Comparison of Sentinel-2 and High-Resolution Imagery for Mapping Land Abandonment in Fragmented Areas

被引:33
|
作者
Morell-Monzo, Sergio [1 ]
Estornell, Javier [2 ]
Sebastia-Frasquet, Maria-Teresa [1 ]
机构
[1] Univ Politecn Valencia, Inst Invest Gest Integrada Zonas Costeras, C Paraninfo 1, Gandia 46730, Spain
[2] Univ Politecn Valencia, Geoenvironm Cartog & Remote Sensing Grp, Cami Vera S-N, Valencia 46022, Spain
关键词
citrus; land abandonment; high-resolution imagery; Sentinel-2; image classification; Random Forests algorithm; machine learning algorithms; USE CHANGE SCENARIOS; FARMLAND ABANDONMENT; CROPLAND ABANDONMENT; VEGETATION; CLASSIFICATION; RECULTIVATION; FORESTS; EUROPE; POLICY;
D O I
10.3390/rs12122062
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Agricultural land abandonment is an important environmental issue in Europe. The proper management of agricultural areas has important implications for ecosystem services (food production, biodiversity, climate regulation and the landscape). In the coming years, an increase of abandoned areas is expected due to socio-economic changes. The identification and quantification of abandoned agricultural plots is key for monitoring this process and for applying management measures. The Valencian Region (Spain) is an important fruit and vegetable producing area in Europe, and it has the most important citrus industry. However, this agricultural sector is highly threatened by diverse factors, which have accelerated land abandonment. Landsat and MODIS satellite images have been used to map land abandonment. However, these images do not give good results in areas with high spatial fragmentation and small-sized agricultural plots. Sentinel-2 and airborne imagery shows unexplored potential to overcome this thanks to higher spatial resolutions. In this work, three models were compared for mapping abandoned plots using Sentinel-2 with 10 m bands, Sentinel-2 with 10 m and 20 m bands, and airborne imagery with 1 m visible and near-infrared bands. A pixel-based classification approach was used, applying the Random Forests algorithm. The algorithm was trained with 144 plots and 100 decision trees. The results were validated using the hold-out method with 96 independent plots. The most accurate map was obtained using airborne images, the Enhanced Vegetation Index (EVI) and Thiam's Transformed Vegetation Index (TTVI), with an overall accuracy of 88.5%. The map generated from Sentinel-2 images (10 m bands and the EVI and TTVI spectral indices) had an overall accuracy of 77.1%. Adding 20 m Sentinel-2 bands and the Normalized Difference Moisture Index (NDMI) did not improve the classification accuracy. According to the most accurate map, 4310 abandoned plots were detected in our study area, representing 32.5% of its agricultural surface. The proposed methodology proved to be useful for mapping citrus in highly fragmented areas, and it can be adapted to other crops.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] A novel cotton mapping index combining Sentinel-1 SAR and Sentinel-2 multispectral imagery
    Xun, Lan
    Zhang, Jiahua
    Cao, Dan
    Yang, Shanshan
    Yao, Fengmei
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2021, 181 : 148 - 166
  • [22] Machine Learning and the End of Atmospheric Corrections: A Comparison between High-Resolution Sea Surface Salinity in Coastal Areas from Top and Bottom of Atmosphere Sentinel-2 Imagery
    Medina-Lopez, Encarni
    REMOTE SENSING, 2020, 12 (18)
  • [23] Combining Sentinel-1 and Sentinel-2 data for improved land use and land cover mapping of monsoon regions
    Steinhausen, Max J.
    Wagner, Paul D.
    Narasimhan, Balaji
    Waske, Bjoern
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2018, 73 : 595 - 604
  • [24] Comparison of Masking Algorithms for Sentinel-2 Imagery
    Zekoll, Viktoria
    Main-Knorn, Magdalena
    Louis, Jerome
    Frantz, David
    Richter, Rudolf
    Pflug, Bringfried
    REMOTE SENSING, 2021, 13 (01) : 1 - 21
  • [25] Monitoring Cropland Abandonment in Hilly Areas with Sentinel-1 and Sentinel-2 Timeseries
    He, Shan
    Shao, Huaiyong
    Xian, Wei
    Yin, Ziqiang
    You, Meng
    Zhong, Jialong
    Qi, Jiaguo
    REMOTE SENSING, 2022, 14 (15)
  • [26] A High-Resolution Global Map of Giant Kelp (Macrocystis pyrifera) Forests and Intertidal Green Algae (Ulvophyceae) with Sentinel-2 Imagery
    Mora-Soto, Alejandra
    Palacios, Mauricio
    Macaya, Erasmo C.
    Gomez, Ivan
    Huovinen, Pirjo
    Perez-Matus, Alejandro
    Young, Mary
    Golding, Neil
    Toro, Martin
    Yaqub, Mohammad
    Macias-Fauria, Marc
    REMOTE SENSING, 2020, 12 (04)
  • [27] Sentinel-2 Data for Land Cover/Use Mapping: A Review
    Phiri, Darius
    Simwanda, Matamyo
    Salekin, Serajis
    Nyirenda, Vincent R.
    Murayama, Yuji
    Ranagalage, Manjula
    REMOTE SENSING, 2020, 12 (14)
  • [28] The role of harmonized Landsat Sentinel-2 (HLS) products to reveal multiple trajectories and determinants of cropland abandonment in subtropical mountainous areas
    Hong, Changqiao
    V. Prishchepov, Alexander
    Jin, Xiaobin
    Han, Bo
    Lin, Jinhuang
    Liu, Jingping
    Ren, Jie
    Zhou, Yinkang
    JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2023, 336
  • [29] Evaluating the feasibility of using Sentinel-2 and Sentinel-3 satellites for high-resolution evapotranspiration estimations
    Guzinski, Radoslaw
    Nieto, Hector
    REMOTE SENSING OF ENVIRONMENT, 2019, 221 : 157 - 172
  • [30] Deep learning-based burned forest areas mapping via Sentinel-2 imagery: a comparative study
    Atasever, Umit Haluk
    Tercan, Emre
    ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2024, 31 (04) : 5304 - 5318