A low footprint olive grove weather forecasting using a single-layered seasonal attention encoder-decoder model |
| |
| Institution: | 1. Electronics and Electrical Communications Engineering Department, Faculty of Engineering, Cairo University, Giza 12613, Egypt;2. University of Science and Technology, Zewail City of Science, Technology and Innovation, Giza 12578, Egypt;1. College of New Energy and Environment, Jilin University, Jilin Province, China;2. Department of Oceanography and Coastal Sciences, Louisiana State University, Baton Rouge, LA, USA;3. Retired, United States Geological Survey, Louisiana Water Science Center, Baton Rouge, LA, USA;1. Institute of Agricultural and Forestry Defense of the Espírito Santo – IDAF, BR 262, Km 195, Iúna, ES, Brazil;2. Federal University of Espírito Santo – UFES, Av. Governor Lindemberg, 316, Jerônimo Monteiro, ES, Brazil;3. Canopy Remote Sensing Solutions, Rod. José Carlos Daux, 4150, Florianópolis, SC, Brazil;4. Federal University of Sergipe – UFS, Av. Marechal Rondon, São Cristóvão, SE, Brazil;5. Federal University of Mato Grosso – UFMT, Av. Fernando Correa da Costa, 2367, Boa Esperança, Cuiabá, MT, Brazil;6. Federal University of Pará – UFPA, University Campus of Altamira, St. Cel. José Porfírio, 2515, São Sebastiao, Altamira, PA, Brazil;1. Fundación Alium Pacific, Cali, Colombia;2. Instituto Politécnico Nacional, Centro Interdisciplinario de Ciencias Marinas, C.P. 23096 La Paz, Baja California Sur, Mexico;3. Universidad Jorge Tadeo Lozano, Programa de Biología Marina, Facultad de Ciencias Naturales e Ingeniería, Santa Marta, Colombia;4. Coastal Marine Education and Research Academy, Clearwater, FL, USA;1. Remote Sensing Laboratory, Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi 221005, India;2. Image Processing Laboratory (IPL), University of Valencia, Valencia 46010, Spain;3. DST-Mahamana Centre for Excellence in Climate Change Research, Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi 221005, India;4. Secretary of Research and Postgraduate, CONACYT-UAN, Tepic, Nayarit, Mexico;5. Department of Physics, Indian Institute of Technology (BHU), Varanasi, India |
| |
| Abstract: | Weather forecasting is essential in various applications such as olive smart farming. Farmers use the predicted weather data to take appropriate actions with the aim of increasing the crop production. Many deep learning models have been developed for tackling such a problem. However, olive groves are located in remote areas with no Internet connectivity, therefore these models are not applicable as they require either powerful processors or communication with cloud servers for inference. In this work, we propose a deep learning encoder-decoder model that uses a seasonal attention mechanism for time series forecasting of weather variables. The proposed model is non-complex, yet more powerful, compared to the more complex models in the literature. We use this model as the core of a framework that preprocess the training and testing data, train the model, and deploy the model on a resource-constrained microcontroller. Using real-life weather datasets of Spanish, Greek, and Chinese weather stations, we prove that the proposed model achieves a higher prediction accuracy compared to the existing literature. More specifically, the achieved prediction mean absolute error (MAE) is 2.13 °C and root mean squared error (RMSE) is 2.64 °C. This outstanding accuracy performance is achieved with the model requiring only 37.6 kB of memory for storing the model parameters with a total memory requirement of 50.1 kB. Since the model is relatively non-complex, we implement it on the Raspberry Pi Pico platform which has a very low cost with minimal power consumption compared to other embedded platforms. We also build a prototype and test it to verify the model's ability to achieve the target objective in real-life scenarios. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
