Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks
"> Figure 1
<p>Location of the study area. (<b>a</b>) The position of the Loess Plateau; (<b>b</b>) The locations of Yongshou (YS), Zhengning (ZN), and Baishui (BS).</p> "> Figure 2
<p>Unmanned aerial vehicle (UAV) platform and multispectral sensor.</p> "> Figure 3
<p>Distribution of UAV multispectral sample plots: (<b>a</b>) distribution of scattered small plots; (<b>b</b>) distribution of large-block plots; (<b>c</b>) distribution of plots in YS County; and (<b>d</b>) distribution of large-block plot distribution. “P” represents “plot”.</p> "> Figure 4
<p>UAV multispectral data of coniferous and broadleaf forest plots based on multispectral synthesis.</p> "> Figure 5
<p>The framework for identifying broadleaf and coniferous forests using Residual Neural Network (ResNet) architecture and transfer learning techniques: (<b>a</b>) pre-trained model; (<b>b</b>) fine-tuning the pre-trained model; (<b>c</b>) evaluation of the effectiveness of the fine-tuning; and (<b>d</b>) model application.</p> "> Figure 6
<p>Trends associated with loss-curve changes under different combination strategies, with a 1 × 1 window size.</p> "> Figure 7
<p>Trends associated with loss-curve changes under different combination strategies, with a 3 × 3 window size.</p> "> Figure 8
<p>Impacts of image size, sample quantity, and model depth on the total training time and the average inference time per image of the residual architecture model.</p> "> Figure 9
<p>Differences in classification results of coniferous and broadleaf forests among different combination strategies.</p> "> Figure 10
<p>Spatial distribution map of coniferous and broadleaf forests.</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area
2.2. Acquisition and Preprocessing of UAV Multispectral and Landsat Remote Sensing Data
2.2.1. UAV Platform and Multispectral Sensor
2.2.2. Setting up the UAV Operation Plots
2.2.3. UAV Operation Parameters and Data Preprocessing
2.2.4. Acquisition and Preprocessing of Landsat Remote Sensing Images
2.3. Rapid Identification of Broadleaf and Coniferous Forests Using Deep Learning-Based Techniques
2.3.1. Dataset Preparation for Labeling
2.3.2. Determining the Number of Input Channels for the Model
2.3.3. Constructing Pre-Trained Models
- (1)
- Model Selection
- (2)
- ResNet Model Initialization and Architectural Adjustments
- (3)
- Training of ResNet Models
- (4)
- Performance Evaluation of the Pre-trained Model
2.3.4. Sensitivity Analysis
2.3.5. Fine-Tuning the Pre-Trained Model Using Transfer Learning and Performance Evaluation
3. Results
3.1. Impacts of Different Combination Strategies on the Performance of Pre-Trained Models
3.1.1. Loss-Curve Variation Trends
3.1.2. The Impacts of Image Size, Sample Quantity, and Model Depth on the Time Efficiency of Pre-Trained Models
3.1.3. The Impacts of Image Size, Sample Quantity, and Model Depth on Classification Results
3.2. Fine-Tuning Pre-Trained Models with Multispectral UAV Data for Enhanced Classification Performance
4. Discussion
5. Conclusions
- By integrating the ResNet architecture with transfer learning techniques, and utilizing multispectral data from UAVs and Landsat satellites, the framework achieved substantial improvements in classification accuracy. The fine-tuned model achieved over 90% accuracy in classifying forest types in Yongshou, Zhengning, and Baishui counties. This validates the effectiveness and rapidity of the proposed technical framework.
- The study systematically evaluated the effects of image size, sample quantity, and model depth on the model’s performance. It was found that appropriate image sizes (3 × 3 pixels) and increased sample quantities substantially enhance the model’s classification accuracy and generalization ability. The optimal strategy was identified as using a 3 × 3 image size, 2000 samples, and a ResNet-50 model depth, achieving the best balance between accuracy and efficiency.
Supplementary Materials
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Locatelli, B. Ecosystem services and climate change. In Routledge Handbook of Ecosystem Services; Routledge: London, UK, 2016; pp. 481–490. [Google Scholar] [CrossRef]
- Sultana, F.; Arfin-Khan, M.; Karim, M.; Mukul, S. Rainfall Modifies the Disturbance Effects on Regulating Ecosystem Services in Tropical Forests of Bangladesh. Forests 2023, 14, 272. [Google Scholar] [CrossRef]
- Kramer, K.; Leinonen, I.; Loustau, D. The importance of phenology for the evaluation of impact of climate change on growth of boreal, temperate and Mediterranean forests ecosystems: An overview. Int. J. Biometeorol. 2000, 44, 67–75. [Google Scholar] [CrossRef] [PubMed]
- Walkiewicz, A.; Bieganowski, A.; Rafalska, A.; Khalil, M.; Osborne, B. Contrasting Effects of Forest Type and Stand Age on Soil Microbial Activities: An Analysis of Local Scale Variability. Biology 2021, 10, 850. [Google Scholar] [CrossRef] [PubMed]
- Gao, L.; Bowker, M.; Xu, M.; Sun, H.; Tuo, D.; Zhao, Y. Biological soil crusts decrease erodibility by modifying inherent soil properties on the Loess Plateau, China. Soil Biol. Biochem. 2017, 105, 49–58. [Google Scholar] [CrossRef]
- Lu, A.; Tian, P.; Mu, X.; Zhao, G.; Feng, Q.; Guo, J.; Xu, W. Fuzzy Logic Modeling of Land Degradation in a Loess Plateau Watershed, China. Remote Sens. 2022, 14, 4779. [Google Scholar] [CrossRef]
- Liu, J.; Chang, Q.; Zhang, J.; Chen, T.; Jia, K. Effect of vegetation on soil fertility in different woodlands on Loess Plateau. J. Northwest A F Univ. Nat. Sci. Ed. 2004, 32, 111–115. [Google Scholar] [CrossRef]
- Huang, Y.; Liu, D.; An, S. Effects of slope aspect on soil nitrogen and microbial properties in the Chinese Loess region. Catena 2015, 125, 135–145. [Google Scholar] [CrossRef]
- Shi, Z.; Bai, Z.; Guo, D.; Chen, M. Develop a Soil Quality Index to Study the Results of Black Locust on Soil Quality below Different Allocation Patterns. Land 2021, 10, 785. [Google Scholar] [CrossRef]
- Lehmann, E.A.; Caccetta, P.; Lowell, K.; Mitchell, A.; Zhou, Z.S.; Held, A.; Tapley, I. SAR and optical remote sensing: Assessment of complementarity and interoperability in the context of a large-scale operational forest monitoring system. Remote Sens. Environ. 2015, 156, 335–348. [Google Scholar] [CrossRef]
- Lu, M.; Chen, B.; Liao, X.H.; Yue, T.X.; Yue, H.Y.; Ren, S.M.; Xu, B. Forest types classification based on multi-source data fusion. Remote Sens. 2017, 9, 1153. [Google Scholar] [CrossRef]
- Liu, Y.; Gong, W.; Hu, X.; Gong, J. Forest Type Identification with Random Forest Using Sentinel-1A, Sentinel-2A, Multi-Temporal Landsat-8 and DEM Data. Remote Sens. 2018, 10, 946. [Google Scholar] [CrossRef]
- Elizar, E.; Zulkifley, M.A.; Muharar, R.; Zaman, M.H.M.; Mustaza, S.M. A review on multiscale-deep-learning applications. Sensors 2022, 22, 7384. [Google Scholar] [CrossRef] [PubMed]
- Li, J.X.; Hong, D.F.; Gao, L.R.; Yao, J.; Zheng, K.; Zhang, B.; Chanussot, J. Deep learning in multimodal remote sensing data fusion: A comprehensive review. Int. J. Appl. Earth Obs. Geoinf. 2022, 112, 102926. [Google Scholar] [CrossRef]
- Day, O.; Khoshgoftaar, T.M. A survey on heterogeneous transfer learning. J. Big Data 2017, 4, 29. [Google Scholar] [CrossRef]
- Ma, Y.C.; Chen, S.; Ermon, S.; Lobell, D.B. Transfer learning in environmental remote sensing. Remote Sens. Environ. 2024, 301, 113924. [Google Scholar] [CrossRef]
- Han, X.; Zhang, Z.; Ding, N.; Gu, Y.; Liu, X.; Huo, Y.; Zhu, J. Pre-trained models: Past, present and future. AI Open 2021, 2, 225–250. [Google Scholar] [CrossRef]
- Cao, K.; Zhang, X. An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images. Remote Sens. 2020, 12, 1128. [Google Scholar] [CrossRef]
- Zhang, C.; Xia, K.; Feng, H.; Yang, Y.; Du, X. Tree species classification using deep learning and RGB optical images obtained by an unmanned aerial vehicle. J. For. Res. 2020, 32, 1879–1888. [Google Scholar] [CrossRef]
- Xi, Z.; Hopkinson, C.; Rood, S.B.; Peddle, D.R. See the forest and the trees: Effective machine and deep learning algorithms for wood filtering and tree species classification from terrestrial laser scanning. ISPRS J. Photogramm. Remote Sens. 2020, 168, 1–16. [Google Scholar] [CrossRef]
- Han, T.; Sánchez-Azofeifa, G. A Deep Learning Time Series Approach for Leaf and Wood Classification from Terrestrial LiDAR Point Clouds. Remote Sens. 2022, 14, 3157. [Google Scholar] [CrossRef]
- Thenmozhi, K.; Reddy, U.S. Crop pest classification based on deep convolutional neural network and transfer learning. Comput. Electron. Agric. 2019, 164, 104906. [Google Scholar] [CrossRef]
- Aldayel, M.; Ykhlef, M.; Al-Nafjan, A. Electroencephalogram-Based Preference Prediction Using Deep Transfer Learning. IEEE Access 2020, 8, 176818–176829. [Google Scholar] [CrossRef]
- Odebiri, O.; Odindi, J.; Mutanga, O. Basic and deep learning models in remote sensing of soil organic carbon estimation: A brief review. Int. J. Appl. Earth Obs. Geoinf. 2021, 102, 102389. [Google Scholar] [CrossRef]
- Veras, H.F.P.; Ferreira, M.P.; da Cunha Neto, E.M.; Figueiredo, E.O.; Dalla Corte, A.P.; Sanquetta, C.R. Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. Ecol. Inform. 2022, 71, 101815. [Google Scholar] [CrossRef]
- Scheeres, J.; de Jong, J.; Brede, B.; Brancalion, P.H.; Broadbent, E.N.; Zambrano, A.M.A.; de Almeida, D.R.A. Distinguishing forest types in restored tropical landscapes with UAV-borne LIDAR. Remote Sens. Environ. 2023, 290, 113533. [Google Scholar] [CrossRef]
- Lin, F.C.; Shiu, Y.S.; Wang, P.J.; Wang, U.H.; Lai, J.S.; Chuang, Y.C. A model for forest type identification and forest regeneration monitoring based on deep learning and hyperspectral imagery. Ecol. Inform. 2024, 80, 102507. [Google Scholar] [CrossRef]
- Zhong, Z.; Li, J.; Ma, L.; Jiang, H.; Zhao, H. Deep residual networks for hyperspectral image classification. In Proceedings of the 2017 IEEE IGARSS, Worth, TX, USA, 23–28 July 2017; pp. 1824–1827. [Google Scholar] [CrossRef]
- Bharati, S.; Podder, P.; Mondal, M.; Prasath, V. CO-ResNet: Optimized ResNet model for COVID-19 diagnosis from X-ray images. Int. J. Hybrid Intell. Syst. 2021, 17, 71–85. [Google Scholar] [CrossRef]
- Li, H.; Hu, B.; Li, Q.; Jing, L. CNN-Based Individual Tree Species Classification Using High-Resolution Satellite Imagery and Airborne LiDAR Data. Forests 2021, 12, 1697. [Google Scholar] [CrossRef]
- Susanti, M.; Novita, R.; Permana, I. Application of Residual Network Architecture on COVID-19 Chest X-ray Classification. In Proceedings of the International Symposium on Information Technology and Digital Innovation (ISITDI), Virtual, 27–28 July 2022; pp. 121–125. [Google Scholar] [CrossRef]
- Ghimire, B.R.; Nagai, M.; Tripathi, N.K.; Witayangkurn, A.; Mishara, B.; Sasaki, N. Mapping of Shorea robusta forest using time series MODIS data. Forests 2017, 8, 384. [Google Scholar] [CrossRef]
- Li, L.W.; Li, N.; Lu, D.; Chen, Y. Mapping Moso bamboo forest and its on-year and off-year distribution in a subtropical region using time-series Sentinel-2 and Landsat 8 data. Remote Sens. Environ. 2019, 231, 111265. [Google Scholar] [CrossRef]
- Borlaf-Mena, I.; García-Duro, J.; Santoro, M.; Villard, L.; Badea, O.; Tanase, M.A. Seasonality and directionality effects on radar backscatter are key to identify mountain forest types with Sentinel-1 data. Remote Sens. Environ. 2023, 296, 113728. [Google Scholar] [CrossRef]
- Zhang, J.; Zhang, Y.Y.; Zhou, T.Y.; Sun, Y.; Yang, Z.C.; Zheng, S.L. Research on the identification of land types and tree species in the Engebei ecological demonstration area based on GF-1 remote sensing. Ecol. Inform. 2023, 77, 102242. [Google Scholar] [CrossRef]
- Teixeira, I.; Morais, R.; Sousa, J.; Cunha, A. Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review. Agriculture 2023, 13, 965. [Google Scholar] [CrossRef]
- Zhao, X.; Jing, L.; Zhang, G.; Zhu, Z.; Liu, H.; Ren, S. Object-Oriented Convolutional Neural Network for Forest Stand Classification Based on Multi-Source Data Collaboration. Forests 2024, 15, 529. [Google Scholar] [CrossRef]
- Zhen, J.; Mao, D.; Shen, Z.; Zhao, D.; Xu, Y.; Wang, J.; Ren, C. Performance of XGBoost Ensemble Learning Algorithm for Mangrove Species Classification with Multi-Source Spaceborne Remote Sensing Data. J. Remote Sens. 2024, 0146. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar] [CrossRef]
- Ding, Y.; Sheng, L.; Liang, J.; Zheng, A.; He, R. ProxyMix: Proxy-based mixup training with label refinery for source-free domain adaptation. Neural Netw. 2023, 167, 92–103. [Google Scholar] [CrossRef] [PubMed]
- Salman, S.; Liu, X. Overfitting mechanism and avoidance in deep neural networks. arXiv 2019, arXiv:1901.06566. [Google Scholar] [CrossRef]
- Wu, S.; Li, G.Q.; Chen, F.; Shi, L.P. Training and inference with integers in deep neural networks. arXiv 2018, arXiv:1802.04680. [Google Scholar] [CrossRef]
- Tong, X.Y.; Xia, G.S.; Lu, Q.; Shen, H.; Li, S.; You, S.; Zhang, L. Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sens. Environ. 2020, 237, 111322. [Google Scholar] [CrossRef]
- Peng, M.; Liu, Y.; Khan, A.; Ahmed, B.; Sarker, S.K.; Ghadi, Y.Y.; Ali, Y.A. Crop monitoring using remote sensing land use and land change data: Comparative analysis of deep learning methods using pre-trained CNN models. Big Data Res. 2024, 36, 100448. [Google Scholar] [CrossRef]
- Liu, Z.; Xu, Y.; Xu, Y.; Qian, Q.; Li, H.; Ji, X.; Jin, R. Improved fine-tuning by better leveraging pre-training data. Adv. Neural Inf. Process. Syst. 2022, 35, 32568–32581. [Google Scholar]
- Dey, B.; Ahmed, R.; Ferdous, J.; Haque, M.M.U.; Khatun, R.; Hasan, F.E.; Uddin, S.N. Automated plant species identification from the stomata images using deep neural network: A study of selected mangrove and freshwater swamp forest tree species of Bangladesh. Ecol. Inform. 2023, 75, 102128. [Google Scholar] [CrossRef]
- Hamrouni, Y.; Paillassa, E.; Chéret, V.; Monteil, C.; Sheeren, D. From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2. ISPRS J. Photogramm. Remote Sens. 2021, 171, 76–100. [Google Scholar] [CrossRef]
- Kırbaş, İ.; Çifci, A. An effective and fast solution for classification of wood species: A deep transfer learning approach. Ecol. Inform. 2022, 69, 101633. [Google Scholar] [CrossRef]
- Moritake, K.; Cabezas, M.; Nhung, T.T.C.; Caceres, M.L.L.; Diez, Y. Sub-alpine shrub classification using UAV images: Performance of human observers vs DL classifiers. Ecol. Inform. 2024, 80, 102462. [Google Scholar] [CrossRef]
- Han, D.; Liu, Q.; Fan, W. A new image classification method using CNN transfer learning and web data augmentation. Expert Syst. Appl. 2018, 95, 43–56. [Google Scholar] [CrossRef]
- Semma, A.; Lazrak, S.; Hannad, Y.; Boukhani, M.; El Kettani, Y. Writer Identification: The effect of image resizing on CNN performance. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 2021, 46, 501–507. [Google Scholar] [CrossRef]
- Khan, A.; Sohail, A.; Zahoora, U.; Qureshi, A.S. A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 2020, 53, 5455–5516. [Google Scholar] [CrossRef]
- Alom, M.Z.; Taha, T.M.; Yakopcic, C.; Westberg, S.; Sidike, P.; Nasrin, M.S.; Asari, V.K. A state-of-the-art survey on deep learning theory and architectures. Electronics 2019, 8, 292. [Google Scholar] [CrossRef]
- Shorten, C.; Khoshgoftaar, T. A survey on Image Data Augmentation for Deep Learning. J. Big Data 2019, 6, 60. [Google Scholar] [CrossRef]
- Shorten, C.; Khoshgoftaar, T.; Furht, B. Text Data Augmentation for Deep Learning. J. Big Data 2021, 8, 101. [Google Scholar] [CrossRef] [PubMed]
- Peng, S.; Huang, H.; Chen, W.; Zhang, L.; Fang, W. More trainable inception-ResNet for face recognition. Neurocomputing 2020, 411, 9–19. [Google Scholar] [CrossRef]
- Zhang, H.; Wu, C.; Zhang, Z.; Zhu, Y.; Lin, H.; Zhang, Z.; Smola, A. Resnest: Split-attention networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 2736–2746. [Google Scholar] [CrossRef]
- Song, Y.; Jang, S.; Kim, K. Depth-Specific Variational Scaling Method to Improve Accuracy of ResNet. J. Korean Inst. Intell. Syst. 2021, 8, 338–345. [Google Scholar] [CrossRef]
- Khan, R.; Zhang, X.; Kumar, R.; Aboagye, E. Evaluating the Performance of ResNet Model Based on Image Recognition. In Proceedings of the 2018 International Conference on Computing and Artificial Intelligence, Las Vegas, NV, USA, 12–14 December 2018; pp. 86–90. [Google Scholar] [CrossRef]
- Gao, S.; Cheng, M.; Zhao, K.; Zhang, X.; Yang, M.; Torr, P. Res2Net: A New Multi-Scale Backbone Architecture. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 43, 652–662. [Google Scholar] [CrossRef] [PubMed]
- Bello, I.; Fedus, W.; Du, X.; Cubuk, E.; Srinivas, A.; Lin, T.; Shlens, J.; Zoph, B. Revisiting ResNets: Improved Training and Scaling Strategies. arXiv 2021, arXiv:abs/2103.07579. [Google Scholar]
Plot Number | Flight Date | Flight Time | Number of Photos |
---|---|---|---|
P1 | 4 September 2022 | 11:19 | 1014 |
P2 | 4 September 2022 | 17:19 | 1410 |
P3 | 4 September 2022 | 16:47 | 492 |
P4 | 5 September 2022 | 12:15 | 780 |
P7 | 5 September 2022 | 17:19 | 1080 |
P8 | 5 September 2022 | 16:47 | 876 |
P9 | 6 September 2022 | 14:34 | 1080 |
P10 | 6 September 2022 | 15:22 | 948 |
P11 | 6 September 2022 | 12:00 | 1098 |
P12 | 6 September 2022 | 11:58 | 654 |
P13 | 6 September 2022 | 15:53 | 876 |
P14 | 7 September 2022 | 10:47 | 702 |
P15 | 7 September 2022 | 12:00 | 1164 |
P16 | 7 September 2022 | 13:04 | 954 |
P17 | 7 September 2022 | 13:22 | 2058 |
P18 | 8 September 2022 | 14:34 | 16,416 |
P19 | 9 September 2022 | 15:22 | 11,598 |
County | Year | Sensor | Path/Row | Date of Acquisition |
---|---|---|---|---|
YS | 2022 | Landsat OLI 9 | 127-36 | 18 September 2022 |
ZN | 2022 | Landsat OLI 9 | 127-35/36 | 22 September 2022 |
BS | 2022 | Landsat OLI 9 | 127-35/36 | 18 September 2022 |
Layer Name | Output Size | 18-Layer | 34-Layer | 50-Layer |
---|---|---|---|---|
Conv1 | 32 × 32/64 × 64 | 3 × 3, 64, stride 1 | ||
Conv2x | 32 × 32/64 × 64 | |||
Conv3x | 16 × 16/32 × 32 | |||
Conv4x | 8 × 8/16 × 16 | |||
Conv5x | 4 × 4/8 × 8 | |||
1 × 1 | Average pool, 1000-d fc, SoftMax | |||
FLOPs | 1.8 × 109 | 3.6 × 109 | 3.8 × 109 |
Predicted class | |||
Negative (N) | Positive (P) | ||
Actual Class | Negative (N) | True Negative (TN) | False Positive (FP) |
Positive (P) | False Negative (FN) | True Positive (TP) |
Metric | Formula |
---|---|
Accuracy (ACC) | |
Precision (P) | |
Recall (R) | |
F1-Score (F1) |
Group Number | Window Size | Sample Quantity | Model Depth |
---|---|---|---|
G1 | 1 × 1/3 × 3 | 500 | ResNet-18 |
G2 | 1 × 1/3 × 3 | 500 | ResNet-34 |
G3 | 1 × 1/3 × 3 | 500 | ResNet-50 |
G4 | 1 × 1/3 × 3 | 1000 | ResNet-18 |
G5 | 1 × 1/3 × 3 | 1000 | ResNet-34 |
G6 | 1 × 1/3 × 3 | 1000 | ResNet-50 |
G7 | 1 × 1/3 × 3 | 2000 | ResNet-18 |
G8 | 1 × 1/3 × 3 | 2000 | ResNet-34 |
G9 | 1 × 1/3 × 3 | 2000 | ResNet-50 |
G10 | 1 × 1/3 × 3 | 4000 | ResNet-18 |
G11 | 1 × 1/3 × 3 | 4000 | ResNet-34 |
G12 | 1 × 1/3 × 3 | 4000 | ResNet-50 |
G13 | 1 × 1/3 × 3 | 8000 | ResNet-18 |
G14 | 1 × 1/3 × 3 | 8000 | ResNet-34 |
G15 | 1 × 1/3 × 3 | 8000 | ResNet-50 |
County | Before Model Fine-Tuning | After Model Fine-Tuning |
---|---|---|
ZN | 0.85 | 0.93 |
YS | 0.89 | 0.96 |
BS | 0.86 | 0.94 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, M.; Yin, D.; Li, Z.; Zhao, Z. Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks. Remote Sens. 2024, 16, 2096. https://doi.org/10.3390/rs16122096
Zhang M, Yin D, Li Z, Zhao Z. Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks. Remote Sensing. 2024; 16(12):2096. https://doi.org/10.3390/rs16122096
Chicago/Turabian StyleZhang, Mei, Daihao Yin, Zhen Li, and Zhong Zhao. 2024. "Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks" Remote Sensing 16, no. 12: 2096. https://doi.org/10.3390/rs16122096