Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images.

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 red-green-blue images. During ripening stage and at harvest, over 22,000 digital images were captured vertically downward over the rice canopy from a distance of 0.8 to 0.9 m at 4,820 harvesting plots having the yield of 0.1 to 16.1 t·ha-1 across 6 countries in Africa and Japan. A convolutional neural network applied to these data at harvest predicted 68% variation in yield with a relative root mean square error of 0.22. The developed model successfully detected genotypic difference and impact of agronomic interventions on yield in the independent dataset. The model also demonstrated robustness against the images acquired at different shooting angles up to 30° from right angle, diverse light environments, and shooting date during late ripening stage. Even when the resolution of images was reduced (from 0.2 to 3.2 cm·pixel-1 of ground sampling distance), the model could predict 57% variation in yield, implying that this approach can be scaled by the 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, and yield forecast at several weeks before harvesting.

Vibrational decoherence induced by ultrafast intramolecular charge separation of an asymmetric bianthryl derivative.

Coherent wavepacket oscillation accompanying the ultrafast photoexcited intramolecular charge separation (CS) of 9,9'-bianthryl (BA) and 10-cyano-9,9'-bianthryl (CBA) in a room temperature ionic liquid, N,N-diethyl-N-methyl-N-(methoxyethyl)ammonium tetrafluoroborate (DemeBF4), was investigated by femtosecond time-resolved transient absorption spectroscopy. The frequency of the coherent oscillation observed for CBA in nonpolar n-hexane solution (Hex) was 377 cm-1, while this oscillation was undetectable in DemeBF4. For BA in DemeBF4, coherent oscillation with a frequency of 394 cm-1 was observed, which is similar to that for CBA in Hex. CS of CBA occurs in the ultrashort time range of ≤100 fs, while that of BA occurs in a few picosecond range [E. Takeuchi et al., J. Phys. Chem. C 120, 14502-14512 (2016)]. Hence, the oscillation of CBA in Hex and that of BA in DemeBF4 are assigned to the molecular vibration in the locally excited state, while this oscillation dephases instantaneously for CBA in DemeBF4 due to the ultrafast CS and no oscillation was generated in the CS state. This result suggests that the CS reaction is not mediated by a specific intramolecular vibration in the CS state but occurs incoherently through higher levels of multiple vibrational modes.