Instant estimation of rice yield using ground-based RGB images and its potential applicability to UAV

Rice (Oryza sativa L.) is one of the most important cereals, which provides 20% of the world’s food energy. However, its productivity is poorly assessed especially in the global South. Here, we provide a first study to perform a deep learning-based approach for instantaneously estimating rice yield using RGB images. During ripening stage and at harvest, over 22,000 digital images were captured vertically downwards over the rice canopy from a distance of 0.8 to 0.9m at 4,820 harvesting plots having the yield of 0.1 to 16.1 t ha-1 across six countries in Africa and Japan. A convolutional neural network (CNN) applied to these data at harvest predicted 68% variation in yield with a relative root mean square error (rRMSE) of 0.22. Even when the resolution of images was reduced (from 0.2 to 3.2cm pixel-1 of ground sampling distance), the model could predict 57% variation in yield, implying that this approach can be scaled by use of unmanned aerial vehicles. Our work offers low-cost, hands-on, and rapid approach for high throughput phenotyping, and can lead to impact assessment of productivity-enhancing interventions, detection of fields where these are needed to sustainably increase crop production.

総合論文 (Comprehensive paper)