FlexibleNet: A New Lightweight Convolutional Neural Network Model for Estimating Carbon Sequestration Qualitatively Using Remote Sensing

被引:8
作者
Awad, Mohamad M. M. [1 ]
机构
[1] Natl Council Sci Res, Remote Sesning Ctr, Beirut 11072260, Lebanon
关键词
peri-urban forests; lightweight convolutional neural network; FlexibleNet; carbon sequestration; remote sensing; IMAGE CLASSIFICATION;
D O I
10.3390/rs15010272
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Many heavy and lightweight convolutional neural networks (CNNs) require large datasets and parameter tuning. Moreover, they consume time and computer resources. A new lightweight model called FlexibleNet was created to overcome these obstacles. The new lightweight model is a CNN scaling-based model (width, depth, and resolution). Unlike the conventional practice, which arbitrarily scales these factors, FlexibleNet uniformly scales the network width, depth, and resolution with a set of fixed scaling coefficients. The new model was tested by qualitatively estimating sequestered carbon in the aboveground forest biomass from Sentinel-2 images. We also created three different sizes of training datasets. The new training datasets consisted of six qualitative categories (no carbon, very low, low, medium, high, and very high). The results showed that FlexibleNet was better or comparable to the other lightweight or heavy CNN models concerning the number of parameters and time requirements. Moreover, FlexibleNet had the highest accuracy compared to these CNN models. Finally, the FlexibleNet model showed robustness and low parameter tuning requirements when a small dataset was provided for training compared to other models.
引用
收藏
页数:17
相关论文
共 56 条
[51]   Super-Resolution Mapping Based on Spatial-Spectral Correlation for Spectral Imagery [J].
Wang, Peng ;
Wang, Liguo ;
Leung, Henry ;
Zhang, Gong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (03) :2256-2268
[52]  
Xu B., 2015, arXiv
[53]   An Efficient and Lightweight Convolutional Neural Network for Remote Sensing Image Scene Classification [J].
Yu, Donghang ;
Xu, Qing ;
Guo, Haitao ;
Zhao, Chuan ;
Lin, Yuzhun ;
Li, Daoji .
SENSORS, 2020, 20 (07)
[54]   Low-res MobileNet: An efficient lightweight network for low-resolution image classification in resource-constrained scenarios [J].
Yuan, Haiying ;
Cheng, Junpeng ;
Wu, Yanrui ;
Zeng, Zhiyong .
MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (27) :38513-38530
[55]   Estimation of Aboveground Carbon Density of Forests Using Deep Learning and Multisource Remote Sensing [J].
Zhang, Fanyi ;
Tian, Xin ;
Zhang, Haibo ;
Jiang, Mi .
REMOTE SENSING, 2022, 14 (13)
[56]  
Zhou Y, 2019, 2019 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2019), P251, DOI [10.1109/aicas.2019.8771475, 10.1109/AICAS.2019.8771475]