J. For. Sci., 2024, 70(5):209-222 | DOI: 10.17221/111/2023-JFS

Sensitivity analysis and performance evaluation of neural networks for predicting forest stand volume – A case study: District 2, Kacha, Guilan province, IranOriginal Paper

Sima Lotfi Asl1, Iraj Hassanzad Navroodi2, Aman Mohammad Kalteh3
1 Department of Forestry, University Campus, University of Guilan, Rasht, Iran
2 Department of Forestry, Faculty of Natural Resources, University of Guilan, Sowmehsara, Iran
3 Department of Rang and Watershed Management, Faculty of Natural Resources, University of Guilan, Sowmehsara, Iran

Tree volume is a characteristic used in many cases, such as determining fertility, habitat quality, growth size, allowable harvesting, and the principles of forest trade. It is imperative to develop methods that predict forest stand volume to obtain this extensive information quickly and cost-effectively. This study used supervised self-organising map (SSOM), multi-layer perceptron (MLP), and radial basis function (RBF) neural networks to predict forest stand volume based on physiography, topography, soil, and human factors. A sensitivity analysis method called the importance of prediction was used to determine how input variables influenced network output. First, the map of homogeneous units was prepared with ArcMap (Version 10.3.1, 2015) by combining digital layers to measure the tree's volume per hectare. Then, separate tree species in different diameter classes were measured in a circular grid of 200 m × 150 m, 0.1 ha of coverage, 3.3% sampling intensity, and a diameter at breast height (DBH) greater than 7.5 cm using systematic sampling on a homogeneous unit map in a regular random method. The neural network modelling results showed that SSOM, MLP, and RBF predicted forest stand volume most accurately according to physiography, topography, soil, and human factors. Furthermore, the sensitivity analysis results found that altitude above sea level, soil depth, and slope are the most influential input variables. In contrast, soil texture variables are the least effective at predicting forest stand volume.

Keywords: best matching unit; error back-propagation; importance of prediction neighbour function; spread; supervised learning

Received: October 14, 2023; Revised: February 23, 2024; Accepted: February 26, 2024; Prepublished online: May 6, 2024; Published: May 24, 2024  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Lotfi Asl S, Navroodi IH, Kalteh AM. Sensitivity analysis and performance evaluation of neural networks for predicting forest stand volume – A case study: District 2, Kacha, Guilan province, Iran. J. For. Sci. 2024;70(5):209-222. doi: 10.17221/111/2023-JFS.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Abadi M., Barham P., Chen J., Chen Z.F., Davis A., Dean J., Devin M., Ghemawat S., Irving G., Isard M., Kudlur M., Levenberg J., Monga R., Moore S., Murray D.G., Steiner B., Tucker P., Vasudevan V., Warden P., Wicke M., Yu Y., Zheng X., Brain G. (2016): TensorFlow: A system for large-scale machine learning. 12th USENIX Conference on Operating Systems Design and Implementation, Savannah, Nov 2-4, 2016: 265-283.
    2. Ahmadian A.S. (2015): Numerical modeling and simulation. In: Ahmadian A.S (ed.): Numerical Models for Submerged Breakwaters. Amsterdam, Elsevier: 109-126. Go to original source...
    3. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology (2000): Artificial neural networks in hydrology I: Preliminary concepts. Journal of Hydrologic Engineering, 5: 115-123. Go to original source...
    4. Bayat M., Namiranian M., Omid M., Rashidi A., Babaei S. (2016): Applicability of artificial neural network for estimating the forest growing stock. Iranian Journal of Forest and Poplar Research, 24: 214-226. (in Persian)
    5. Bayat M., Bettinger P., Heidari S., Henareh Khalyani A., Jourgholami M., Hamidi S.K. (2020): Estimation of tree heights in an uneven-aged, mixed forest in northern Iran using artificial intelligence and empirical models. Forests, 11: 324. Go to original source...
    6. Belgiu M., Drãguþ L. (2016): Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114: 24-31. Go to original source...
    7. Bonèina A., Èavloviæ J. (2009): Perspectives of forest management planning: Slovenian and Croatian experience. Croatian Journal of Forest Engineering, 30: 77-87.
    8. Chen J., Zhang M. (2014): Advances in machine learning applications in remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 93: 1-2. Go to original source...
    9. Coulson R.N., Folse L.J., Loh D.K. (1987): Artificial intelligence and natural resource management. Science, 237: 262-267. Go to original source... Go to PubMed...
    10. Daghestani M., Zanganeh M., Taheri M. (2017): Investigation on quantitative characteristic and soil properties of Juniperus excelsa M. Bieb stands in Tarom Zanjan. Journal of Forest Research and Development, 3: 175-190. (in Persian)
    11. De R.K., Pal N.R., Pal S.K. (1997): Feature analysis: Neural network and fuzzy set theoretic approaches. Pattern Recognition, 30: 1579-1590. Go to original source...
    12. Dinghofer K., Hartung F. (2020): Analysis of criteria for the selection of machine learning frameworks. International Conference on Computing, Networking and Communications (ICNC), Big Island, Feb 17-20, 2020: 373-377. Go to original source...
    13. Ercanli I., Günlü A., ªenyurt M., Keleº S. (2018): Artificial neural network models predicting the leaf area index: A case study in pure even-aged Crimean pine forests from Turkey. Forest Ecosystems, 5: 1-12. Go to original source...
    14. Fernando D.A.K., Jayawardena A.W. (1998): Runoff forecasting using RBF networks with OLS algorithm. Journal of Hydrologic Engineering, 3: 203-209. Go to original source...
    15. Ferraz Filho A.C.; Mola-Yudego B.; Ribeiro A.; Scolforo J.R.S., Loos R.A., Scolforo H.F. (2018): Height-diameter models for Eucalyptus sp. plantations in Brazil. Cerne, 24: 9-17. Go to original source...
    16. Gebreslasie M.T., Ahmed F.B., Van Aardt J.A.N. (2010): Predicting forest structural attributes using ancillary data and ASTER satellite data. International Journal of Applied Earth Observation and Geoinformation, 12: S23-S26. Go to original source...
    17. Gil D., Johnsson M. (2010): Supervised SOM based architecture versus Multilayer Perceptron and RBF networks. Expert Systems with Applications, 37: 4713-4718. Go to original source...
    18. Haykin S. (1999): Neural Networks: A Comprehensive Foundation. Upper Saddle River, Prentice Hall: 842.
    19. Hu Y., Xu X., Wu F., Sun Z., Xia H., Meng Q., Huang W., Zhou H., Gao J., Li W., Peng D., Xiao X. (2020): Estimating forest stock volume in Hunan province, China, by integrating in situ plot data, Sentinel-2 images, and linear and machine learning regression models. Remote Sensing, 12: 2-23. Go to original source...
    20. Kalteh A.M., Hjorth P. (2008): Imputation of missing values in precipitation-runoff process database. Hydrology Research, 40: 420-432. Go to original source...
    21. Kalteh A.M., Hjorth P., Berndtsson R. (2008): Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application. Environmental Modelling and Software, 23: 835-845. Go to original source...
    22. Keller S., Maier P.M., Riese F.M., Norra S., Holbach A., Börsig N., Wilhelms A., Moldaenke C., Zaake A., Hinz S. (2018): Hyperspectral data and machine learning for estimating CDOM, chlorophyll a, diatoms, green algae, and turbidity. International Journal of Environmental Research and Public Health, 15: 1-15. Go to original source... Go to PubMed...
    23. Klippel L., Krusic P.J., Brandes R., Hartl-Meier C., Trouet V., Meko M., Esper J. (2017): High-elevation inter-site differences in Mount Smolikas tree-ring width data. Dendrochronologia, 44: 164-173. Go to original source...
    24. Klobucar D., Subasic M. (2012): Using self-organizing map in the visualization and analysis of forest inventory. iForest - Biogeosciences and Forestry, 5: 216-223. Go to original source...
    25. Kohonen T. (1982): Analysis of a simple self-organizing process. Biological Cybernetics, 44: 135-140. Go to original source...
    26. Lacerda T.H.S., Cabacinha C.D., Araújo Júnior C.A.A., Maia R.D., Lacerda K.W.S. (2017): Artificial neural networks for estimating tree volume in the Brazilian savanna. Cerne, 23: 483-491. Go to original source...
    27. Liu Z., Peng C., Work T., Candau J.N., Desrochers A., Kneeshaw D. (2018): Application of machine learning methods in forest ecology: Recent progress and future challenges. Environmental Reviews, 26: 339-350. Go to original source...
    28. Marvie Mohadjer M.R. (2006): Silviculture. Tehran, University of Tehran: 387.
    29. Mohammadi J., Joibary S.S., Yaghmaee F., Mahiny A.S. (2010): Modelling forest stand volume and tree density using Landsat ETM+ data. International Journal of Remote Sensing, 31: 2959-2975. Go to original source...
    30. Natural Resources and Watershed Management Organization (2008): Revision Plan of District 2, Kacha, Guilan, Rasht. Tehran, Forestry Technical Office: 365.
    31. Özçelik R., Diamantopoulou M.J., Brooks J.R. (2017): The use of tree crown variables in over-bark diameter and volume prediction models. iForest - Biogeosciences Forestry, 7: 132-139. Go to original source...
    32. Peng C., Wen X. (1999): Recent application of artificial neural networks in forest resource management: An overview. In: Cortés U., Sànchez-Marrè M. (eds): Proceedings of the Meeting Environmental Decision Support Systems and Artificial Intelligence. Orlando, AAAI Press: 15-22.
    33. Pokhariyal S., Patel N.R., Govind A. (2023): Machine learning-driven remote sensing applications for agriculture in India - A systematic review. Agronomy, 13: 1-30. Go to original source...
    34. Riese F.M., Keller S., Hinz S. (2020): Supervised and semi-supervised self-organizing maps for regression and classification focusing on hyperspectral data. Remote Sensing, 12: 1-23. Go to original source...
    35. Ronoud G., Darvish Sefat A.A., Fatehi P. (2019): Beech tree density estimation using Sentinel-2 data (Case study: Khyroud forest). SPRS International GeoSpatial Conference, Karaj, Oct 12-14, 2019: 891-895. Go to original source...
    36. Saltelli A., Tarantola S., Campolongo F., Ratto M. (2004): Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models. New York, Halsted Press: 466.
    37. Saltelli A., Ratto M., Andres T., Campolongo F., Cariboni J., Gatelli D., Saisana M., Tarantola S. (2008): Global Sensitivity Analysis: The Primer. Chichester, Wiley Online Library: 291. Go to original source...
    38. Sefidi K., Firouzi Y., Keivan Behju F., Sharari M., Rostamikia Y. (2018): Quantification of spatial structure of juniper stands in Kandaragh region. Iranian Journal of Forest, 10: 207-220. (in Persian)
    39. Stümer W., Kenter B., Köhl M. (2010): Spatial interpolation of in situ data by self-organizing map algorithms (neural networks) for the assessment of carbon stocks in European forests. Forest Ecology and Management, 260: 287-293. Go to original source...
    40. Wyman M.S., Stein T.V. (2010): Modeling social and land-use/land-cover change data to assess drivers of smallholder deforestation in Belize. Applied Geography, 30: 329-342. Go to original source...
    41. Zhang Z.H., Hu G., Ni J. (2013): Effects of topographical and edaphic factors on the distribution of plant communities in two subtropical karst forests, southwestern China. Journal of Mountain Science, 10: 95-104. Go to original source...
    42. Zobeiry M. (2005): Forest Inventory (Measurement of Tree and Stand). 3rd Ed. Tehran, University of Tehran Press: 308. (in Persian)

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content