Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network
Relationship of total height and diameter at breast height (hereafter diameter) of the trees is generally nonlinear, and therefore has complex characteristics, which can be accurately described by the height-diameter model developed using the back propagation (BP) neural network approach. The multip...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/11/4/442 |
| _version_ | 1797570682323730432 |
|---|---|
| author | Jianbo Shen Zongda Hu Ram P. Sharma Gongming Wang Xiang Meng Mengxi Wang Qiulai Wang Liyong Fu |
| author_facet | Jianbo Shen Zongda Hu Ram P. Sharma Gongming Wang Xiang Meng Mengxi Wang Qiulai Wang Liyong Fu |
| author_sort | Jianbo Shen |
| collection | DOAJ |
| description | Relationship of total height and diameter at breast height (hereafter diameter) of the trees is generally nonlinear, and therefore has complex characteristics, which can be accurately described by the height-diameter model developed using the back propagation (BP) neural network approach. The multiple hidden layered-BP neural network has several hidden layers and neurons, and is therefore considered more appropriate modeling approach compared to the single hidden layered-BP neural network approach. However, the former approach is not widely applied for tree height prediction due to absence of the effective optimization method, but it can be done using the BP neural network modeling approach. The poplar (<i>Populus</i> spp. L.) plantation data acquired from Guangdong province of China were used for evaluating the BP neural network modeling approach and compared its results with those obtained from the traditional regression modeling and mixed-effects modeling approaches. We determined the best BP neural network structure with two hidden layers and five neurons in each layer, and logistic sigmoid transfer functions. Relative to the Mitscherlich height-diameter model that had the highest fitting precision among the six traditional height-diameter models evaluated, coefficient of determination (<i>R<sup>2</sup></i>) of the neural network height-diameter model increased by 10.3%, root mean squares error (RMSE) and mean absolute error (MAE) decreased by 12% and 13.5%, respectively. The BP neural network height-diameter model also appeared more accurate than the mixed-effects height-diameter model. Our study proposes the method of determining the optimal numbers of hidden layers, neurons of each layer, and transfer functions in the BP neural network structure. This method can be useful for other modeling studies of similar or different types, such as tree crown modeling, height, and diameter increments modeling, and so on. |
| first_indexed | 2024-03-10T20:29:28Z |
| format | Article |
| id | doaj.art-e03e4f4a768145deb5796ceada5f30ce |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-10T20:29:28Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-e03e4f4a768145deb5796ceada5f30ce2023-11-19T21:34:42ZengMDPI AGForests1999-49072020-04-0111444210.3390/f11040442Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural NetworkJianbo Shen0Zongda Hu1Ram P. Sharma2Gongming Wang3Xiang Meng4Mengxi Wang5Qiulai Wang6Liyong Fu7Academy of Agricultural Planning and Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100125, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu 611130, ChinaInstitute of Forestry, Tribhuwan University, Kritipur, Kathmandu 44600, NepalInstitute of Biophysics, Chinese Academy of Sciences, Beijing 100101, ChinaResearch Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaResearch Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaForestry Surveying and Designing Institute of Guangdong Province, Guangzhou 510520, ChinaResearch Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaRelationship of total height and diameter at breast height (hereafter diameter) of the trees is generally nonlinear, and therefore has complex characteristics, which can be accurately described by the height-diameter model developed using the back propagation (BP) neural network approach. The multiple hidden layered-BP neural network has several hidden layers and neurons, and is therefore considered more appropriate modeling approach compared to the single hidden layered-BP neural network approach. However, the former approach is not widely applied for tree height prediction due to absence of the effective optimization method, but it can be done using the BP neural network modeling approach. The poplar (<i>Populus</i> spp. L.) plantation data acquired from Guangdong province of China were used for evaluating the BP neural network modeling approach and compared its results with those obtained from the traditional regression modeling and mixed-effects modeling approaches. We determined the best BP neural network structure with two hidden layers and five neurons in each layer, and logistic sigmoid transfer functions. Relative to the Mitscherlich height-diameter model that had the highest fitting precision among the six traditional height-diameter models evaluated, coefficient of determination (<i>R<sup>2</sup></i>) of the neural network height-diameter model increased by 10.3%, root mean squares error (RMSE) and mean absolute error (MAE) decreased by 12% and 13.5%, respectively. The BP neural network height-diameter model also appeared more accurate than the mixed-effects height-diameter model. Our study proposes the method of determining the optimal numbers of hidden layers, neurons of each layer, and transfer functions in the BP neural network structure. This method can be useful for other modeling studies of similar or different types, such as tree crown modeling, height, and diameter increments modeling, and so on.https://www.mdpi.com/1999-4907/11/4/442Levenberg–Marquardt algorithm<i>k</i>-fold cross-validationtraditional height-diameter functionsmixed-effects modeloptimal neural network height-diameter model |
| spellingShingle | Jianbo Shen Zongda Hu Ram P. Sharma Gongming Wang Xiang Meng Mengxi Wang Qiulai Wang Liyong Fu Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network Forests Levenberg–Marquardt algorithm <i>k</i>-fold cross-validation traditional height-diameter functions mixed-effects model optimal neural network height-diameter model |
| title | Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network |
| title_full | Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network |
| title_fullStr | Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network |
| title_full_unstemmed | Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network |
| title_short | Modeling Height–Diameter Relationship for Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back Propagation Neural Network |
| title_sort | modeling height diameter relationship for poplar plantations using combined optimization multiple hidden layer back propagation neural network |
| topic | Levenberg–Marquardt algorithm <i>k</i>-fold cross-validation traditional height-diameter functions mixed-effects model optimal neural network height-diameter model |
| url | https://www.mdpi.com/1999-4907/11/4/442 |
| work_keys_str_mv | AT jianboshen modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT zongdahu modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT rampsharma modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT gongmingwang modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT xiangmeng modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT mengxiwang modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT qiulaiwang modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork AT liyongfu modelingheightdiameterrelationshipforpoplarplantationsusingcombinedoptimizationmultiplehiddenlayerbackpropagationneuralnetwork |