A variable weight combination prediction model for climate in a greenhouse based on BiGRU-Attention and LightGBM
文献类型： 外文期刊
作者： Mao, Xiaojuan 1 ; Ren, Ni 1 ; Dai, Peiyu 1 ; Jin, Jing 1 ; Wang, Baojia 1 ; Kang, Rui 1 ; Li, Decui 1 ;
作者机构： 1.Jiangsu Acad Agr Sci, Agr Informat Inst, Nanjing 210014, Peoples R China
2.Minist Agr & Rural Affairs, Key Lab Intelligent Agr Technol Changjiang Delta, Nanjing 210014, Peoples R China
关键词： Greenhouse; Climate; Bi-directional Gated Recurrent Unit; Attention; LightGBM
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.3； 五年影响因子：8.3 ）
ISSN： 0168-1699
年卷期： 2024 年 219 卷
页码：
收录情况： SCI
摘要： Accurate prediction of environmental changes in a greenhouse is crucial for precise control and promoting crop growth. However, the microclimate environment in a greenhouse is nonlinear, temporal, multivariate, and strongly coupled, making it difficult to establish a robust fitting model. To address these issues, this study proposed a variable weight combination prediction model based on attention mechanism optimized Bidirectional Gated Recurrent Unit (BiGRU-Attention) and Light Gradient Boosting Machine (LightGBM). The Particle Swarm Optimization Algorithm (PSO) was employed to optimize the weight coefficients of the predicted values from BiGRU-Attention and LightGBM models at different times. This optimization aimed to enhance the accuracy of predicting air temperature, air humidity, and Photosynthetically Active Radiation (PAR) in a greenhouse. In predictions spanning time steps from 30 to 120 min, the variable weight combination prediction model demonstrated superior performance compared to single models and equal weight combination model BiGRU-Attention-LightGBM. At the time step of 120 min, the coefficient of determination R2 for air temperature was 0.9586, air humidity was 0.9232, and PAR was 0.8066. This indicated that the variable weight combination model (PSO-BiGRU-Attention-LightGBM) could more accurately predict the future dynamic trends of climatic environment factors in a greenhouse.
- 相关文献
作者其他论文 更多>>
-
3D-GhostNet: A novel spatial-spectral algorithm to improve foodborne bacteria classification coupled with hyperspectral microscopic imaging technology
作者：Kang, Rui;Huang, Jiaxing;Kang, Rui;Ouyang, Qin;Park, Bosoon;Kang, Rui;Sun, Shangpeng;Ouyang, Qin
关键词：Hyperspectral microscope imaging; Foodborne pathogen; Rapid detection; 3D hypercube classification
-
Toward Real Scenery: A Lightweight Tomato Growth Inspection Algorithm for Leaf Disease Detection and Fruit Counting
作者：Kang, Rui;Huang, Jiaxin;Ren, Ni;Kang, Rui;Zhou, Xuehai;Sun, Shangpeng
关键词：
-
Response of Flavor Substances in Tomato Fruit to Light Spectrum and Daily Light Integral
作者：Fan, Xiaoxue;Jin, Jing;Mao, Xiaojuan;Ren, Ni;Lu, Na;Xu, Wenshuo;Zhuang, Yunfei
关键词：PFALs; light quality; DLI; fruit quality; flavor substances
-
China-US grain trade shapes the spatial genetic pattern of common ragweed in East China cities
作者：Lu, Siran;Yang, Jun;Luo, Xiangyu;Wang, Hongfang;Gentili, Rodolfo;Citterio, Sandra;Yang, Jingyi;Jin, Jing;Li, Jianguang;Lu, Siran;Lu, Siran
关键词：
-
Automated segmentation of foodborne bacteria from chicken rinse with hyperspectral microscope imaging and deep learning methods
作者：Park, Bosoon;Shin, Taesung;Yoon, Seung-Chul;Kang, Rui;Fong, Alexandre;McDonogh, Barry
关键词：Hyperspectral microscopy; Foodborne pathogen; Bacterial detection; Single-cell segmentation; U-Net
-
Physicochemical indicators coupled with multivariate analysis for comprehensive evaluation of matcha sensory quality
作者：Wu, Jizhong;Ouyang, Qin;Wang, Li;Chen, Quansheng;Park, Bosoon;Kang, Rui;Wang, Zhen
关键词：Fine tea powder; Sensory attributes; Physicochemical properties; LASSO fitting; Principal component analysis
-
Sensor Location Optimisation Design Based on IoT and Geostatistics in Greenhouse
作者：Liu, Yang;Dai, Xiu;Xun, Guanglian;Ren, Ni;Kang, Rui;Mao, Xiaojuan;Liu, Xiaoyu;Liu, Yang;Liu, Xiaoyu;Kang, Rui
关键词：Vegetable greenhouse; environmental monitoring; internet of things; sensor location design; ordinary kriging
