Soil Moisture Prediction Model Based on Improved GRU Recurrent Neural Network

Authors

  • Guowei Wang College of Information Technology, Jilin Agricultural University, Changchun 130118, China
  • Chunying Wei College of Information Technology, Jilin Agricultural University, Changchun 130118, China
  • Li Yan College of Information Technology, Jilin Agricultural University, Changchun 130118, China
  • Jian Li College of Information Technology, Jilin Agricultural University, Changchun 130118, China

DOI:

https://doi.org/10.13052/spee1048-5236.4329

Keywords:

GRU recurrent neural network, Seagull optimization algorithm, Soil moisture prediction

Abstract

Soil moisture plays a crucial role in land water and energy cycles, and has a certain impact on weather and climate change. In agricultural production, crop moisture status can be determined based on soil moisture, and timely and effective irrigation strategies can be formulated to ensure grain yield while saving water resources, maximizing the value of agricultural water resource utilization, and achieving sustainable development. Therefore, the accuracy of soil moisture prediction has important research value for many fields such as agriculture and climate. In this paper, the super parameters of GRU Recurrent neural network are optimized by intelligent seagull optimization algorithm using a small number of influencing factors, namely, atmospheric temperature, atmospheric humidity, rainfall and soil moisture data, and a soil moisture prediction model is established. The model was used to predict soil moisture for the next 12 hours, 24 hours, 36 hours, and 48 hours, respectively. The final experiment showed that the model in this paper had better predictive effect on soil moisture, with the best predictive evaluation index data being MAPE (12h) = 4.4120%, R2 (12h) = 0.94605, and RMSE (12h) = 1.9998; By comparing the prediction results of multiple time steps vertically, it was found that the prediction accuracy of the model in this paper decreased more smoothly, meeting the requirements of soil moisture prediction.

Downloads

Download data is not yet available.

Author Biographies

Guowei Wang, College of Information Technology, Jilin Agricultural University, Changchun 130118, China

Guowei Wang, PhD, associate professor, works at Jilin Agricultural University. Executive Director of Jilin Provincial Operations Research Association and Executive Director of Jilin Provincial Smart Agriculture Association. The main research areas include artificial intelligence and computer agriculture applications, intelligent decision-making systems, and GIS. Led 3 projects of the Provincial Department of Science and Technology, 1 project of the Provincial Agricultural Commission, participated in 9 national level projects, and 8 provincial-level scientific research projects; Received 1 first prize and 2 second prizes for scientific and technological progress in Jilin Province. Obtained 4 national invention patents, 6 utility model patents, and 24 software copyright registrations; Write over 30 scientific research papers.

Chunying Wei, College of Information Technology, Jilin Agricultural University, Changchun 130118, China

Chunying Wei, Master of computer science and technology. Her research interests include deep learning and agricultural big data analysis.

Li Yan, College of Information Technology, Jilin Agricultural University, Changchun 130118, China

Li Yan, lecturer, teacher at the Mathematics Department of the School of Information Technology, Jilin Agricultural University. Main research directions: Information theory, data mining. Guiding students to participate in mathematical modeling competitions has won one national second prize and multiple provincial awards in Jilin. Guide students to participate in two innovation and entrepreneurship program projects. Participated in 3 projects of the Jilin Provincial Department of Science and Technology, 5 other department level projects, and 1 Jilin Provincial Innovation Team. Hosted or participated in 4 school level educational reform projects. Published 9 papers, obtained 2 utility model patents, and applied for 14 software copyright registrations.

Jian Li, College of Information Technology, Jilin Agricultural University, Changchun 130118, China

Jian Li, a member of the Communist Party of China, holds a Ph.D. in Engineering, a professor, and a doctoral supervisor. He is currently the Vice Dean of the School of Information Technology at Jilin Agricultural University, the leader of the first level discipline authorized for a Master’s degree in Computer Science and Technology, and the leader of the Data Science and Big Data Technology major. Expert in the evaluation of the National Natural Science Foundation project, communication evaluation expert of the Degree Center of the Ministry of Education, member of the Jilin Province Higher Education Undergraduate Teaching Guidance Committee, and Jilin Province Science and Technology Commissioner.

References

Nie Yan, Ma Zeyue, Zhou Xiaofeng, Yu Lei, Yu Jing. Research on Soil Moisture Inversion and Monitoring in the Aksu River Basin. Journal of Ecology, 2019, 39(14):5138–5148.

Zhai Hui. Study on the influence mechanism of water and organic matter on the transformation of soil selenium forms. Northwest A&F University, 2021.

Hao Zhen. Research on soil moisture inversion technology based on multi-source data collaboration. Lanzhou Jiaotong University, 2017.

Thiemann M, Trosset M, Gupta H, et al. Bayesian recursive parameter estimation for hydrologicmodels. Water Resources Research, 2001, 37(10):2521–2535.

Aguilera H, Moreno L, Wesseling J G, et al. Soil moisture prediction to support management in semiarid wetlands during drying episodes. CATENA, 2016,147:709–724.

Yan Changrong, Shen Huijuan, He Wenqing, Liu Shuang, Liu Qin. Research on soil moisture prediction model based on multiple regression method. Journal of Hubei University for Nationalities (Natural Science Edition), 2008(3):241–245.

Haoxiong Yang, Chuan Zhao, Xinjian Du, Jing Wang. Risk Prediction of City Distribution Engineering Based on BP. Systems Engineering Procedia, 2012, 5.

Bai Dongmei, Guo Mancai, Guo Zhongsheng, Chen Yanan. Application of Time Series Autoregressive Model in Soil Moisture Prediction. Soil and Water Conservation in China, 2014(2):42–45+

Muhammad Mukhlisin, Ahmed El-Shafie, Mohd Raihan Taha. Regularized versus non-regularized neural network model for prediction of saturated soil-water content on weathered granite soil formation. Neural Computing and Applications, 2012,21(3):543–553.

Zai Songmei, Guo Dongdong, Han Qibiao, Wen Ji. Prediction of soil moisture based on artificial neural Network theory theory. China Agricultural Bulletin, 2011,27(8):280–283.

Yu Jingxin, Zhang Xin, Xu Linlin, Dong Jing, Zhangzhong Lili. A hybrid CNN-GRU model for predicting soil moisture in maize root zone. Agricultural Water Management, 2021,245:106649.

Xue Ming, Wei Bo, Li Juan, Chen Cihao, Huang Minhui, Zou Linxin. Research on soil moisture prediction method based on improved BP neural network and support vector machine. Soil Bulletin, 2021,52(4): 793–800.

Apeksha Shewalkar, Deepika Nyavanandi, Simone A. Ludwig. Performance Evaluation of Deep Neural Networks Applied to Speech Recognition: RNN, LSTM and GRU. Journal of Artificial Intelligence and Soft Computing Research, 2019,9(4):235–245.

Ge Xiangyu, Ding Jianli, Wang Jingzhe, Wang Fei, Cai Lianghong, Sun Huilan. Estimation of soil moisture content based on competitive adaptation weighted sampling algorithm coupled with machine learning. Journal of Optics, 2018,38(10):393–400.

Kyunghyun Cho, Bart van Merrienboer, Çaglar Gülçehre, Fethi Bougares, Holger Schwenk, Yos hua Bengio. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. CoRR, 2014, abs/1406.1078.

Zhao Jianpeng, Zhang Aijun, Cai Chengfei, Su Yinhong. Research on Prediction of Wave Dip Angle Based on Gated Recurrent Networks. Foreign Electronic Measurement Technology, 2019,38(5):96–100.

Gaurav Dhiman, Vijay Kumar. Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems. Knowledge-Based Systems, 2018,165:169–196.

Jiang Siwei, Sun Yan, Chen Jing, et al. Improved Particle Swarm Optimization GRU Network for Grain Storage Temperature Prediction. Computer and Digital Engineering, 2023,51(05):1036–1041+1156.

Qiao Xiaodan, Zheng Wengang, Zhang Xin, et al. Research on the Prediction Method of Sunlight Greenhouse Environment Based on LSTM-GRU. Jiangsu Agricultural Science, 2022,50(16):211–218.

Chen Yihao, Li Mingwei, An Xiaogang, et al. Research on the Intelligent Prediction Method of Dam Deformation Based on Chaotic Quantum Bat CNN-GRU. Journal of Harbin Engineering University: 1–12 [2023-09-25].

Zhu Hainan, Li Fengshuo, Sun Huazhong et al. Short term load forecasting method for distribution networks based on improved AlexNet GRU deep learning network. Power Capacitors and Reactive Power Compensation, 2023,44(04):48–54+61.

Li Yuanhang. Comparative Study on the Optimization Performance of Seagull Optimization Algorithm and Whale Optimization Algorithm. Modern Information Technology, 2021,5(03):67–71

Downloads

Published

2024-01-14

How to Cite

Wang, G. ., Wei, C. ., Yan, L. ., & Li, J. . (2024). Soil Moisture Prediction Model Based on Improved GRU Recurrent Neural Network. Strategic Planning for Energy and the Environment, 43(02), 381–400. https://doi.org/10.13052/spee1048-5236.4329

Issue

Section

Greener Energy and Sustainable Development with AI-based loT