ARTIFICIAL NEURAL NETWORK MODELLING OF ABOVEGROUND BIOMASS FROM TROPICAL RAIN FORESTS IN NIGERIA
Keywords:
Aboveground Biomass, Neural Network, Regression, ReLU, RMSEAbstract
This study investigated the impact of applying artificial neural networks (ANNs) with different input variables and different architectures to estimate aboveground biomass (AGB) using allometric data from tropical forests in Southwestern Nigeria. The study also compared the result of ANNs with linear regression. Three fully connected feed-forward neural networks (all four-layer) with backpropagation of error were used in this study. They had two hidden layers: the first two had topography [2, 3, 3, 1], and the third had topography [3, 5, 5, 1]. Rectified Linear Unit (ReLU) activation function was used for all networks; Mean Squared Error (MSE) was used as the loss function. A learning rate of 1e-06 and 1000 iterations was used to run the first two ANNs, and a learning rate of 1e-06 and 1850 iterations was used to run the third. Maximum loss for each neural network was 12.8393, 12.0371, and 0.2078, respectively, while minimum loss was 0.0391, 0.0408, and 0.1559, respectively. Accuracy was measured using Root Mean Squared Error (RMSE) with the training for each neural network RMSE’s being 0.1997, 0.2113 and 0.3949 while test RMSE’s was 0.2199, 0.2284, and 0.3812 for each neural network.
References
Ali A, Xu MS, Zhao YT, Zhang QQ, Zhou LL, Yang XD, Yan ER 2015. Allometric biomass equations for shrub and small tree species in subtropical China. Silva Fennica 49:1–10. https://doi.org/10.14214/sf.1275
Baccini A, Walker W, Carvalho L, Farina M, Sulla-Menashe D, Houghton RA 2017. Tropical forests are a net carbon source based on aboveground measurements of gain and loss. Science 358:230–234. https://doi.org/10. 1126/science.aam5962
Bernacchi, C.J., Coleman, J.S., Bazzaz, F.A., McConnaughay, K.D.M. 2000. Biomass allocation in old-field annual species grown in elevated CO2 environments: no evidence for optimal partitioning. Global Change Biology 6(7): 855–863.
Chave J, Réjou-Méchain M, Búrquez A, Chidumayo E, Colgan MS, Delitti WB, Duque A, Eid T, Fearnside PM, Goodman RC, Henry M, Martinez-Yrizar A, Mugasha WA, Muller-Landau HC, Mencuccini M, Nelson BW, Ngomanda A, Nogueira EM, Ortiz-Malavassi E, Pelissier R, Ploton P, Ryan CM, Saldarriaga JG, Vieilledent G 2014. Improved allometric models to estimate the aboveground biomass of tropical trees. Global Change Biology 20:3177–3190. https://doi.org/10.1111/gcb.12629
Chave, J., Réjou-Méchain, M., Búrquez, A., Chidumayo, E., Colgan, M. S., Delitti, W. B. C., Vieilledent, G. 2014. Improved allometric models to estimate the aboveground biomass of tropical trees. Global Change Biology 20(10): 3177–3190. http://doi.org/10.1111/gcb.12629
Elzinga, C., Shearer, R. C., & Elzinga, G. 2005. Observer Variation in Tree Diameter Measurements. Western Journal of Applied Forestry 20(2): 134–137, https://doi.org/10.1093/wjaf/20.2.134
Fukushima, K. 1980. Neocognitron: A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position. Biological Cybernetics 36: 193 – 202.
Hunter, J. D. 2007. Matplotlib: A 2D graphics environment. Computing in Science & Engineering 9(3), 90–95. Doi:10.1109/MCSE.2007.55
Kumar L, Sinha P, Taylor S, Alqurashi AF 2015. Review of the use of remote sensing for biomass estimation to support renewable energy generation. Journal of Applied Remote Sensing 9:976-996
McKinney, W., & others. 2010. Data structures for statistical computing in python. In Proceedings of the 9th Python in Science Conference. 445, 51–56.
Nair, V., and Hilton, G. E. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. In Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel, 2010.
Oliphant, T. E. 2006. A guide to NumPy (Vol. 1). Trelgol Publishing USA.
Pan Y, Birdsey RA, Fang J, Houghton R, Kauppi PE, Kurz WA, Phillips OL, Shvidenko A, Lewis SL, Canadell JG, Ciais P, Jackson RB, Pacala SW, McGuire AD, Piao SL, Rautiainen A, Sitch S, Hayes D 2011. A large and persistent carbon sink in the world’s forests. Science, 333:988–993. https://doi.org/10.1126/science.1201609
Paul KI, Roxburgh SH, Chave J, England JR, Zerihun A, Specht A, Lewis T, Bennett LT, Baker TG, Adams MA, Huxtable D, Montagu KD, Falster DS, Feller M, Sochacki S, Ritson P, Bastin G, Bartle J, Inildy D, Hobbs T, Armour JL, Waterworth R, Stewart HTL, Jonsonf J, Forrester DI, Applegate G, Mendhan D, Bradford M, O'Grady A, Green D, Sudmeyer R, Rance SJ, Turner J, Barton C, Wenk EH, Grove T, Attiwill PM, Pinkard E, Butler D, Brooksbank K, Spencer B, Snowdon P, O'Brien N, Battaglia M, Cameron DM, Hamilton S, Mcauthur G, Sinclair A 2015. Testing the generality of above-ground biomass allometry across plant functional types at the continent scale. Global Change Biology 22:2106–2124
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12: 2825-2830.
Picard, N., Rutishauser, E., Ploton, P., Ngomanda, A., & Henry, M. 2015. Forest Ecology and Management Should tree biomass allometry be restricted to power models ? Forest Ecology and Management, 353, 156–163. https://doi.org/10.1016/j.foreco.2015.05.035
Rodríguez-Soalleiro R, Eimil-Fraga C, Gómez-García E, García-Villabrille JD, Rojo- Alboreca A, Muñoz F, Oliveira N, Sixto H, Pérez-Cruzado C 2018. Exploring the factors affecting carbon and nutrient concentrations in tree biomass components in natural forests, forest plantations and short rotation forestry. Forest Ecosystems, 5:35. https://doi.org/10.1186/s40663-018-0154-y
Schmidhuber, J. 2014. Deep Learning in Neural Networks: An Overview. Technical Report IDSIA-03-14 / arXiv:1404.7828 v4 [cs.NE].
Sileshi, G.W. 2014. A critical review of forest biomass estimation models, common mistakes and corrective measures. Forest Ecology and Management 329, 237–254.
Stevens, C.F. 2009. Darwin and Huxley revisited: the origin of allometry. Journal of Biology, 8 (2), PMC2687774.
Van Rossum, G., Drake, F. L. 2009. Python 3 Reference Manual. Scotts Valley, CA: CreateSpace.
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., van der Walt, S. J., Brett, M., Wilson, J., Jarrod Millman, K., Mayorov, N., Nelson, A. R.–J. Jones, E., Kern, R., Larson, E., Carey, C. J., Polat, I., Feng, Y., Moore, E. W., VanderPlas, J., Laxalde, D., Perktold, J., Cimrman, R., Henriksen, I., Quintero, E.–A. Harris, C. R., Archibald, A. M., Ribeiro, A.H., Pedregosa, F., van Mulbregt, Paul and SciPy 1.0 Contributors. 2020. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nature Methods 17, 261 – 272. Doi: 10.1038/s41592-019-0686-2
