Salberg, Arnt-Borre [1 ]
机构
[1] Norwegian Comp Ctr, Postboks 114 Blindern, NO-0314 Oslo, Norway
关键词
deep learning; deep neural network; semi-automatic; road detection; satellite images; remote sensing;
D O I
10.3390/rs16213972
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The Norwegian Environment Agency is responsible for updating a map of undisturbed nature, which is performed every five years based on aerial photos. Some of the aerial photos are already up to five years old when a new version of the map of undisturbed nature is published. Thus, several new nature interventions may have been missed. To address this issue, the timeliness and mapping accuracy were improved by integrating Sentinel-2 satellite imagery for the detection of new roads across Norway. The focus on new roads was due to the fact that most new nature interventions include the construction of new roads. The proposed methodology is based on applying U-Net on all the available summer images with less than 10% cloud cover over a five-year period, with an aggregation step to summarize the predictions. The observed detection rate was 98%. Post-processing steps reduced the false positive rate to 46%. However, as the false positive rate was still substantial, the manual verification of the predicted new roads was needed. The false negative rate was low, except in areas without vegetation.
引用
收藏
页数:24
相关论文
共 50 条
  • [21] Forest fire area detection using Sentinel-2 data: Case of the Beni Salah national forest - Algeria
    Zennir, Rabah
    Khallef, Boubaker
    JOURNAL OF FOREST SCIENCE, 2023, 69 (01) : 33 - 40
  • [22] A Method of Chestnut Forest Identification Based on Time Series and Key Phenology from Sentinel-2
    Xiong, Nina
    Chen, Hailong
    Li, Ruiping
    Su, Huimin
    Dai, Shouzheng
    Wang, Jia
    REMOTE SENSING, 2023, 15 (22)
  • [23] Leveraging Sentinel-2 time series for bark beetle-induced forest dieback inventory
    Andresini, Giuseppina
    Appice, Annalisa
    Malerba, Donato
    39TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2024, 2024, : 875 - 882
  • [24] GARLIC MAPPING FOR SENTINEL-2 TIME-SERIES DATA USING A RANDOM FOREST CLASSIFIER
    Chai, Zhaoyang
    Zhang, Hongyan
    Xu, Xiong
    Zhang, Liangpei
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 7224 - 7227
  • [25] Burned area detection and mapping using time series Sentinel-2 multispectral images
    Liu, Peng
    Liu, Yongxue
    Guo, Xiaoxiao
    Zhao, Wanjing
    Wu, Huansha
    Xu, Wenxuan
    REMOTE SENSING OF ENVIRONMENT, 2023, 296
  • [26] Kernel-Based Early Detection of Forest Bark Beetle Attack Using Vegetation Indices Time Series of Sentinel-2
    Jamali, Sadegh
    Olsson, Per-Ola
    Mueller, Mitro
    Ghorbanian, Arsalan
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 12868 - 12877
  • [27] A MULTIVARIATE CHANGE VECTOR ANALYSIS SYSTEM FOR UNSUPERVISED DETECTION OF CLEAR-CUTS IN SENTINEL-2 TIME SERIES OF THE INDONESIAN FOREST
    Zanetti, Massimo
    Bruzzone, Lorenzo
    Fernandez-Prieto, Diego
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 1942 - 1945
  • [28] Using of Sentinel-2 images for automation of the forest succession detection
    Szostak, Marta
    Hawrylo, Pawel
    Piela, Obroslawa
    EUROPEAN JOURNAL OF REMOTE SENSING, 2018, 51 (01): : 142 - 149
  • [29] Detection of Irrigated and Rainfed Crops in Temperate Areas Using Sentinel-1 and Sentinel-2 Time Series
    Pageot, Yann
    Baup, Frederic
    Inglada, Jordi
    Baghdadi, Nicolas
    Demarez, Valerie
    REMOTE SENSING, 2020, 12 (18)
  • [30] Forest fire area detection using Sentinel-2 data: Case of the Beni Salah national forest-Algeria
    Zennir, Rabah
    Khallef, Boubaker
    JOURNAL OF FOREST SCIENCE, 2023,