Estimating Forest Carbon Stocks Using CNN and Vegetation Texture Features Extracted from UAV and Satellite Data in Telkom University
DOI:
https://doi.org/10.26555/jiteki.v10i4.30546Keywords:
Carbon Stock Estimation, Remote Sensing, Convolutional Neural Networks, Vegetation and Texture Features, UAV and Satellite DataAbstract
Forests play a crucial role in mitigating climate change by acting as carbon sinks, yet traditional methods of carbon stock estimation, reliant on manual tree measurements, are costly, time-consuming, and geographically limited. Recent advancements in remote sensing technologies, such as the combination of Unmanned Aerial Vehicles (UAVs) and Google Earth Engine (GEE), offer a promising alternative by integrating high-resolution local observations with global-scale data. Using the power of Convolutional Neural Networks (CNNs), this study suggests an integrated method for classifying carbon stocks by fusing textural parameters like homogeneity and entropy with spectral indices like Green Chromatic Coordinates (GCC) and Excess Green Index (ExG). CNNs are used to capture the spectral richness and structural complexity of vegetation because of their propensity to extract hierarchical spatial characteristics. The research compares the performance of various feature combinations—color-based, texture-based, and mixed features—using a hybrid framework of UAV and GEE data. It is anticipated that the results will demonstrate how spectral and textural features work together to increase classification accuracy. In addition to tackling major issues in carbon stock estimation, this scalable and integrated framework is made to adapt to a variety of forest ecosystems and aid in the creation of conservation policies and the mitigation of climate change.
References
[1] Z. Yu, “Improved implicit diffusion model with knowledge distillation to estimate the spatial distribution density of carbon stock in remote sensing imagery,” arxiv. 2024, [Online]. Available: http://arxiv.org/abs/2411.17973.
[2] L. Zhang, Y. Cai, H. Huang, A. Li, L. Yang, and C. Zhou, “A CNN-LSTM Model for Soil Organic Carbon Content Prediction with Long Time Series of MODIS-Based Phenological Variables,” Remote Sens (Basel), vol. 14, no. 18, p. 4441, Sep. 2022, https://doi.org/10.3390/rs14184441.
[3] L. J. R. Nunes, C. I. R. Meireles, C. J. Pinto Gomes, and N. M. C. Almeida Ribeiro, “Forest Contribution to Climate Change Mitigation: Management Oriented to Carbon Capture and Storage,” Climate, vol. 8, no. 2, p. 21, Jan. 2020, https://doi.org/10.3390/cli8020021.
[4] G. Reiersen et al., “ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery,” arxiv. 2022, [Online]. Available: http://arxiv.org/abs/2201.11192.
[5] Y. Ye, M. Wang, L. Zhou, G. Lei, J. Fan, and Y. Qin, “Adjacent-Level Feature Cross-Fusion With 3-D CNN for Remote Sensing Image Change Detection,” IEEE Transactions on Geoscience and Remote Sensing. 2023, https://doi.org/10.1109/TGRS.2023.3305499.
[6] B. Pan et al., “A CNN–LSTM Machine-Learning Method for Estimating Particulate Organic Carbon from Remote Sensing in Lakes,” Sustainability, vol. 15, no. 17, p. 13043, Aug. 2023 https://doi.org/10.3390/su151713043.
[7] A. R. Arunarani, S. Selvanayaki, M. S. Al Ansari, M. A. A. Walid, N. Devireddy, and M. M. Keerthi, “Crop Yield Prediction Using Spatio Temporal CNN and Multimodal Remote Sensing,” in 2023 2nd International Conference on Edge Computing and Applications (ICECAA), pp. 1042–1048, 2023, https://doi.org/10.1109/ICECAA58104.2023.10212267.
[8] S. Illarionova et al., “A Survey of Computer Vision Techniques for Forest Characterization and Carbon Monitoring Tasks,” Remote Sensing, vol. 14, no. 22, pp. 5861, 2022, https://doi.org/10.3390/rs14225861.
[9] R. Su, W. Du, Y. Shan, H. Ying, W. Rihan, and R. Li, “Aboveground Carbon Stock Estimation Based on Backpack LiDAR and UAV Multispectral Imagery at the Forest Sample Plot Scale,” Remote Sens (Basel), vol. 16, no. 21, p. 3927, Oct. 2024, https://doi.org/10.3390/rs16213927.
[10] I. Rahmatika, I. N. Hidayati, R. Suharyadi, and E. Nurjani, “Carbon Stock Estimation From Vegetation Biomass Using Spot-7 Imagery,” Indonesian Journal of Geography, vol. 55, no. 3, pp. 385–396, 2023, https://doi.org/10.22146/ijg.78690.
[11] S. F. Tóth, K. L. Oken, C. C. Stawitz, and H.-E. Andersen, “Optimal Survey Design for Forest Carbon Monitoring in Remote Regions Using Multi-Objective Mathematical Programming,” Forests, vol. 13, no. 7, p. 972, Jun. 2022, https://doi.org/10.3390/f13070972.
[12] A. O. Adegbite, I. Barrie, S. F. Osholake, T. Alesinloye, and A. B. Bello, “Artificial Intelligence in Climate Change Mitigation: A Review of Predictive Modeling and Data-Driven Solutions for Reducing Greenhouse Gas Emissions,” World Journal of Advanced Research and Reviews, vol. 24, no. 1, pp. 408–414, Oct. 2024, https://doi.org/10.30574/wjarr.2024.24.1.3043.
[13] A. A. Dar and N. Parthasarathy, “Patterns and drivers of tree carbon stocks in Kashmir Himalayan forests: implications for climate change mitigation,” Ecol Process, vol. 11, no. 1, p. 58, Sep. 2022, https://doi.org/10.1186/s13717-022-00402-z.
[14] C.-H. Lee, K.-Y. Chen, and L. D. Liu, “Effect of Texture Feature Distribution on Agriculture Field Type Classification with Multitemporal UAV RGB Images,” Remote Sens (Basel), vol. 16, no. 7, p. 1221, Mar. 2024, https://doi.org/10.3390/rs16071221.
[15] K. Yang, H. Zhang, F. Wang, and R. Lai, “Extraction of Broad-Leaved Tree Crown Based on UAV Visible Images and OBIA-RF Model: A Case Study for Chinese Olive Trees,” Remote Sens (Basel), vol. 14, no. 10, p. 2469, May 2022, https://doi.org/10.3390/rs14102469.
[16] K. C. L. Wong, L. Klein, A. F. da Silva, H. Wang, J. Singh, and T. Syeda-Mahmood, “Image-Based Soil Organic Carbon Remote Sensing from Satellite Images with Fourier Neural Operator and Structural Similarity,” In IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium, pp. 1305-1308, 2023, https://doi.org/10.1109/IGARSS52108.2023.10281551.
[17] Y. Zhao, Y. Ma, L. J. Quackenbush, and Z. Zhen, “Estimation of Individual Tree Biomass in Natural Secondary Forests Based on ALS Data and WorldView-3 Imagery,” Remote Sens (Basel), vol. 14, no. 2, p. 271, Jan. 2022, https://doi.org/10.3390/rs14020271.
[18] M. O. Duman and M. E. Tağluk, “Assessment of an Optimal Multilayer Perceptron Model in Estimation of Stock’s Price Rates; a Sample from the Turkish Stock Exchange BIST,” in 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP), pp. 1–5. 2024, https://doi.org/10.1109/IDAP64064.2024.10710792.
[19] F. Ecer, S. Ardabili, S. S. Band, and A. Mosavi, “Training Multilayer Perceptron with Genetic Algorithms and Particle Swarm Optimization for Modeling Stock Price Index Prediction,” Entropy, vol. 22, no. 11, p. 1239, Oct. 2020, https://doi.org/10.3390/e22111239.
[20] B. Yuan, S. S. Sehra, and B. Chiu, “Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images,” Remote Sens (Basel), vol. 16, no. 21, p. 3961, Oct. 2024, https://doi.org/10.3390/rs16213961.
[21] D. Datta, M. Paul, M. Murshed, S. W. Teng, and L. M. Schmidtke, “Unveiling Soil-Vegetation Interactions: Reflection Relationships and an Attention-Based Deep Learning Approach for Carbon Estimation,” in 2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 1–6, 2024, https://doi.org/10.1109/ICMEW63481.2024.10645460.
[22] L. Wang, J. Gao, and X. Geng, “A Modified Homotopy-Based Tensor Eigenpairs Algorithm for Remote Sensing Feature Extraction,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022, https://doi.org/10.1109/LGRS.2021.3089153.
[23] R. Du, G. Wang, N. Zhang, L. Chen, and W. Liu, “Domain Adaptive Remote Sensing Scene Classification With Middle-Layer Feature Extraction and Nuclear Norm Maximization,” IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 17, pp. 2448–2460, 2024, https://doi.org/10.1109/JSTARS.2023.3339336.
[24] Standar Nasional Indonesia, “Pengukuran dan penghitungan cadangan karbon-Pengukuran lapangan untuk penaksiran cadangan karbon berbasis lahan (land-based carbon accounting),” 2019. [Online]. Available: www.bsn.go.id.
[25] “Strategi Nasional REDD+,” 2010.
[26] M. Varsha, B. Poornima, and P. Kumar, “A Machine Learning Technique for Rice Blast Disease Severity Prediction Using K-Means SMOTE Class Balancing,” Int J Risk Conting Manag, vol. 11, no. 1, pp. 1–27, Dec. 2022, https://doi.org/10.4018/IJRCM.315304.
[27] G. R. Patra, S. P. Iyer, S. Satyaprakash, and M. N. Mohanty, “A Class Balancing Based Machine Learning Approach for Fraudulent Credit Card Transaction Detection,” in 2023 1st International Conference on Circuits, Power and Intelligent Systems (CCPIS), pp. 1–6, 2023, https://doi.org/10.1109/CCPIS59145.2023.10291883.
[28] Z. Wu et al., “Urban carbon stock estimation based on deep learning and UAV remote sensing: a case study in Southern China,” All Earth, vol. 35, no. 1, pp. 272–286, Dec. 2023, https://doi.org/10.1080/27669645.2023.2249645.
[29] B. Wang, Y. Chen, Z. Yan, and W. Liu, “Integrating Remote Sensing Data and CNN-LSTM-Attention Techniques for Improved Forest Stock Volume Estimation: A Comprehensive Analysis of Baishanzu Forest Park, China,” Remote Sens (Basel), vol. 16, no. 2, p. 324, Jan. 2024, https://doi.org/10.3390/rs16020324.
[30] A. A. S. Gunawan, I. S. Edbert, F. S. Pramudya, and A. N. Rakhiemah, “Web-based mangrove distribution and carbon stock monitoring system in Papua using CNN on satellite imagery,” Procedia Comput Sci, vol. 245, pp. 637–646, 2024, https://doi.org/10.1016/j.procs.2024.10.290.
[31] H. Mosaid et al., “Improved soil carbon stock spatial prediction in a Mediterranean soil erosion site through robust machine learning techniques,” Environ Monit Assess, vol. 196, no. 2, p. 130, Feb. 2024, https://doi.org/10.1007/s10661-024-12294-x.
[32] H. Henri, A. M. Farhaby, O. Supratman, W. Adi, and S. Febrianto, “Assessment of species diversity, biomass and carbon stock of mangrove forests on Belitung Island, Indonesia,” Biodiversitas, vol. 25, no. 1, Feb. 2024, https://doi.org/10.13057/biodiv/d250103.
[33] I. P. Sugiana, T. Prartono, R. Rastina, and A. F. Koropitan, “Ecosystem carbon stock and annual sequestration rate from three genera-dominated mangrove zones in Benoa Bay, Bali, Indonesia,” Biodiversitas, vol. 25, no. 1, Feb. 2024, https://doi.org/10.13057/biodiv/d250133.
[34] J. Tang and J. Li, “Carbon risk and return prediction: Evidence from the multi-CNN method,” Front Environ Sci, vol. 10, Oct. 2022, https://doi.org/10.3389/fenvs.2022.1035809.
[35] J. Asian, N. D. Arianti, A. Ariefin, and M. Muslih, “Comparison of feature extraction and auto-preprocessing for chili pepper (Capsicum Frutescens) quality classification using machine learning,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 1, p. 319, Mar. 2024, https://doi.org/10.11591/ijai.v13.i1.pp319-328.
[36] K. Jung, D.-H. Bae, M.-J. Um, S. Kim, S. Jeon, and D. Park, “Evaluation of Nitrate Load Estimations Using Neural Networks and Canonical Correlation Analysis with K-Fold Cross-Validation,” Sustainability, vol. 12, no. 1, p. 400, Jan. 2020, https://doi.org/10.3390/su12010400.
[37] B. Kumar, K. Manisha, A. Sinha, A. Kumar, and J. Kumar, “Deep Learning Based Image Classification for Automated Face Spoofing Detection Using Machine Learning: Convolutional Neural Network,” in 2024 2nd World Conference on Communication & Computing (WCONF), pp. 1–8, 2024, https://doi.org/10.1109/WCONF61366.2024.10692150.
[38] S. A. Mosa, Istomo, and A. P. P. Hartoyo, “Estimation of vegetation density using NDVI and carbon stock in the Utilization Zone of Gunung Halimun Salak National Park,” IOP Conf Ser Earth Environ Sci, vol. 1315, no. 1, p. 012041, Mar. 2024, https://doi.org/10.1088/1755-1315/1315/1/012041.
[39] F. Zhang, Z. Hu, K. Yang, Y. Fu, Z. Feng, and M. Bai, “The Surface Crack Extraction Method Based on Machine Learning of Image and Quantitative Feature Information Acquisition Method,” Remote Sens (Basel), vol. 13, no. 8, p. 1534, Apr. 2021, https://doi.org/10.3390/rs13081534.
[40] M. E. Sahin, “Image processing and machine learning‐based bone fracture detection and classification using X‐ray images,” Int J Imaging Syst Technol, vol. 33, no. 3, pp. 853–865, May 2023, https://doi.org/10.1002/ima.22849.
[41] P. P. Monfared and S. M. Jarchi, “CNN-NLP Based Persian Feedback Detection of Stock Symbols in the Stock Market,” in 2024 10th International Conference on Artificial Intelligence and Robotics (QICAR), pp. 125–130, 2024, https://doi.org/10.1109/QICAR61538.2024.10496608.
[42] H. İ. Tuncer and D. Altınel, “Classification of Eye Diseases using Machine Learning with Preprocessing,” in 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP), pp. 1–7, 2024, https://doi.org/10.1109/IDAP64064.2024.10710977.
[43] X. Zong, “MLP, CNN, LSTM and Hybrid SVM for Stock Index Forecasting Task to INDU and FTSE100,” SSRN Electronic Journal, 2020, https://doi.org/10.2139/ssrn.3644034.
[44] A. Sharma and S. Rani, “A Cutting‐Edge Hybrid Deep Learning Technique with Low Rank Approximation for Attacks Classification on IoT Traffic Data,” Internet Technology Letters, Nov. 2024, https://doi.org/10.1002/itl2.606.
[45] D. S. Rao, K. M. Lakshmi, M. Sridevi, P. P. M. Krishna, G. J. Rao “Multi-Object Classification for Deep Learning Analysis in CNN and MLP,” NeuroQuantology, vol. 20, no. 10, p. 5805. 2022, https://doi.org/10.48047/nq.2022.20.10.NQ55581.
[46] P. Mittal, A. Sharma, and R. Singh, “Deformable patch-based-multi-layer perceptron Mixer model for forest fire aerial image classification,” J Appl Remote Sens, vol. 17, no. 2, Nov. 2022, https://doi.org/10.1117/1.JRS.17.022203.
[47] D. Banerjee, V. Kukreja, S. Vats, V. Jain, and B. Goyal, “Enhancing Accuracy of Yellowing Disease Severity Level Detection in Coconut Palms with SVM Regularization and CNN Feature Extraction,” in 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), pp. 109–114, 2023, https://doi.org/10.1109/ICSCCC58608.2023.10176557.
[48] F. Guo, D. Liu, S. Mo, Q. Li, J. Meng, and Q. Huang, “Assessment of Phenological Dynamics of Different Vegetation Types and Their Environmental Drivers with Near-Surface Remote Sensing: A Case Study on the Loess Plateau of China,” Plants, vol. 13, no. 13, p. 1826, Jul. 2024, https://doi.org/10.3390/plants13131826.
[49] K. A. Rashedi, M. T. Ismail, S. Al Wadi, A. Serroukh, T. S. Alshammari, and J. J. Jaber, “Multi-Layer Perceptron-Based Classification with Application to Outlier Detection in Saudi Arabia Stock Returns,” Journal of Risk and Financial Management, vol. 17, no. 2, p. 69, Feb. 2024, https://doi.org/10.3390/jrfm17020069.
[50] C. Wang et al., “R-MFNet: Analysis of Urban Carbon Stock Change against the Background of Land-Use Change Based on a Residual Multi-Module Fusion Network,” Remote Sens (Basel), vol. 15, no. 11, Jun. 2023, https://doi.org/10.3390/rs15112823.
[51] Y. Zheng, Z. Dang, C. Peng, C. Yang, and X. Gao, “Multi-view Multi-label Anomaly Network Traffic Classification based on MLP-Mixer Neural Network,” arXiv preprint arXiv:2210.16719, 2022, https://doi.org/10.48550/arXiv.2210.16719.
[52] Q. Zhang, E. Bai, M. Shao, and H. Liang, “Video-Mlp: Convolution-Free, Attention-Free Architecture for Video Classification,” Journal of Intelligent & Fuzzy Systems, (Preprint), pp. 1-12, 2023, https://doi.org/10.2139/ssrn.4372886.
[53] S. Illarionova, P. Tregubova, I. Shukhratov, D. Shadrin, A. Efimov, and E. Burnaev, “Advancing forest carbon stocks’ mapping using a hierarchical approach with machine learning and satellite imagery,” Sci Rep, vol. 14, no. 1, Dec. 2024, https://doi.org/10.1038/s41598-024-71133-8.
[54] T. Leditznig and H. Klug, “Estimating Carbon Stock in Unmanaged Forests Using Field Data and Remote Sensing,” Remote Sens (Basel), vol. 16, no. 21, p. 3926, Oct. 2024, https://doi.org/10.3390/rs16213926.
[55] T. D. Pham et al., “Advances in Earth observation and machine learning for quantifying blue carbon,” Earth-Science Reviews, p. 104501, 2023, https://doi.org/10.1016/j.earscirev.2023.104501.
[56] R. Ma, W. Wu, Q. Wang, N. Liu, and Y. Chang, “Offshore Hydrocarbon Exploitation Target Extraction Based on Time-Series Night Light Remote Sensing Images and Machine Learning Models: A Comparison of Six Machine Learning Algorithms and Their Multi-Feature Importance,” Remote Sens (Basel), vol. 15, no. 7, Apr. 2023, https://doi.org/10.3390/rs15071843.
[57] L. Dong et al., “Application of convolutional neural network on lei bamboo above-ground-biomass (AGB) estimation using Worldview-2,” Remote Sens (Basel), vol. 12, no. 6, Mar. 2020, https://doi.org/: 10.3390/rs12060958.
[58] D. Krstinić, M. Braović, L. Šerić, and D. Božić-Štulić, “Multi-label Classifier Performance Evaluation with Confusion Matrix,” in Computer Science & Information Technology, pp. 1–14, 2020, https://doi.org/10.5121/csit.2020.100801.
[59] X. Zhou and A. Del Valle, “Range Based Confusion Matrix for Imbalanced Time Series Classification,” in 2020 6th Conference on Data Science and Machine Learning Applications (CDMA), pp. 1–6, 2020, https://doi.org/10.1109/CDMA47397.2020.00006.
[60] I. O. Awoyelu, B. R. Ojo, S. B. Aregbesola, O. O. Soyele “Performance Evaluation of a Classification Model for Oral Tumor Diagnosis,” Computer and Information Science, vol. 13, no. 1, p. 1, Dec. 2019, https://doi.org/10.5539/cis.v13n1p1.
[61] A. Shandilya, “ML Model for Stock Classification,” Int J Res Appl Sci Eng Technol, vol. 12, no. 4, pp. 5230–5239, Apr. 2024, https://doi.org/10.22214/ijraset.2024.61136.
[62] J. Zhou et al., “Evaluation of Different Algorithms for Estimating the Growing Stock Volume of Pinus massoniana Plantations Using Spectral and Spatial Information from a SPOT6 Image,” Forests, vol. 11, no. 5, p. 540, May 2020, https://doi.org/10.3390/f11050540.
[63] A. Algherairy, W. Almattar, E. Bakri, and S. Albelali, “The Impact of Feature Selection on Different Machine Learning Models for Breast Cancer Classification,” in 2022 7th International Conference on Data Science and Machine Learning Applications (CDMA), pp. 91–96, 2022, https://doi.org/10.1109/CDMA54072.2022.00020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Raditya Aydin, Erwin Budi Setiawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with JITEKI agree to the following terms:
- Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
This work is licensed under a Creative Commons Attribution 4.0 International License
