Evaluation of Tree Diameter and Height Measurements in UAV Data by Integrating Remote Sensing and Machine Learning Methods

Abstract

This study evaluates the effects of different ground sampling distances on the diameter and height measurements of brutian pine trees in point cloud data from unmanned aerial vehicle photographs. The study is located within the Çandır Forest Management Directorate of the Isparta Regional Directorate of Forestry. The results serve as independent variables in machine learning methods to predict field-measured diameter and height values. Nine distinct machine learning techniques were used, including AdaBoost Regression, Artificial Neural Networks, Deep Neural Networks, Decision Tree Regression, Gradient Boosting Regression, Linear Regression, Random Forest Regression, Support Vector Regression, and eXtreme Gradient Boosting Regression. The results show that predictions made using data with a low ground sampling distance had the lowest correlation values for diameter and height, while predictions made using data with a high ground sampling distance had the lowest correlation values. Deep Neural Network achieved the highest success rate for diameter estimation, while Decision Tree Regression had the lowest success.

Keywords

• Machine learning
• unmanned aerial vehicle
• remote sensing
• point cloud

İHA ile Ağaç Çapı ve Yüksekliği Ölçümlerinin Uzaktan Algılama ve Makine Öğrenmesi Yöntemleriyle Bütünleştirilerek Değerlendirilmesi

Abstract

Bu çalışmada insansız hava aracı fotoğraflarından elde edilen nokta bulutu verilerinde farklı yerden örnekleme mesafelerinin kızılçam ağaçlarının çap ve yükseklik ölçümlerine etkisi değerlendirilmektedir. Çalışma Isparta Orman Bölge Müdürlüğü'ne bağlı Çandır Orman İşletme Müdürlüğü bünyesinde yer almaktadır. Sonuçlar, sahada ölçülen çap ve yükseklik değerlerini tahmin etmek için makine öğrenimi yöntemlerinde bağımsız değişkenler olarak hizmet etmektedir. Araştırmada, AdaBoost Regresyon, Yapay Sinir Ağları, Derin Sinir Ağları, Karar Ağacı Regresyonu, Gradient Boosting Regresyon, Doğrusal Regresyon, Rastgele Orman Regresyon, Destek Vektör Regresyonu ve eXtreme Gradient Boosting Regresyon dahil olmak üzere dokuz farklı makine öğrenme tekniği kullanıldı. Sonuçlar, düşük yerden örnekleme mesafesine sahip veriler kullanılarak yapılan tahminlerin çap ve yükseklik için en düşük korelasyon değerlerine sahip olduğunu, yüksek yerden örnekleme mesafesine sahip veriler kullanılarak yapılan tahminlerin ise en düşük korelasyon değerlerine sahip olduğunu göstermektedir. Çap tahmininde en yüksek başarı oranını Derin Sinir Ağı elde ederken, Karar Ağacı Regresyonu en düşük başarıyı elde etmiştir.

Keywords

• Makine öğrenmesi
• insansız hava aracı
• uzaktan algılama
• nokta bulutu

References

1. [1] H. O. Çoban, “Uydu verileri ile orman alanlarındaki zamansal değişimlerin belirlenmesi,” Ph.D. dissertation, İstanbul Univ., İstanbul, Türkiye, 2006.
2. [2] H. Durgun and H. O. Çoban, Tarım, orman ve su bilimlerinde öncü ve çağdaş çalışmalar: Isparta ve Burdur bölgesindeki orman ekosistemleri ve topoğrafik değişkenler arasindaki ilişkilerin değerlendirilmesi. Duvar Yayınları, 2023, 113-137.
3. [3] A. Koç, "Coğrafi bilgi sistemlerinde veriler ve elde ediliş yöntemleri," Journal of the Faculty of Forestry Istanbul University, vol. 43, pp. 117–134, 1993.
4. [4] İ. Balcı, H. O. Çoban and M. Eker, "Coğrafi bilgi sistemi," Turkish Journal of Forestry, vol. 1, pp. 115–132, 2009. doi:10.18182/tjf.56117
5. [5] E. Buğday, "Orman yönetiminde insansız hava aracı uygulamaları," in Abstract Book: 2nd International Eurasian Conference on Biological and Chemical Sciences, EurasianBioChem2019, Ankara, Turkey, June 28-29, 2019, pp. 29.
6. [6] B. Menteşoğlu and M. İnan, "İnsansız hava araçlarının (İHA) ormancılık uygulamalarında kullanımı," in VI. Uzaktan Algılama ve Cografi Bilgi Sistemleri Sempozyumu: UZAL-CBS 2016, Adana, Turkey, October 5-7, 2016, pp. 5–7.
7. [7] W. Gao, Q. Qiu, C. Yuan, X. Shen, F. Cao, G. Wang and G. Wang, “Forestry big data: A review and bibliometric analysis,” Forests, vol. 13(10), pp. 1549, 2022. doi:10.3390/f13101549
8. [8] G. Selvi, “Automated Machine Learning Platform,” in 6th International Conference on Computer Science and Engineering: UBMK2021, Ankara, Turkey, September 15-17, 2021, pp.769-774.

9. [9] T. Liu, Y. Sun, C. Wang, Y. Zhang, Z. Qiu, W. Gong and X. Duan, “Unmanned aerial vehicle and artificial intelligence revolutionizing efficient and precision sustainable forest management,” Journal of Cleaner Production, vol. 311, pp. 127546, 2021. doi:10.1016/j.jclepro.2021.127546
10. [10] M. A. Lefsky, W. B. Cohen, A. Hudak, S. A. Acker and J. L. Ohmann, "Integration of lidar, Landsat ETM+ and forest inventory data for regional forest mapping," in International Archives of Photogrammetry and Remote Sensing, vol. 32, no. 3/W14, pp. 119–126, 1999.
11. [11] M. Moghaddam, J. Dungan, S. Acker, "Forest variable estimation from fusion of SAR and multispectral optical data," IEEE Transactions on Geoscience and Remote Sensing, vol. 40, no. 10, pp. 2176–2187, 2002. doi:10.1109/TGRS.2002.804725
12. [12] K. Tsuya, N. Fujii, D. Kokuryo, T. Kaihara, Y. Sunami, R. Izuno and M. Mano, "A Study on tree species discrimination using machine learning in forestry," Procedia CIRP, vol. 99, pp. 703–706, 2021. doi:10.1016/j.procir.2021.03.094
13. [13] A. Şahin, G. Aylak Özdemir, O. Oral, B. L. Aylak, M. İnce and E. Özdemir, "Estimation of tree height with machine learning techniques in coppice-originated pure sessile oak (Quercus petraea (Matt.) Liebl.) stands," Scandinavian Journal of Forest Research, vol. 38, no. 1-2, pp. 87–96, 2023. doi:10.1080/02827581.2023.2168044
14. [14] B. L. Aylak, M. İnce, O. Oral, G. Süer, N. Almasarwah, M. Singh and B. Salah, "Application of machine learning methods for pallet loading problem," Applied Sciences, vol. 11, no. 18, pp. 8304, 2021. doi:10.3390/app11188304
15. [15] H. Varol Özkavak, M. İnce and E. Bıçaklı, "Prediction of mechanical properties of the 2024 aluminum alloy by using machine learning methods," Arabian Journal for Science and Engineering, vol. 48, no. 3, pp. 2841–2850, 2023. doi:10.1007/s13369-022-07009-8
16. [16] D. Stojanova, P. Panov, V. Gjorgjioski, A. Kobler and S. Džeroski, "Estimating vegetation height and canopy cover from remotely sensed data with machine learning," Ecological Informatics, vol. 5, no. 4, pp. 256–266, 2010. doi:10.1016/j.ecoinf.2010.03.004
17. [17] R. Eker, K. C. Alkiş, Z. Uçar and A. Aydın, “Ormancılıkta makine öğrenmesi kullanımı,” Turkish Journal of Forestry, vol. 24, no.2, pp. 150-177, 2023. doi:10.18182/tjf.1282768
18. [18] O. Alkan and R. Özçelik, "Toros göknarı için uyumlu hacim ve gövde çapı modelleri," Turkish Journal of Forestry, vol. 22, no. 4, pp.408–416, 2021. doi:10.18182/tjf.989732
19. [19] USGS, “Shuttle Radar Topography Mission (SRTM) Data Download,” United States Geological Survey, [Online]. Available: https://earthexplorer.usgs.gov. [Accessed: July. 26, 2023]
20. [20] IOBM, “Çandır Orman İşletme Şefliği 2021 yılı Orman Amenajman Planı,” Isparta Orman Bölge Müdürlüğü, Isparta, Türkiye, 2021.
21. [21] DJI, “Mavic Air User Manual,” [Online] Available: https://dl.djicdn.com/downloads. [Accessed: July. 15, 2023]
22. [22] B. Ruzgienė, T. Berteška, S. Gečyte, E. Jakubauskienė and V. C. Aksamitauskas, "The surface modelling based on UAV Photogrammetry and qualitative estimation," Measurement, vol. 73, pp. 619–627, 2015. doi:10.1016/j.measurement.2015.04.018
23. [23] C. Stöcker, F. Nex, M. Koeva and M. Gerke, "Quality assessment of combined IMU/GNSS data for direct georeferencing in the context of UAV-based mapping," The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 42, pp. 355–361, 2017. doi:10.5194/isprs-archives-XLII-2-W6-355-2017
24. [24] H. Durgun, H. O. Çoban and M. Eker, "İHA gorüntülerinin geometrik düzeltmesinin ağaç çap ve boy ölçümlerine etkileri,” in 5th International Conferences on Science and Technology, ICONST22, Budva, Montenegro, September 7-8, 2022.
25. [25] South, “Galaxy G6 measuring system user manual,” [Online] Available: https://globalgpssystems.com/wp content/uploads/2020/03/Galaxy-G6-Measuring-System-User-Manual.pdf. [Accessed: July. 18, 2023]
26. [26] ArcGIS, “ArcGIS,” [Online] Available: https://www.arcgis.com/index.html. [Accessed: July. 18, 2023].
27. [27] Microsoft “Microsoft,” [Online] Available: https://www.microsoft.com/tr-tr/microsoft-365. [Accessed: July. 18, 2023]
28. [28] Pix4d, “Pix4d,” [Online] Available: https://www.pix4d.com. [Accessed: July. 18, 2023]
29. [29] N. Snavely, S. Seitz and R. Szeliski, "Modeling the world from internet photo collections," International journal of computer vision, vol. 80, pp. 189–210, 2008. doi:10.1007/s11263-007-0107-3
30. [30] H. Durgun, “İnsansız hava aracıyla elde edilen hava fotoğraflarından kızılçam ağaçlarının çap ve boylarının ölçülmesi,” MSc. dissertation, Isparta Uygulamalı Bilimler Univ., Isparta, Türkiye, 2023.
31. [31] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of computer and system sciences, vol. 55 no. 1, pp. 119-139, 1997.
32. [32] L. Breiman, J. H. Friedman, R. A. Olshen and C. J. Stone, “Classification and regression trees,” CRC press, 1984.
33. [33] Y. Jiang, Y. Zhang, J. Tian and C. Zhou, “A comparative study of machine learning methods for predicting house prices,” Sustainability, vol. 13, no. 15, pp. 8233, 2021.
34. [34] R. M. Costa, M. F. Ribeiro, M. C. Fialho and J. M. C. Sousa, “A random forest classifier for medical diagnosis based on particle swarm optimization,” Computational and mathematical methods in medicine, 2020.
35. [35] J. Wu, W. Xu, C. Zeng, Y. Wang and J. Huang, “Support vector regression for predicting disease progression in breast cancer, BMC Bioinformatics, vol. 18, no. 1, pp. 365, 2017.
36. [36] J. Sequeira, M. Barandas, J. Neves and F. Silva, “Hybrid gradient boosting machine learning approach to predict photovoltaic energy production,” Energies, vol. 14, no. 3, pp. 630, 2021.
37. [37] K. Zhao, Y. Ma and J. Zhang, “XGBoost-based stock price forecasting in financial market,” Mathematical Problems in Engineering, 2019.
38. [38] Y. LeCun, Y. Bengio and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015.
39. [39] GridSearchCV, “Scikit-learn machine learning in python,” [Online] Available: https://scikitlearn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html. [Accessed: Aug. 10, 2023]
40. [40] C. Peng, “Developing ecoregion-based height-diameter models for jack pine and black spruce in Ontario. Sault Ste. Marie: Ontario,” Forest Research Institute, 2001.
41. [41] R. Özçelik, M. J. Diamantopoulou, F. Crecente-Campo and Ü. Eler, "Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models," Forest ecology and management, vol. 306, pp. 52–60, 2013. doi:10.1016/j.foreco.2013.06.009
42. [42] J. Castaño-Santamaría, F. Crecente-Campo, J. L. Fernández-Martínez, M. Barrio-Anta and J. R. Obeso, "Tree height prediction approaches for uneven-aged beech forests in northwestern Spain," Forest Ecology and Management, vol. 307, pp. 63–73, 2013. doi:10.1016/j.foreco.2013.07.014
43. [43] İ. Ercanlı, "Artificial intelligence with deep learning algorithms to model relationships between total tree height and diameter at breast height," Forest Systems, vol. 29, no. 2, pp. 13, 2020. doi:10.5424/fs/2020292-16393
44. [44] S. Long, S. Zeng, F. Liu and C. Wang, "Influence of slope, aspect and competition index on the height-diameter relationship of Cyclobalanopsis glauca trees for improving prediction of height in mixed forests," Silva Fennica, vol. 54, no. 1, 2020. doi:10.14214/sf.10242
45. [45] H. Durgun, H. O. Çoban and M. Eker, "İnsansız hava aracıyla elde edilen hava fotoğraflarından kızılçam ağaçlarının çap ve boylarının ölçümü ve gövde hacminin tahmini," Turkish Journal of Forestry, vol. 23, no. 4, pp. 255–267, 2022. doi:10.18182/tjf.1199567
46. [46] S. Carus and Y. Çatal, “Kızılçam (pinus brutia ten.) meşcerelerinde 7-ağaç örnek nokta yöntemiyle meşcere ağaç sayisinin çap basamaklarina dağiliminin belirlenmesi,” Turkish Journal of Forestry, vol. 9, no. 2, pp. 158-169, 2009. doi:10.18182-tjf.94714-195711
47. [47] Y. S. Lim, J. S. Park, M. W. Pyeon and J. Kim, “Calculation of tree height and canopy crown from drone images using segmentation,” Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, vol. 33, no. 6, pp. 605- 613, 2015. doi:10.7848/ksgpc.2015.33.6.605
48. [48] A. C. Birdal, “Ağaç Yüksekliklerinin Belirlenmesinde İnsansız Hava Araçlarının Kullanımı: Eskişehir Kent Ormanı Örneği,” MSc. dissertation, Anadolu Univ., Eskişehir, Türkiye, 2016.
49. [49] D. J. Kachamba, H. O. Orka, T. Gobakken, T. Eid and W. Mwase, “Biomass estimation using 3d data from unmanned aerial vehicle imagery in a tropical woodland,” Remote Sensing, vol. 8, no. 11, pp. 968, 2016. doi:10.3390/rs8110968
50. [50] M. Messinger, G. P. Asner and M. Silman, “Rapid assessments of amazon forest structure and biomass using small unmanned aerial systems,” Remote Sensing, vol. 8, no. 8, pp. 615, 2016. doi:10.3390/rs8080615
51. [51] B. Brede, K. Calders, A. Lau, P. Raumonen, H. M. Bartholomeus, M. Herold and L. Kooistra, “Non-destructive tree volume estimation through quantitative structure modelling: comparing UAV laser scanning with terrestrial lidar,” Remote Sensing of Environment, vol. 111355, pp. 233, 2019. doi:10.1016/j.rse.2019.111355
52. [52] X. Zhou, Y. He, H. Huang and X. Xu, “Estimation of forest stand volume on coniferous forest cutting area based on two periods unmanned aerial vehicle images,” Scientia Silvae Sinicae, vol. 55, no. 11, pp. 117-125, 2019. doi:10.11707/j.1001-7488.20191113
53. [53] L. Windrim, M. Bryson, M. McLean, J. Randle and C. Stone, “Automated mapping of woody debris over harvested forest plantations using uavs, highresolution imagery, and machine learning,” Remote Sensing, vol. 11, pp. 733, 2019. doi:10.3390/rs11060733
54. [54] G. Morales, G. Kemper, G. Sevillano, D. Arteaga, I. Ortega and J. Telles, “Automatic segmentation of Mauritia flexuosa in unmanned aerial vehicle (UAV) imagery using deep learning,” Forests, vol. 9, no. 12, pp. 736, 2018. doi:10.3390/f9120736
55. [55] S. Puliti, B. Talbot and R. Astrup, “Tree-stump detection, segmentation, classification, and measurement using unmanned aerial vehicle imagery,” Forests, vol. 9, pp. 102, 2018. doi:10.3390/f9030102
56. [56] S. S. Akay, O. Özcan, F. B. Şanlı, B. Bayram and T. Görüm, “İHA Görüntülerinden Üretilen Verilerin Doğruluk Değerlendirmesi,” X. Türkiye Ulusal Fotogrametri ve Uzaktan Algılama Birliği Teknik Sempozyumu, Nisan 25-27, Aksaray, Türkiye, 106-110, 2019.
57. [57] M. Akgül, H. Yurtseven, M. Demir, A. E. Akay, S. Gülci and T. Öztürk, “İnsansız hava araçları ile yüksek hassasiyette sayısal yükseklik modeli üretimi ve ormancılıkta kullanım olanakları,” Journal of the Faculty of Forestry Istanbul University, vol. 66, no. 1, pp. 104-118, 2016. doi:10.17099/jffiu.23976
58. [58] A. Navarro, M. Young, B. Allan, P. Carnell, P. Macreadie and D. Ierodiaconou, “The application of unmanned aerial vehicles (UAVs) to estimate above-ground biomass of mangrove ecosystems,” Remote Sensing of Environment, pp. 242, 2020. doi:10.1016/j.rse.2020.111747
59. [59] T. Liu, Y. Sun, C. Wang, Y. Zhang, Z. Qiu, W. Gong and X. Duan, “Unmanned aerial vehicle and artificial intelligence revolutionizing efficient and precision sustainable forest management,” Journal of Cleaner Production, pp. 311, 2021. doi:10.1016/j.jclepro.2021.127546
60. [60] B. Ruzgiene, T. Berteska, S. Gecyte, E. Jakubauskiene and V. C. Aksamitauskas, “The surface modelling based on UAV photogrammetry and qualitative estimation,” Measurement, vol. 73, pp. 619–627, 2015.
61. [61] C. Stöcker, F. Nex, M. Koeva and M. Gerke, “Quality assessment of combined IMU/GNSS data for direct georeferencing in the context of UAV-based mapping,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 42, pp. 355, 2017.
62. [62] H. S. Kapıcığolu, K. O. Hastaoğlu, F. Poyraz and Y. Gül, “Investigation of topographic effect in ground control point selection in uav photogrammetry: Gaziantep/Nizip,” International Conference on Innovative Engineering Applications, September 20-22, Sivas, Türkiye, 1174-1178, 2018.
63. [63] M. Rabah, M. Basiouny, E. Ghanem and A. Elhadary, “Using RTK and VRS in direct geo-referencing of the UAV imagery,” NRIAG Journal of Astronomy and Geophysics, vol. 7, no. 2, pp. 220-226, 2018. doi:10.1016/j.nrjag.2018.05.003
64. [64] S. S. Akay, O. Özcan, F. B. Şanlı, B. Bayram and T. Görüm, "İHA görüntülerinden üretilen verilerin doğruluk değerlendirmesi," in X. Türkiye Ulusal Fotogrametri ve Uzaktan Algılama Birliği Teknik Sempozyumu, pp. 25–27, 2019.
65. [65] S. Krause, T. G. Sanders, J. P. Mund and K. Greve, "UAV-based photogrammetric tree height measurement for intensive forest monitoring," Remote sensing, vol. 11, no. 7, pp. 758, 2019. doi:10.3390/rs11070758
66. [66] A. P. Dalla Corte, F. E. Rex, D. Almeida, C. R. Sanquetta, C. A. Silva, M. M. Moura and E. N. Broadbent, "Measuring individual tree diameter and height using GatorEye High-Density UAV-Lidar in an integrated crop-livestock-forest system," Remote Sensing, vol. 12, no. 5, pp. 863, 2020. doi:10.3390/rs12050863
67. [67] M. J. Allen, S. W. Grieve, H. J. Owen and E. R. Lines, “Tree species classification from complex laser scanning data in Mediterranean forests using deep learning,” Methods in Ecology and Evolution, vol. 14, no. 7, pp. 1657-1667, 2022. doi:10.1111/2041210X.13981
68. [68] S. Arjasakusuma, S. Swahyu Kusuma and S. Phinn, “Evaluating variable selection and machine learning algorithms for estimating forest heights by combining lidar and hyperspectral data,” ISPRS International Journal of Geo-Information, vol. 9, no. 9, pp. 507, 2020.
69. [69] M. Ataş and A. Talay, “Development of automatic tree counting software from UAV based aerial images with machine learning,”arxiv.org, Jan. 7, 2022. [Online]. Available: https://arxiv.org/abs/2201.02698. [Accessed: Sept. 16, 2023].