Identifying Leaf Phenology of Deciduous Broadleaf Forests from PhenoCam Images Using a Convolutional Neural Network Regression Method

被引:15
|
作者
Cao, Mengying [1 ]
Sun, Ying [1 ]
Jiang, Xin [2 ]
Li, Ziming [1 ]
Xin, Qinchuan [1 ]
机构
[1] Sun Yat Sen Univ, Sch Geog & Planning, Guangdong Key Lab Urbanizat & Geosimulat, Guangzhou 510275, Peoples R China
[2] Southern Univ Sci & Technol, Sch Environm Sci & Engn, Shenzhen 518055, Peoples R China
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
leaf phenology; convolutional neural network regression; PhenoCam; image segmentation; green chromatic coordinate; DIGITAL REPEAT PHOTOGRAPHY; VEGETATION PHENOLOGY; RESPONSES; TIME;
D O I
10.3390/rs13122331
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Vegetation phenology plays a key role in influencing ecosystem processes and biosphere-atmosphere feedbacks. Digital cameras such as PhenoCam that monitor vegetation canopies in near real-time provide continuous images that record phenological and environmental changes. There is a need to develop methods for automated and effective detection of vegetation dynamics from PhenoCam images. Here we developed a method to predict leaf phenology of deciduous broadleaf forests from individual PhenoCam images using deep learning approaches. We tested four convolutional neural network regression (CNNR) networks on their ability to predict vegetation growing dates based on PhenoCam images at 56 sites in North America. In the one-site experiment, the predicted phenology dated to after the leaf-out events agree well with the observed data, with a coefficient of determination (R2) of nearly 0.999, a root mean square error (RMSE) of up to 3.7 days, and a mean absolute error (MAE) of up to 2.1 days. The method developed achieved lower accuracies in the all-site experiment than in the one-site experiment, and the achieved R2 was 0.843, RMSE was 25.2 days, and MAE was 9.3 days in the all-site experiment. The model accuracy increased when the deep networks used the region of interest images rather than the entire images as inputs. Compared to the existing methods that rely on time series of PhenoCam images for studying leaf phenology, we found that the deep learning method is a feasible solution to identify leaf phenology of deciduous broadleaf forests from individual PhenoCam images.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] A Method for Identifying Origin of Digital Images Using a Convolutional Neural Network
    Huang, Rong
    Fang, Fuming
    Nguyen, Huy H.
    Yamagishi, Junichi
    Echizen, Isao
    2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 1293 - 1299
  • [2] Monitoring elevation variations in leaf phenology of deciduous broadleaf forests from SPOT/VEGETATION time-series
    Guyon, Dominique
    Guillot, Marie
    Vitasse, Yann
    Cardot, Herve
    Hagolle, Olivier
    Delzon, Sylvain
    Wigneron, Jean-Pierre
    REMOTE SENSING OF ENVIRONMENT, 2011, 115 (02) : 615 - 627
  • [3] Novel method for identifying wheat leaf disease images based on differential amplification convolutional neural network
    Dong, Mengping
    Mu, Shaomin
    Shi, Aiju
    Mu, Wenqian
    Sun, Wenjie
    INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING, 2020, 13 (04) : 205 - 210
  • [4] Evaluation of deciduous broadleaf forests mountain using satellite data using neural network method near Caspian Sea in North of Iran
    Hashemi, Seyed A.
    ANAIS DA ACADEMIA BRASILEIRA DE CIENCIAS, 2016, 88 (04): : 2357 - 2362
  • [5] Identifying Fagaceae and Lauraceae species using leaf images and convolutional neural networks
    Wu, Tsan-Yu
    Yeh, Kuan-Ting
    Hsu, Hao-Chun
    Yang, Chih-Kai
    Tsai, Ming-Jer
    Kuo, Yan-Fu
    ECOLOGICAL INFORMATICS, 2022, 68
  • [6] Identifying the vegetation type in Google Earth images using a convolutional neural network: a case study for Japanese bamboo forests
    Watanabe, Shuntaro
    Sumi, Kazuaki
    Ise, Takeshi
    BMC ECOLOGY, 2020, 20 (01)
  • [7] A recognition method for cucumber diseases using leaf symptom images based on deep convolutional neural network
    Ma, Juncheng
    Du, Keming
    Zheng, Feixiang
    Zhang, Lingxian
    Gong, Zhihong
    Sun, Zhongfu
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 154 : 18 - 24
  • [8] Chlorophyll-a Retrieval From Sentinel-2 Images Using Convolutional Neural Network Regression
    Aptoula, Erchan
    Ariman, Sema
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [9] Chlorophyll-a Retrieval from Sentinel-2 Images Using Convolutional Neural Network Regression
    Aptoula, Erchan
    Ariman, Sema
    IEEE Geoscience and Remote Sensing Letters, 2022, 19
  • [10] Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network
    Vishnoi, Vibhor Kumar
    Kumar, Krishan
    Kumar, Brajesh
    Mohan, Shashank
    Khan, Arfat Ahmad
    IEEE ACCESS, 2023, 11 : 6594 - 6609