To solve the problem of non-destructive crop water content of detection under outdoor conditions, we propose a method to predict lettuce canopy water content by collecting outdoor hyperspectral images of potted lettuce plants and combining spectral analysis techniques and model training methods. Firstly, background noise was removed by correlation segmentation, proposed in this paper, whereby light intensity correction is performed on the segmented lettuce canopy images. We then chose the first derivative combined with mean centering (MC) to preprocess the raw spectral data. Hereafter, feature bands were screened by a combination of Monte Carlo uninformative variable elimination (MCUVE) and competitive adaptive reweighting sampling (CARS) to eliminate redundant information. Finally, a lettuce canopy moisture prediction model was constructed by combining partial least squares (PLS). The correlation coefficient between model predicted and measured values was used as the main model performance evaluation index, and the modeling set correlation coefficient R_c was 82.71%, while the prediction set correlation coefficient R_P was 84.67%. The water content of each lettuce canopy pixel was calculated by the constructed model, and the visualized lettuce water distribution map was generated by pseudo-color image processing, which finally revealed a visualization of the water content of the lettuce canopy leaves under outdoor conditions. This study extends the hyperspectral image prediction possibilities of lettuce canopy water content under outdoor conditions.

Climate change poses emerging threats to wheat growth in coming future. These threats need to be explored to ensure sustainable wheat production. To do this, the SALTMED model was calibrated using data from experiments conducted on different levels of irrigation and nitrogen doses. The performance of the SALTMED model was assessed based on values of the root mean square error (RMSE), normalized root mean square error (NRMSE), coefficient of determination (R²) and coefficient of residual mass (CRM) that ranged from 0.23–1.82, 0.09–0.17, 0.91–0.93 and −0.01–0.02, respectively for calibration and 0.31–1.89, 0.11–0.31, 0.87–0.90 and −0.02–0.01, respectively for validation. Projections for future climate scenarios for wheat growth indicated that by the end of the century, sowing dates advanced by nine days under the RCP4.5 scenario and eleven days under the RCP8.5 scenario, while harvesting dates shifted earlier by twenty-four days under RCP4.5 and twenty-eight days under RCP8.5. Consequently, the overall crop duration was shortened by fifteen days under RCP4.5 and eighteen days under RCP8.5. Further simulations revealed that the wheat yield was reduced by 14.2% under RCP4.5 and 21.0% under RCP8.5; the dry matter was reduced by 14.9% under RCP4.5 and 23.3% under RCP8.5; the irrigation amount was expected to increase by 14.9% under RCP4.5 and 18.0% under RCP8.5; and water productivity was expected to be reduced by 25.3% under RCP4.5 and 33.0% under RCP8.5 until the end of century. The hypothetical scenarios showed that adding an extra 20–40% more nitrogen can enhance wheat yield and dry matter by 10.2–23.0% and 11.5–24.6%, respectively, under RCP4.5, and by 12.0–23.4% and 12.9–29.6%, respectively, under RCP8.5. This study offers valuable insights into the effects of climate change on future wheat production so that effective contingency plans could be made by policymakers and adopted by stakeholders for higher wheat productivity.