ABSTRACT
Climate prediction plays a crucial role in understanding and adapting to the impacts of climate change. In recent years, researchers have explored its application in climate prediction models. Our aim is to build a deep hybrid model for climate prediction specifically in the Daxiangxi region, which includes CNN, LSTM, and MLP (called CLM). It aims to assist in decision-making related to agriculture, water resource management, and human being life. Deep learning models typically adopt different neural network structures with multiple hidden layers, which can learn the spatiotemporal relationship in historical meteorological data, and effectively predict future climate conditions. In this research, a large amount of meteorological data, including temperature, precipitation, and wind speed, was collected. These data will be used to train the different models, such as LSTM, CNN, ConvLSTM, and our proposed hybrid model, for predicting future climate changes in the Daxiangxi region. To achieve the high accuracy of our proposed model, optimization techniques such as data processing, regularization, and hyperparameter tuning can be employed. Additionally, in our experiments, datasets need to be divided into three parts such as training, validation, and testing sets. Appropriate evaluation metrics are selected to assess the predictive capability of these models. Our tests show that the proposed model performs well.
- Cifuentes, J., Marulanda, G., Bello, A., & Reneses. 2020. Air Temperature Forecasting Using Machine Learning Techniques: A Review. Energies, 13 [16], 4215Google Scholar
- Tol, R.S. 2002.Estimates of the damage costs of climate change. Part 1: Benchmark estimates. Environ. Resour. Econ. 21, 47–73.Google ScholarCross Ref
- Schizas CN, Michaelides S, Pattichis CS, Livesay RR. 1991. Artificial neural networks in forecasting minimum temperature [weather]. In: 1991 Second International Conference On Artificial Neural Networks, pp 112–114Google Scholar
- Rumelhart DE, McClelland JL. 1987. The PDP perspective. In: Parallel distributed processing: explorations in the microstructure of cognition: foundations, MITP.Google Scholar
- Han, Z., Zhao, J., Leung, H., Ma, K. F., & Wang, W. 2021. A Review of Deep Learning Models for Time Series Prediction. IEEE Sensors Journal, 21 [6], 7833–7848.Google Scholar
- Tsokov, S., Lazarova, M., & Aleksieva-Petrova, A. 2022. A Hybrid Spatiotemporal Deep Model Based on CNN and LSTM for Air Pollution Prediction. Sustainability, 14 [9], 5104.Google Scholar
- Zanaty, E. A. 2012. Support vector machines [SVMs] versus multilayer perception [MLP] in data classification. Egyptian Informatics Journal, 13 [3], 177-183.Google Scholar
- Eymen, A., Köylü, Ü. 2019. Seasonal trend analysis and ARIMA modeling of relative humidity and wind speed time series around Yamula Dam. Meteorol Atmos Phys 131, 601–612Google ScholarCross Ref
- Edwin Raczko & Bogdan Zagajewski. 2017. Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images, European Journal of Remote Sensing, 50:1, 144-154Google ScholarCross Ref
- Mao, F., Xu, X., & Li, M. 2021. PM2.5 concentration prediction based on convolutional neural network and long short-term memory network. Atmospheric Pollution Research, 12 [1], 93-102.Google Scholar
- Zhang, Z., & Dong, Y. 2020. Temperature Forecasting via Convolutional Recurrent Neural Networks Based on Time-Series Data. Complexity, 2020, 1–8.Google Scholar
- Grover, A., Kapoor, A., & Horvitz, E. 2015. A Deep Hybrid Model for Weather Forecasting. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Google ScholarDigital Library
- Q. Fu, D. Niu, Z. Zang, J. Huang and L. Diao. 2019. Multi-Stations Weather Prediction Based on Hybrid Model Using 1D CNN and Bi-LSTM, 2019 Chinese Control Conference [CCC], Guangzhou, China, pp. 3771-3775.Google Scholar
- Zhang C, Yu J, Wang S. 2021. Fault detection and recognition of multivariate process based on feature learning of one-dimensional convolutional neural network and stacked denoised autoencoder. International Journal of Production Research, 59 [8]: 2426-2449.Google Scholar
- Lecun, Y.; Bottou, L.; Bengio, Y.; Haffner, P.1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324.Google ScholarCross Ref
- S. Siami-Namini, N. Tavakoli and A. S. Namin. 2019. The Performance of LSTM and BiLSTM in Forecasting Time Series. IEEE International Conference on Big Data [Big Data], Los Angeles, CA, USA. pp. 3285-3292.Google Scholar
Recommendations
Hybrid Wavelet-Postfix-GP model for rainfall prediction of anand region of India
An accurate prediction of rainfall is crucial for national economy and management of water resources. The variability of rainfall in both time and space makes the rainfall prediction a challenging task. The present work investigates the applicability of ...
A hybrid deep neural network approach to estimate reference evapotranspiration using limited climate data
AbstractReference evapotranspiration (ET0) plays an undeniably important role in irrigation management. Thus, accurate estimation of ET0 is necessary to avoid over or under irrigation to increase agricultural productivity and manage water resources ...
A Hybrid Deep Learning Model Based on LSTM for Long-term PM2.5 Prediction
ICIST '21: Proceedings of the 3rd International Conference on Intelligent Science and TechnologyWith the acceleration of industrialization and urbanization, problem of air pollution becomes an urgent problem to be solved. PM2.5 is a major pollutant in the atmosphere which is harmful to human health. Existing models like RNN and LSTM could make ...
Comments