nach oben

Earth Science Informatics

Erschienen in:

05.08.2022 | Research Article

Comparative analysis of machine learning algorithms and statistical models for predicting crown width of Larix olgensis

verfasst von: Siyu Qiu, Ruiting Liang, Yifu Wang, Mi Luo, Yujun Sun

Erschienen in: Earth Science Informatics | Ausgabe 4/2022

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Crown width is one of the most important crown dimensions that influence tree growth and survival. Accurate crown width prediction is vital for forest management. However, measuring crown width is time-consuming and labor-intensive, making it necessary to construct a convenient and accurate crown width prediction model. Nowadays, machine learning technologies have already been increasingly used to accurately predict tree growth, but there is still a lack of systematic and comprehensive comparison. This paper provided a comparative analysis of various machine learning methods (i.e., the Linear Regression, the Least Absolute Shrinkage and Selection Operator, the k-NearestNeighbors, the Random Forest, the Gradient Boosting Decision Tree, the Support Vector Regression, the Voting Regressor and the Multi-Layer Perceptron), simple crown width-diameter of breast height model, generalized crown width-diameter of breast height model and nonlinear mixed-effect crown width model for estimating the crown width of Larix olgensis in terms of the coefficient of determination, root mean squared error, mean absolute error, and mean absolute percentage error using hold-out validation and 10-fold cross-validation. The study showed that machine learning algorithms performed better than common nonlinear regression and nonlinear mixed-effect models. Specifically, the voting regressor and random forest algorithm yielded the highest prediction quality of crown width among the different models. In addition, from a practical point of view, the advantage of machine learning is that its implementation does not require crown width measurements. On the contrary, the calibration of the mixed-effect model requires prior information, which limits its use.

Vorheriger Artikel Identification of areas at the risk of landslide via the short-time Fourier transform

Nächster Artikel Evaluating different machine learning algorithms for snow water equivalent prediction

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Buchacher R, Ledermann T (2020) Interregional crown width models for individual trees growing in pure and mixed stands in Austria. Forests 11:114. https://doi.org/10.3390/f11010114CrossRef

Calama R, Montero G (2004) Interregional nonlinear height diameter model with random coefficients for stone pine in Spain. Can J For Res 34:150–163. https://doi.org/10.1139/x03-199CrossRef

Casas GG, Gonzáles DGE, Villanueva JRB, Fardin LP, Leite HG (2022) Configuration of the deep neural network Hyperparameters for the hypsometric modeling of the Guazuma crinita Mart. In the Peruvian Amazon. Forests 13:697. https://doi.org/10.3390/f13050697CrossRef

Cattaneo N, Schneider R, Bravo F, Bravo-Oviedo A (2020) Inter-specific competition of tree congeners induces changes in crown architecture in Mediterranean pine mixtures. For Ecol Manag 476. https://doi.org/10.1016/j.foreco.2020.118471

Che S, Tan X, Xiang C, Sun J, Hu X, Zhang X, Duan A, Zhang J (2019) Stand basal area modelling for Chinese fir plantations using an artificial neural network model. J For Res 30:1641–1649. https://doi.org/10.1007/s11676-018-0711-9CrossRef

Chen Q, Duan G, Liu Q, Ye Q, Sharma RP, Chen Y, Liu H, Fu L (2021) Estimating crown width in degraded forest: a two-level nonlinear mixed-effects crown width model for Dacrydium pierrei and Podocarpus imbricatus in tropical China. For Ecol Manag 497:119486. https://doi.org/10.1016/j.foreco.2021.119486CrossRef

de Oliveira Neto RR, Leite HG, Gleriani JM, Strimbu BM (2022) Estimation of Eucalyptus productivity using efficient artificial neural network. Eur J For Res 141:129–151. https://doi.org/10.1007/s10342-021-01431-7CrossRef

Diamantopoulou MJ (2005) Artificial neural networks as an alternative tool in pine bark volume estimation. Comput Electron Agr 48:235–244. https://doi.org/10.1016/j.compag.2005.04.002CrossRef

Diamantopoulou MJ, Milios E (2010) Modelling total volume of dominant pine trees in reforestations via multivariate analysis and artificial neural network models. Biosyst Eng 105:306–315. https://doi.org/10.1016/j.biosystemseng.2009.11.010CrossRef

Diamantopoulou MJ, Özçelik R, Yavuz H (2018) Tree-bark volume prediction via machine learning: a case study based on black alder’s tree-bark production. Comput Electron Agr 151:431–440. https://doi.org/10.1016/j.compag.2018.06.039CrossRef

Dong L, Zhang L, Li F (2018) Additive biomass equations based on different Dendrometric variables for two dominant species (Larix gmelini Rupr. And Betula platyphylla Suk.) in natural forests in the eastern Daxing’an mountains, Northeast China. Forests 9:261. https://doi.org/10.3390/f9050261CrossRef

Dong L, Wei H, Liu Z (2020) Optimizing Forest spatial structure with neighborhood-based indices: four case studies from Northeast China. Forests 11:413. https://doi.org/10.3390/f11040413CrossRef

Ercanlı İ (2020) Innovative deep learning artificial intelligence applications for predicting relationships between individual tree height and diameter at breast height. For Ecosyst 7:1–18. https://doi.org/10.1186/s40663-020-00226-3CrossRef

Fang Z, Bailey RL (2001) Nonlinear mixed effects modeling for slash pine dominant height growth following intensive Silvicultural treatments. For Sci 47:287–300

Fu L, Sun H, Sharma RP, Lei Y, Zhang H, Tang S (2013) Nonlinear mixed-effects crown width models for individual trees of Chinese fir (Cunninghamia lanceolata) in south-Central China. For Ecol Manag 302:210–220. https://doi.org/10.1016/j.foreco.2013.03.036CrossRef

Fu L, Sharma RP, Hao K, Tang S (2017a) A generalized interregional nonlinear mixed-effects crown width model for prince Rupprecht larch in northern China. For Ecol Manag 389:364–373. https://doi.org/10.1016/j.foreco.2016.12.034CrossRef

Fu LY, Sharma RP, Wang GX, Tang SZ (2017b) Modelling a system of nonlinear additive crown width models applying seemingly unrelated regression for prince Rupprecht larch in northern China. For Ecol Manag 386:71–80. https://doi.org/10.1016/j.foreco.2016.11.038CrossRef

Fu LY, Xiang W, Wang GX, Hao KJ, Tang SZ (2017c) Additive crown width models comprising nonlinear simultaneous equations for prince Rupprecht larch (Larix principis-rupprechtii) in northern China. Trees-Struct Funct 31:1959–1971. https://doi.org/10.1007/s00468-017-1600-0CrossRef

Gauthier R, Largouët C, Dourmad J-Y (2022) Prediction of litter performance in lactating sows using machine learning, for precision livestock farming. Comput Electron Agr 196:106876. https://doi.org/10.1016/j.compag.2022.106876CrossRef

Gill SJ, Biging GS, Murphy EC (2000) Modeling conifer tree crown radius and estimating canopy cover. For Ecol Manag 126:405–416. https://doi.org/10.1016/s0378-1127(99)00113-9CrossRef

Gonzalez-Benecke CA, Gezan SA, Samuelson LJ, Cropper WP, Leduc DJ, Martin TA (2014) Estimating Pinus palustris tree diameter and stem volume from tree height, crown area and stand-level parameters. J For Res 25:43–52. https://doi.org/10.1007/s11676-014-0427-4CrossRef

González-Rodríguez MA, Diéguez-Aranda U (2020) Exploring the use of learning techniques for relating the site index of radiata pine stands with climate, soil and physiography. For Ecol Manag 458. https://doi.org/10.1016/j.foreco.2019.117803

Görgens EB, Montaghi A, Rodriguez LCE (2015) A performance comparison of machine learning methods to estimate the fast-growing forest plantation yield based on laser scanning metrics. Comput Electron Agr 116:221–227. https://doi.org/10.1016/j.compag.2015.07.004CrossRef

Gray AN, McIntosh ACS, Garman SL, Shettles MA (2021) Predicting canopy cover of diverse forest types from individual tree measurements. For Ecol Manag 501:119682. https://doi.org/10.1016/j.foreco.2021.119682CrossRef

Grote R (2003) Estimation of crown radii and crown projection area from stem size and tree position. Ann For Sci 60:393–402. https://doi.org/10.1051/forest:2003031CrossRef

Güner ŞT, Diamantopoulou MJ, Poudel KP, Çömez A, Özçelik R (2022) Employing artificial neural network for effective biomass prediction: an alternative approach. Comput Electron Agr 192:106596. https://doi.org/10.1016/j.compag.2021.106596CrossRef

Hamidi SK, Weiskittel A, Bayat M, Fallah A (2021) Development of individual tree growth and yield model across multiple contrasting species using nonparametric and parametric methods in the Hyrcanian forests of northern Iran. Eur J For Res 140:421–434. https://doi.org/10.21203/rs.3.rs-72348/v1CrossRef

Hemery GE, Savill PS, Pryor SN (2005) Applications of the crown diameter–stem diameter relationship for different species of broadleaved trees. For Ecol Manag 215:285–294. https://doi.org/10.1016/j.foreco.2005.05.016CrossRef

Hetherington JC (1967) Crown diameter: stem diameter relationships in managed stands of Sitka spruce. Commonw For Rev 46:278–281

Hong H, Tsangaratos P, Ilia I, Liu J, Zhu AX, Xu C (2018) Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County. China Science of The Total Environment 630:1044–1056. https://doi.org/10.1016/j.scitotenv.2018.02.278CrossRef

Huy B, Truong NQ, Khiem NQ, Poudel KP, Temesgen H (2022) Deep learning models for improved reliability of tree aboveground biomass prediction in the tropical evergreen broadleaf forests. For Ecol Manag 508:120031. https://doi.org/10.1016/j.foreco.2022.120031CrossRef

Jevšenak J, Skudnik M (2021) A random forest model for basal area increment predictions from national forest inventory data. For Ecol Manag 479:118601. https://doi.org/10.1016/j.foreco.2020.118601CrossRef

Kalliovirta J, Tokola T (2005) Functions for estimating stem diameter and tree age using tree height, crown width and existing stand database information. Silva Fennica 39:227–248. https://doi.org/10.14214/sf.386CrossRef

Lei YK, Fu LY, Affleck DLR, Nelson AS, Shen CC, Wang MX, Zheng JB, Ye QL, Yang GW (2018) Additivity of nonlinear tree crown width models: aggregated and disaggregated model structures using nonlinear simultaneous equations. For Ecol Manag 427:372–382. https://doi.org/10.1016/j.foreco.2018.06.013CrossRef

Li Y, Wang W, Zeng W, Wang J, Meng J (2020) Development of crown ratio and height to Crown Base models for Masson pine in southern China. Forests 11:1216. https://doi.org/10.3390/f11111216CrossRef

Liang R, Sun Y, Zhou L, Wang Y, Qiu S, Sun Z (2022) Analysis of various crown variables on stem form for Cunninghamia lanceolata based on ANN and taper function. For Ecol Manag 507:119973. https://doi.org/10.1016/j.foreco.2021.119973CrossRef

Lindstrom ML, Bates DM (1990) Nonlinear mixed effects models for repeated measures data. Biometrics 46:673–687. https://doi.org/10.2307/2532087CrossRef

Liu ZL, Peng CH, Work T, Candau JN, DesRochers A, Kneeshaw D (2018) Application of machine-learning methods in forest ecology: recent progress and future challenges. Environ Rev 26:339–350. https://doi.org/10.1139/er-2018-0034CrossRef

Liu X, Hao YS, Widagdo FRA, Xie LF, Dong LH, Li FR (2021) Predicting height to Crown Base of Larix olgensis in Northeast China using UAV-LiDAR data and nonlinear mixed effects models. Remote Sens 13:1834. https://doi.org/10.3390/rs13091834CrossRef

Liu Y, Zhuang Y, Ji B, Zhang G, Rong L, Teng G, Wang C (2022) Prediction of laying hen house odor concentrations using machine learning models based on small sample data. Comput Electron Agr 195:106849. https://doi.org/10.1016/j.compag.2022.106849CrossRef

Madsen C, Kunz M, von Oheimb G, Hall J, Sinacore K, Turner BL, Potvin C (2021) Influence of neighbourhoods on the extent and compactness of tropical tree crowns and root systems. Trees-Struct Funct 1-14. https://doi.org/10.1007/s00468-021-02146-3

Miao Z, Widagdo FRA, Dong L, Li F (2021) Prediction of branch growth using quantile regression and mixed-effects models: an example with planted Larix olgensis Henry trees in Northeast China. For Ecol Manag 496:13. https://doi.org/10.1016/j.foreco.2021.119407CrossRef

Miranda EN, Barbosa BHG, Silva SHG, Monti CAU, Tng DYP, Gomide LR (2022) Variable selection for estimating individual tree height using genetic algorithm and random forest. For Ecol Manag 504:13. https://doi.org/10.1016/j.foreco.2021.119828CrossRef

Mohammed S, Elbeltagi A, Bashir B, Alsafadi K, Alsilibe F, Alsalman A, Zeraatpisheh M, Széles A, Harsányi E (2022) A comparative analysis of data mining techniques for agricultural and hydrological drought prediction in the eastern Mediterranean. Comput Electron Agr 197:106925. https://doi.org/10.1016/j.compag.2022.106925CrossRef

Ogana FN, Ercanli I (2021) Modelling height-diameter relationships in complex tropical rain forest ecosystems using deep learning algorithm. J For Res 33:883–898. https://doi.org/10.1007/s11676-021-01373-1CrossRef

Özçelik R, Diamantopoulou MJ, Crecente-Campo F, Eler U (2013) Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models. For Ecol Manag 306:52–60. https://doi.org/10.1016/j.foreco.2013.06.009CrossRef

Özçelik R, Diamantopoulou MJ, Trincado G (2019) Evaluation of potential modeling approaches for scots pine stem diameter prediction in North-Eastern Turkey. Comput Electron Agr 162:773–782. https://doi.org/10.1016/j.compag.2019.05.033CrossRef

Paine, D.P., Hann, D.W., 1982. Maximum crown-width equations for southwestern Oregon tree species

Pinheiro J, Bates D (2006) Mixed-effects models in S and S-PLUS. Springer Science & Business Media

Pretzsch H, Biber P, Uhl E, Dahlhausen J, Rötzer T, Caldentey J, Koike T, van Con T, Chavanne A, Seifert T, Toit BD, Farnden C, Pauleit S (2015) Crown size and growing space requirement of common tree species in urban centres, parks, and forests. Urban For Urban Green 14:466–479. https://doi.org/10.1016/j.ufug.2015.04.006CrossRef

Raptis D, Kazana V, Kazaklis A, Stamatiou C (2018) A crown width-diameter model for natural even-aged black pine Forest management. Forests 9:610. https://doi.org/10.3390/f9100610CrossRef

Raptis DI, Kazana V, Kazaklis A, Stamatiou C (2021) Mixed-effects height–diameter models for black pine (Pinus nigra Arn.) forest management. Trees 35:1167–1183. https://doi.org/10.1007/s00468-021-02106-xCrossRef

Raulier F, Lambert MC, Pothier D, Ung CH (2003) Impact of dominant tree dynamics on site index curves. For Ecol Manag 184:65–78. https://doi.org/10.1016/s0378-1127(03)00149-xCrossRef

Ruchay A, Kober V, Dorofeev K, Kolpakov V, Dzhulamanov K, Kalschikov V, Guo H (2022) Comparative analysis of machine learning algorithms for predicting live weight of Hereford cows. Comput Electron Agr 195:106837. https://doi.org/10.1016/j.compag.2022.106837CrossRef

Saud P, Lynch TB, KC A, Guldin JM (2016) Using quadratic mean diameter and relative spacing index to enhance height–diameter and crown ratio models fitted to longitudinal data. Forestry: An International Journal of Forest Research 89:215–229. https://doi.org/10.1093/forestry/cpw004CrossRef

Shamshirband S, Hashemi S, Salimi H, Samadianfard S, Asadi E, Shadkani S, Kargar K, Mosavi A, Nabipour N, Chau K-W (2020) Predicting standardized streamflow index for hydrological drought using machine learning models. Engineering Applications of Computational Fluid Mechanics 14:339–350. https://doi.org/10.1080/19942060.2020.1715844CrossRef

Sharma RP, Vacek Z, Vacek S (2016) Individual tree crown width models for Norway spruce and European beech in Czech Republic. For Ecol Manag 366:208–220. https://doi.org/10.1016/j.foreco.2016.01.040CrossRef

Sharma RP, Bílek L, Vacek Z, Vacek S (2017) Modelling crown width–diameter relationship for scots pine in the Central Europe. Trees 31:1875–1889. https://doi.org/10.1007/s00468-017-1593-8CrossRef

Skudnik M, Jevšenak J (2022) Artificial neural networks as an alternative method to nonlinear mixed-effects models for tree height predictions. For Ecol Manag 507:120017. https://doi.org/10.1016/j.foreco.2022.120017CrossRef

Thorpe HC, Astrup R, Trowbridge A, Coates KD (2010) Competition and tree crowns: a neighborhood analysis of three boreal tree species. For Ecol Manag 259:1586–1596. https://doi.org/10.1016/j.foreco.2010.01.035CrossRef

Tian Y, Wu B, Su X, Qi Y, Chen Y, Min Z (2020) A crown contour envelope model of Chinese fir based on random Forest and mathematical modeling. Forests 12. https://doi.org/10.3390/f12010048

Vospernik S, Monserud RA, Sterba H (2010) Do individual-tree growth models correctly represent height:diameter ratios of Norway spruce and scots pine? For Ecol Manag 260:1735–1753. https://doi.org/10.1016/j.foreco.2010.07.055CrossRef

Wang C-S, Guo J-J, Hein S, Wang H, Zhao Z-G, Zeng J (2019) Foliar morphology and spatial distribution in five-year-old plantations of Betula alnoides. For Ecol Manag 432:514–521. https://doi.org/10.1016/j.foreco.2018.09.052CrossRef

Wang WW, Ge FX, Hou ZY, Meng JH (2021a) Predicting crown width and length using nonlinear mixed-effects models: a test of competition measures using Chinese fir (Cunninghamia lanceolata (lamb.) hook.). Ann For Sci 78:1–17. https://doi.org/10.1007/s13595-021-01092-xCrossRef

Wang Z, Zhang X, Chhin S, Zhang J, Duan A (2021b) Disentangling the effects of stand and climatic variables on forest productivity of Chinese fir plantations in subtropical China using a random forest algorithm. Agric For Meteorol 304-305:108412. https://doi.org/10.1016/j.agrformet.2021.108412CrossRef

West PW, Ratkowsky DA, Davis AW (1984) Problems of hypothesis testing of regressions with multiple measurements from individual sampling units. For Ecol Manag 7:207–224. https://doi.org/10.1016/0378-1127(84)90068-9CrossRef

Wonn HT, O'Hara KL (2001) Height:diameter ratios and stability relationships for four northern Rocky Mountain tree species. West J Appl For 16:87–94. https://doi.org/10.1093/wjaf/16.2.87CrossRef

Xie LF, Fu LY, Widagdo FRA, Dong LH, Li FR (2021) Improving the accuracy of tree biomass estimations for three coniferous tree species in Northeast China. Trees-Struct Funct 36:451–469. https://doi.org/10.1007/s00468-021-02220-wCrossRef

Xu Q, Lei X, Zhang H (2022) A novel method for approaching the compatibility of tree biomass estimation by multi-task neural networks. For Ecol Manag 508:120011. https://doi.org/10.1016/j.foreco.2022.120011CrossRef

Yang YQ, Huang SM, Meng SX, Trincado G, VanderSchaaf CL (2009) A multilevel individual tree basal area increment model for aspen in boreal mixedwood stands. Canadian Journal of Forest Research-Revue Canadienne De Recherche Forestiere 39:2203–2214. https://doi.org/10.1139/x09-123CrossRef

Zhang H, Zhou X, Gu W, Wang L, Li W, Gao Y, Wu L, Guo X, Tigabu M, Xia D, Chiang VL, Yang C, Zhao X (2021) Genetic stability of Larix olgensis provenances planted in different sites in Northeast China. For Ecol Manag 485:118988. https://doi.org/10.1016/j.foreco.2021.118988CrossRef

Titel: Comparative analysis of machine learning algorithms and statistical models for predicting crown width of Larix olgensis
verfasst von: Siyu Qiu
Ruiting Liang
Yifu Wang
Mi Luo
Yujun Sun
Publikationsdatum: 05.08.2022
Verlag: Springer Berlin Heidelberg
Erschienen in: Earth Science Informatics / Ausgabe 4/2022
Print ISSN: 1865-0473
Elektronische ISSN: 1865-0481
DOI: https://doi.org/10.1007/s12145-022-00854-z

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Weitere Artikel der Ausgabe 4/2022

Non-linear magnetoconvection in a bidispersive porous layer: a brinkman model

Mapping of groundwater potential zones in Pohru Watershed of Jhelum Basin-Western Himalaya, India using integrated approach of remote sensing, GIS and AHP

Prediction of thermal conductivity of granitic rock: an application of arithmetic and salp swarm algorithms optimized ANN

Estimation of the amplification properties of soil through HVSR inversion based on an elitist genetic algorithm

Analysis of rate of penetration prediction in drilling using data-driven models based on weight on hook measurement

Comparative assessment of satellite images spectral characteristics in identifying the different levels of soil salinization using machine learning techniques in Google Earth Engine

Premium Partner