Using Dynamic Time Warping to Calibrate Low-Cost Soil Moisture Sensors

The rapid development of the Internet of Things (IoT) has led to widespread availability of smart sensors. For example, in the context of agriculture this enables the continuous monitoring of plants or automation of irrigation systems. One important parameter in this context is the soil moisture value. But the corresponding sensors are either very expensive or inaccurate. Therefore, low-cost soil moisture sensors have to be calibrated, which is very time intensive, if done properly. This paper proposes an in-situ calibration method to automatically calibrate a cluster of connected low-cost soil moisture sensors using Dynamic Time Warping (DTW) and one medium-priced sensor as reference. We demonstrate that it is possible to achieve better results in comparison to the current easy manual calibration methods with less manual work.