Regional Short-term Micro-climate Air Temperature Prediction with CBPNN

Abstract

This paper proposes a novel short-term air temperature prediction with three-layer Back Propagation Neural Network (BPNN) for the regional application of next 1-12 hours. With the continuous collection of eight real-time micro-climate parameters in the experimentation and demonstration stations in our university, the Multiple Stepwise Regression (MSR) is employed to screen the original historical data to find the parameter factors with greater contribution rate. On the basis of the Root Mean Square Error (RMSE) value evaluating the optimal fitting degree of the stepwise regression, the Levenberg-Marquardt (LM) and the Resilient Propagation (R-Prop) training algorithm are employed to construct a Combined BPNN (CBPNN) with two MSR inputs. Compared with the known micro-climate data sets, the Mean Absolute Error (MAE) is to evaluate the applicability of CBPNN prediction model. The experimentation shows that the MAE is within 4°C in the next 12 hours. This proposal will be deployed in stations in our university for extreme weather warnings, and could be applied to some regional short-term parameter prediction for the future agricultural production service.

Smart greenhouses as the path towards precision agriculture in the food-energy and water nexus: case study of Qatar

“…The WSN's sensed data are processed and then used as multi-inputs to drive advanced control algorithms-based artificial intelligence to manage intelligently the greenhouse internal microclimate and to optimize the use of water and energy. These controllers can also vary from simple, such as feedback controllers (Mekki et al 2015;Maher et al 2016;Pawlowski et al 2017), to modern ones such as fuzzy logic controllers (Rahmawati et al 2018;Alpay and Erdem 2018;Xu et al 2016;Pahuja et al 2015;Márquez-Vera et al 2016;Chen et al 2016b;Wang and Zhang 2018;Li et al 2017bLi et al , 2018Ben Ali et al 2018;Faouzi et al 2017;Carrasquilla-Batista and Chacon-Rodrıguez 2017), artificial neural networks (Nicolosi et al 2017;Huang et al 2018;Francik and Kurpaska 2020;Singh 2017;Hongkang et al 2018;Moon et al 2018;Taki et al 2016), genetic algorithms (Wang et al 2017a;Mahdavian and Wattanapongsakorn 2017), model predictive controllers (Ouammi et al 2020b;Liang et al 2018b;Hamza and Ramdani 2020), sliding controllers (Khelifa et al 2020;Oubehar, et al 2016), adaptative controllers (Essahafi and Lafkih 2018), frequency controllers (Bagheri Sanjareh et al 2021), and receding horizon controllers based on prioritized multi-operational ranges (Singhal et al 2020).…”

Precision Irrigation Scheduling Based on Wireless Soil Moisture Sensors to Improve Water Use Efficiency and Yield for Winter Wheat in Sub-Saharan Africa

“…Several authors [22][23][24] also focused on control systems, which are based on the prediction of soil moisture content and atmospheric conditions, but without much attention to developing intelligent agriculture systems that are less costly and efficient in terms of water and energy use.…”