Optimization path of landscape architectural design based on PCA-SSA-BP algorithm
DOI: https://doi.org/10.3846/jeelm.2026.28338Abstract
With the acceleration of urbanization, the importance of landscape architecture design in improving the quality of urban ecological environment and the quality of life of residents is becoming more and more prominent. To enhance the scientificity and practicability of the landscape design scheme, the study uses principal component analysis to downscale the multidimensional data of landscape architecture. It also combines Sparrow Search Algorithm (SSA) to optimize the initial weights and biases of Back Propagation (BP) neural network, so as to realize the accurate evaluation and adjustment of the design scheme. Meanwhile, the performance of the algorithm is verified on the Garden Buildings and WHU Building datasets. The experimental results showed that the mean square error of the BP neural network optimized by the sparrow algorithm was 0.1228, and the mean absolute error was 0.2321. Meanwhile, the accuracy and recall rate of this algorithm after convergence were significantly higher than those of PSO-BP, GA-BP and BP, with values of 0.946 and 0.951, respectively. In addition, the algorithm performed well in terms of vegetative coverage enhancement, space utilization improvement, and visitor experience enhancement. After the specific optimization of this algorithm, the vegetation coverage rate increased by 14.5%, and the space utilization rate increased by 13.2% and 14.8%, respectively. The findings demonstrate that the sparrow algorithm-optimized BP neural network can efficiently handle complicated multidimensional data, optimize the landscape design scheme, and improve user experience and ecological value. The study provides a scientific, efficient and data-driven optimization method for landscape architecture design, which helps to promote the digital transformation and sustainable development of the landscape design industry.
Keywords:
PCA-SSA-BP, landscape architectural design, data dimensionality reduction, L2 regularization, performance evaluationHow to Cite
Share
License
Copyright (c) 2026 The Author(s). Published by Vilnius Gediminas Technical University.
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Ahmadi, M., Sharifi, A., Jafarian Fard, M., & Soleimani, N. (2023). Detection of brain lesion location in MRI images using convolutional neural network and robust PCA. International Journal of Neuroscience, 133(1), 55–66. https://doi.org/10.1080/00207454.2021.1883602
Ardhianto, P., Santosa, Y. P., Moniaga, C., Utami, M. P., Dewi, C., Christanto, H. J., & Chen, A. P. S. (2023). Generative deep learning for visual animation in landscapes design. Scientific Programming, Article 9443704. https://doi.org/10.1155/2023/9443704
Chen, J., & Stouffs, R. (2023). Deciphering the noisy landscape: Architectural conceptual design space interpretation using disentangled representation learning. Computer‐Aided Civil and Infrastructure Engineering, 38(5), 601–620. https://doi.org/10.1111/mice.12908
Chen, X. (2023). Environmental landscape design and planning system based on computer vision and deep learning. Journal of Intelligent Systems, 32(1), Article 20220092. https://doi.org/10.1515/jisys-2022-0092
Chu, J., Wang, Z., Bao, X., Yao, Z., & Cui, X. (2026). Addressing the contradiction between water supply and demand: A study on multi-objective regional water resources optimization allocation. Environment, Development and Sustainability, 28, 11289–11317. https://doi.org/10.1007/s10668-024-05214-z
Cui, B., & Wang, S. (2025). Interactive park landscape environment design by incorporating improved SOM algorithm. Journal of Advanced Computational Intelligence and Intelligent Informatics, 29(2), 241–255. https://doi.org/10.20965/jaciii.2025.p0241
Fernberg, P., & Chamberlain, B. (2023). Artificial intelligence in landscape architecture: A literature review. Landscape Journal, 42(1), 13–35. https://doi.org/10.3368/lj.42.1.13
Freschlin, C. R., Fahlberg, S. A., Heinzelman, P., & Romero, P. A. (2024). Neural network extrapolation to distant regions of the protein fitness landscape. Nature Communications, 15, Article 6405. https://doi.org/10.1038/s41467-024-50712-3
Gao, Y., Wang, N., & Ma, Y. (2023). L2-SSA-LSTM prediction model of steering drilling wellbore trajectory. IEEE Access, 12(4), 450–461. https://doi.org/10.1109/ACCESS.2023.3347611
Goodarzi, P., Ansari, M., Rahimian, F. P., Mahdavinejad, M., & Park, C. (2023). Incorporating sparse model machine learning in designing cultural heritage landscapes. Automation in Construction, 155, Article 105058. https://doi.org/10.1016/j.autcon.2023.105058
Groumpos, P. P. (2023). A critical historic overview of artificial intelligence: Issues, challenges, opportunities, and threats. Artificial Intelligence and Applications, 1(4), 181–197. https://doi.org/10.47852/bonviewAIA3202689
Guo, J., Xi, W., Yang, Z., Shi, Z., Huang, G., Yang, Z., & Yang, D. (2024). Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm: A case study of Baihetan Reservoir Area. Journal of Mountain Science, 21, 952–972. https://doi.org/10.1007/s11629-023-8083-9
Hong, S., Shen, J., Lü, G., Liu, X., Mao, Y., Sun, N., & Tang, L. (2023). Aesthetic style transferring method based on deep neural network between Chinese landscape painting and classical private garden’s virtual scenario. International Journal of Digital Earth, 16(1), 1491–1509. https://doi.org/10.1080/17538947.2023.2202422
Li, M., Gu, Y., Ge, S., Zhang, Y., Mou, C., Zhu, H., & Wei, G. (2023). Classification and identification of mixed gases based on the combination of semiconductor sensor array with SSA-BP neural network. Measurement Science and Technology, 34, Article 085110. https://doi.org/10.1088/1361-6501/acd0cb
Liu, Y., Fan, L., & Wang, L. (2024). Urban virtual environment landscape design and system based on PSO-BP neural network. Scientific Reports, 14, Article 13747. https://doi.org/10.1038/s41598-024-64296-x
Liu, Z., Yu, H., & Jin, W. (2023). Adaptive leakage protection for low-voltage distribution systems based on SSA-BP neural network. Applied Sciences, 13(16), Article 9273. https://doi.org/10.3390/app13169273
Wang, J., Zeng, G., Xu, M., Wan, X., Wang, K., Mou, J., Hua, C., Fan, C., & Han, P. (2024). SSA‐BP neural network model for predicting rice‐fish production in China. Journal of Applied Ichthyology, Article 5739961. https://doi.org/10.1155/2024/5739961
Wu, S., Cao, L., Xu D., & Zhao, C. (2023). Historical eco-environmental quality mapping in China with multi-source data fusion. Applied Sciences, 13(14), Article 8051. https://doi.org/10.3390/app13148051
Yang, Z., Li, B., Wu, H., Li, M. H., Fan, J., Chen, M., & Long, J. (2023). Water consumption prediction and influencing factor analysis based on PCA-BP neural network in karst regions: A case study of Guizhou Province. Environmental Science and Pollution Research, 30, 33504–33515. https://doi.org/10.1007/s11356-022-24604-2
Yang, M., Zhuang, J., & Wang, M. (2025). Leveraging recurrent neural networks for lithology identification and Chinese rural landscape planning in sustainable design. Sustainability, 17(7), Article 3078. https://doi.org/10.3390/su17073078
You, K., Qiu, G., & Gu, Y. (2023). An efficient lightweight neural network using BiLSTM-SCN-CBAM with PCA-ICEEMDAN for diagnosing rolling bearing faults. Measurement Science and Technology, 34(9), Article 094001. https://doi.org/10.1088/1361-6501/acd5ef
Zhang, K., Chen, Z., Yang, L., & Liang, Y. (2023). Principal component analysis (PCA) based sparrow search algorithm (SSA) for optimal learning vector quantized (LVQ) neural network for mechanical fault diagnosis of high voltage circuit breakers. Energy Reports, 9(S1), 954–962. https://doi.org/10.1016/j.egyr.2022.11.118
Zheng, Y., Li, L., Qian, L., Cheng, B., Hou, W., & Zhuang, Y. (2023). Sine-SSA-BP ship trajectory prediction based on chaotic mapping improved sparrow search algorithm. Sensors, 23(2), Article 704. https://doi.org/10.3390/s23020704
View article in other formats
CrossMark check
Published
Issue
Section
Copyright
Copyright (c) 2026 The Author(s). Published by Vilnius Gediminas Technical University.
License
This work is licensed under a Creative Commons Attribution 4.0 International License.