**5. Conclusions**

In this study, we have applied an artificial neural network algorithm to model the hyperspectral response of water-induced stress in lettuce. The ANN algorithm detected differences since the first day of the induced stress, with an 80% classification accuracy. The algorithm continued to present an increasing performance along with time-series analysis, resulting in a final 93% accuracy. The spectral wavelengths that contributed the most for its prediction were located around 380 to 440 nm, 660 to 730 nm, and, on a lower level, 790 nm onwards. We also detected that absorbance values are more suitable to deal with this issue than reflectance. Although the rhizobacteria did mitigate the water-stress effect at some point, a spectral behavior difference was noticed by the ANN algorithm, proving its robustness. The proposed approach indicated how feasible water stress in lettuce at early stages is measurable with machine learning algorithms such as ANN in hyperspectral data. While the small number of instances (four measurement days) evaluated could provide problems for the experiment, all machine learning algorithms tested here were able to classify it appropriately. For future works, we recommend similar studies with other species and cultivars. Additionally, the method demonstrated here could be scaled up to remote sensing platforms like unmanned aerial vehicles (UAV), as currently hyperspectral sensors can be embedded in it.

**Author Contributions:** Conceptualization, L.P.O. and F.F.d.A.; methodology, L.P.O., É.A.S.M., L.G.B., B.C.d.L., D.R.P.; formal analysis, L.P.O.; resources, F.F.d.A., N.N.I.; data curation, É.A.S.M.; writing—original draft preparation, L.P.O.; A.P.M.R. writing—review and editing, J.M.J., J.E.C., J.L., V.L., W.N.G., N.E., D.R.P.; supervision, F.F.d.A., N.N.I.; project administration, F.F.d.A., N.N.I.; funding acquisition, L.P.O., F.F.d.A.

**Funding:** This research was partially funded by CAPES/Print (p: 88881.311850/2018-01) and FAPESP/Print (p: 2013/20328-0) V. Liesenberg is supported by FAPESC (2017TR1762) and CNPq (313887/2018-7).

**Conflicts of Interest:** The authors declare no conflict of interest.
