|
|
基于响应面法和机器学习算法分析不同条件下微藻生长影响的研究
|
Abstract:
目前随着人工智能的快速发展，机器学习已经广泛应用于各个领域，并对实验中获得的小数据进行模拟分析。本研究以微藻为基础，利用收集的9组文献中对微藻的研究结果为数据，使用四种算法，即BP神经网络、支持向量机、随机森林和径向基函数神经网络，使用MATLAB软件进行建模和分析，与原文献中的响应面分析法进行对比，得出以下主要结论：通过比较相对系数(R2)、平均绝对误差(MAE)、平均偏差误差(MBE)、均方根误差(RMSE)和均方误差(MSE)，相比于传统的响应面分析法，机器学习算法表现出更好的预测效果，其中随机森林和径向基函数神经网络的相对系数最接近于1，预测效果最好，其次是BP神经网络和支持向量机。
Currently, with the rapid development of artificial intelligence, machine learning has been widely applied in various fields and used to simulate and analyze small data obtained from experiments. This study based on microalgae and using the collected 9 groups of microalgae research results in the literature for the data, using four kinds of algorithms, namely, the BP neural network, support vector machine (SVM), random forests (RF) and radial basis function (RBF) neural network, using MATLAB software for modeling and analysis, comparing with the original documents by response surface analysis method. The following main conclusions: by comparing the relative coefficient (R2), the mean absolute error (MAE), mean bias error (MBE), root mean square error (RMSE) and mean square error (MSE), compared with the traditional response surface analysis method, machine learning algorithms show better prediction effect, random forests and the relative coefficient of radial basis function (RBF) neural network is the most close to 1, the prediction effect is best, followed by BP neural network and support vector machine.
| [1] | 吴志刚, 赵璐. 微藻在食品领域中的应用研究进展[J]. 农产品加工, 2023(2): 73-75, 80. |
| [2] | Nuño, K., Villarruel-López, A., Puebla-Pérez, A.M., Romero-Velarde, E., Puebla-Mora, A.G. and Ascencio, F. (2013) Effects of the Marine Microalgae Isochrysis galbana and Nannochloropsis oculata in Diabetic Rats. Journal of Functional Foods, 5, 106-115. https://doi.org/10.1016/j.jff.2012.08.011 |
| [3] | 陈丽红, 孙利芹, 王长海. 微藻抗菌物质及筛选模型[J]. 中国生物工程杂志, 2011, 31(9): 109-116. |
| [4] | 徐彤彤, 刘伟, 葛庆燕, 等. 微藻在污水处理中的二氧化碳减排作用与机制[J]. 环境科学与技术, 2022, 45(12): 133-144. |
| [5] | Jaafari, J. and Yaghmaeian, K. (2019) Optimization of Heavy Metal Biosorption onto Freshwater Algae (Chlorella coloniales) Using Response Surface Methodology (RSM). Chemosphere, 217, 447-455. https://doi.org/10.1016/j.chemosphere.2018.10.205 |
| [6] | 韩仕群, 张振华, 严少华. 国内外利用藻类技术处理废水、净化水体研究现状[J]. 农业环境与发展, 2000(1): 13-16. |
| [7] | 张汉华, 李卓佳, 郭志勋, 等. 有益微生物对海水养虾池浮游生物生态特征的影响研究[J]. 南方水产, 2005, 1(2): 7-14. |
| [8] | 马国杰, 常春, 孙绍辉. 能源微藻规模化培养影响因素的研究进展[J]. 化工进展, 2019, 38(12): 5323-5329. |
| [9] | Bartley, M.L., Boeing, W.J., Corcoran, A.A., Holguin, F.O. and Schaub, T. (2013) Effects of Salinity on Growth and Lipid Accumulation of Biofuel Microalga Nannochloropsis Salina and Invading Organisms. Biomass and Bioenergy, 54, 83-88. https://doi.org/10.1016/j.biombioe.2013.03.026 |
| [10] | 齐雨藻, 李中奎, 邓光, 等. 温度、光照和pH值对锥状斯氏藻和塔玛亚历山大藻光合作用的影响及光暗周期对其生长速率和生物量的影响[J]. 武汉植物学研究, 2004, 22(2): 129-135. |
| [11] | Ota, S., Yoshihara, M., Yamazaki, T., Takeshita, T., Hirata, A., Konomi, M., et al. (2016) Deciphering the Relationship among Phosphate Dynamics, Electron-Dense Body and Lipid Accumulation in the Green Alga Parachlorella kessleri. Scientific Reports, 6, Article No. 25731. https://doi.org/10.1038/srep25731 |
| [12] | 田镇, 曹奕, 陈爱华, 等. 球等鞭金藻培养条件的响应面法优化[J]. 海洋渔业, 2021, 43(3): 377-384. |
| [13] | El-Mekkawi, S.A., El-Ibiari, N.N., El-Ardy, O.A., Abdelmonem, N.M., Elahwany, A.H., Abadir, M.F., et al. (2020) Optimization of Cultivation Conditions for Microcystis Aeruginosa for Biodiesel Production Using Response Surface Methodology. Bulletin of the National Research Centre, 44, 405-412. https://doi.org/10.1186/s42269-019-0265-9 |
| [14] | Shi, Q., Chen, W., Huang, S., Wang, Y. and Xue, Z. (2019) Deep Learning for Mining Protein Data. Briefings in Bioinformatics, 22, 194-218. https://doi.org/10.1093/bib/bbz156 |
| [15] | Hermans, S.M., Buckley, H.L., Case, B.S., Curran-Cournane, F., Taylor, M. and Lear, G. (2020) Using Soil Bacterial Communities to Predict Physico-Chemical Variables and Soil Quality. Microbiome, 8, Article No. 79. https://doi.org/10.1186/s40168-020-00858-1 |
| [16] | Muhammad, G., Alam, M.A., Mofijur, M., Jahirul, M.I., Lv, Y., Xiong, W., et al. (2021) Modern Developmental Aspects in the Field of Economical Harvesting and Biodiesel Production from Microalgae Biomass. Renewable and Sustainable Energy Reviews, 135, Article ID: 110209. https://doi.org/10.1016/j.rser.2020.110209 |
| [17] | Mohamed, M.S., Tan, J.S., Mohamad, R., Mokhtar, M.N. and Ariff, A.B. (2013) Comparative Analyses of Response Surface Methodology and Artificial Neural Network on Medium Optimization for Tetraselmis sp. FTC209 Grown under Mixotrophic Condition. The Scientific World Journal, 2013, Article ID: 948940. https://doi.org/10.1155/2013/948940 |
| [18] | Hariram, V., Bose, A. and Seralathan, S. (2019) Dataset on Optimized Biodiesel Production from Seeds of Vitis vinifera Using ANN, RSM and Anfis. Data in Brief, 25, Article ID: 104298. https://doi.org/10.1016/j.dib.2019.104298 |
| [19] | Muhammad, G., Potchamyou Ngatcha, A.D., Lv, Y., Xiong, W., El-Badry, Y.A., Asmatulu, E., et al. (2022) Enhanced Biodiesel Production from Wet Microalgae Biomass Optimized via Response Surface Methodology and Artificial Neural Network. Renewable Energy, 184, 753-764. https://doi.org/10.1016/j.renene.2021.11.091 |
| [20] | Prakash Maran, J. and Priya, B. (2015) Modeling of Ultrasound Assisted Intensification of Biodiesel Production from Neem (Azadirachta indica) Oil Using Response Surface Methodology and Artificial Neural Network. Fuel, 143, 262-267. https://doi.org/10.1016/j.fuel.2014.11.058 |
| [21] | Mostafaei, M., Javadikia, H. and Naderloo, L. (2016) Modeling the Effects of Ultrasound Power and Reactor Dimension on the Biodiesel Production Yield: Comparison of Prediction Abilities between Response Surface Methodology (RSM) and Adaptive Neuro-Fuzzy Inference System (ANFIS). Energy, 115, 626-636. https://doi.org/10.1016/j.energy.2016.09.028 |
| [22] | Vinoth Arul Raj, J., Praveen Kumar, R., Vijayakumar, B., Gnansounou, E. and Bharathiraja, B. (2021) Modelling and Process Optimization for Biodiesel Production from Nannochloropsis Salina Using Artificial Neural Network. Bioresource Technology, 329, Article 124872. https://doi.org/10.1016/j.biortech.2021.124872 |
| [23] | Betiku, E., Okunsolawo, S.S., Ajala, S.O. and Odedele, O.S. (2015) Performance Evaluation of Artificial Neural Network Coupled with Generic Algorithm and Response Surface Methodology in Modeling and Optimization of Biodiesel Production Process Parameters from Shea Tree (Vitellaria paradoxa) Nut Butter. Renewable Energy, 76, 408-417. https://doi.org/10.1016/j.renene.2014.11.049 |
| [24] | Garg, A. and Jain, S. (2020) Process Parameter Optimization of Biodiesel Production from Algal Oil by Response Surface Methodology and Artificial Neural Networks. Fuel, 277, Article 118254. https://doi.org/10.1016/j.fuel.2020.118254 |
| [25] | Pirmoradi, N., Ghaneian, M.T., Ehrampoush, M.H., Salmani, M.H. and Hatami, B. (2021) The Conversion of Poultry Slaughterhouse Wastewater Sludge into Biodiesel: Process Modeling and Optimization. Renewable Energy, 178, 1236-1249. https://doi.org/10.1016/j.renene.2021.07.016 |
