Water stress level classification of sweet potato using infrared thermal imaging and plant growth indicators

Abstract

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/ licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. Abstract Recently, sudden droughts and floods due to the average temperature increase have become frequent and have become an emerging issue worldwide. It has caused serious decline in agricultural yield and product quality. Also, even though sweet potato is well known for growing under harsh environment, its yield can be affected by abnormal climates. Therefore, the importance of water stress monitoring of sweet potatoes has drawn substantial attention. As a result, a lot of research is being conducted. Then, various water stress level monitoring techniques have been recently developed. Therefore, in the current study, a nondestructive evaluation technique has been suggested for the water stress level evaluation of field-grown sweet potatoes. To accomplish this, thermal imagery and support vector machine (SVM) technique was used and a classifier for water stress evaluation (CSE) was developed. In addition, crop water stress index (CWSI) was derived from acquired thermal imagery and plat growth indices was used for developing the CSE. Consequently, the accuracy of the newly developed CSE was about 0.86. This study has demonstrated that CSE can be used to quantify water level stress and control the amount of irrigation water. Furthermore, based on the developed technique, the water stress level of different field-grown crops will be promising.