Irrigation is one of the most water-intensive agricultural activities in the world, which has been increasing over time. Choosing an optimal irrigation management plan depends on having available data in the monitoring field. A smart agriculture system gathers data from several sources; however, the data are not guaranteed to be free of discrepant values (i.e., outliers), which can damage the precision of irrigation management. Furthermore, data from different sources must fit into the same temporal window required for irrigation management and the data preprocessing must be dynamic and automatic to benefit users of the irrigation management plan. In this paper, we propose the Smart&Green framework to offer services for smart irrigation, such as data monitoring, preprocessing, fusion, synchronization, storage, and irrigation management enriched by the prediction of soil moisture. Outlier removal techniques allow for more precise irrigation management. For fields without soil moisture sensors, the prediction model estimates the matric potential using weather, crop, and irrigation information. We apply the predicted matric potential approach to the Van Genutchen model to determine the moisture used in an irrigation management scheme. We can save, on average, between 56.4% and 90% of the irrigation water needed by applying the Zscore, MZscore and Chauvenet outlier removal techniques to the predicted data.

This paper proposes a method based on multivariate spatial and temporal correlation to improve prediction accuracy in data reduction for Wireless Sensor Networks (WSN). Prediction of data not sent to the sink node is a technique used to save energy in WSNs by reducing the amount of data traffic. However, it may not be very accurate. Simulations were made involving simple linear regression and multiple linear regression functions to assess the performance of the proposed method. The results show a higher correlation between gathered inputs when compared to time, which is an independent variable widely used for prediction and forecasting. Prediction accuracy is lower when simple linear regression is used, whereas multiple linear regression is the most accurate one. In addition to that, our proposal outperforms some current solutions by about 50% in humidity prediction and 21% in light prediction. To the best of our knowledge, we believe that we are probably the first to address prediction based on multivariate correlation for WSN data reduction.