Sustainable agriculture in the future will depend on crops that are tolerant to biotic and abiotic stresses, require minimal input of water and nutrients, and can be cultivated with a minimal carbon footprint. Wild plants that fulfil these requirements abound in nature but are typically low yielding. Thus, replacing current high-yielding crops with less productive but resilient species will require the intractable trade-off of increasing land area under cultivation to produce the same yield. Cultivating more land reduces natural resources, reduces biodiversity, and increases our carbon footprint. Sustainable intensification can be achieved by increasing yield in underutilized or wild plant species that are already resilient but achieving this goal by conventional breeding programs may be a long-term prospect. De novo domestication of orphan or crop wild relatives using mutagenesis is an alternative and fast approach to achieve resilient crops with high yield. With new precise molecular techniques it should be possible to reach economically sustainable yields in a much shorter period of time than ever before in the history of agriculture.

Plant breeders and plant physiologists are deeply committed to high throughput plant phenotyping for drought tolerance. A combination of artificial intelligence with reflectance spectroscopy was tested, as a non-invasive method, for the automatic classification of plant drought stress. Arabidopsis thaliana plants (ecotype Col-0) were subjected to different levels of slowly imposed dehydration (S0, control; S1, moderate stress; S2, severe stress). The reflectance spectra of fully expanded leaves were recorded with an Ocean Optics USB4000 spectrometer and the soil water content (SWC, %) of each pot was determined. The entire data set of the reflectance spectra (intensity vs. wavelength) was given to different machine learning (ML) algorithms, namely decision trees, random forests and extreme gradient boosting. The performance of different methods in classifying the plants in one of the three drought stress classes (S0, S1 and S2) was measured and compared. All algorithms produced very high evaluation scores (F1 > 90%) and agree on the features with the highest discriminative power (reflectance at ~670 nm). Random forests was the best performing method and the most robust to random sampling of training data, with an average F1-score of 0.96 ± 0.05. This classification method is a promising tool to detect plant physiological responses to drought using high-throughput pipelines.

Plants are increasingly exposed to events of elevated temperature and water deficit, which threaten crop productivity. Understanding the ability to rapidly recover from abiotic stress, restoring carbon assimilation and biomass production, is important to unravel crop climate resilience. This study compared the photosynthetic performance of two Triticum aestivum L. cultivars, Sokoll and Paragon, adapted to the climate of Mexico and UK, respectively, exposed to 1-week water deficit and high temperatures, in isolation or combination. Measurements included photosynthetic assimilation rate, stomatal conductance, in vitro activities of Rubisco (EC 4.1.1.39) and invertase (INV, EC 3.2.1.26), antioxidant capacity and chlorophyll a fluorescence. In both genotypes, under elevated temperatures and water deficit (WD38 C), the photosynthetic limitations were mainly due to stomatal restrictions and to a decrease in the electron transport rate. Chlorophyll a fluorescence parameters clearly indicate differences between the two genotypes in the photoprotection when subjected to WD38 C and showed faster recovery of Paragon after stress relief. The activity of the cytosolic invertase (CytINV) under these stress conditions was strongly related to the fast photosynthesis recovery of Paragon. Taken together, the results suggest that optimal sucrose export/utilization and increased photoprotection of the electron transport machinery are important components to limit yield fluctuations due to water shortage and elevated temperatures. | INTRODUCTIONGlobal warming is a serious threat to crop production. Wheat is the world's most harvested crop per area, however, wheat yield is below the average of the other major crops (e.g., maize and rice) being therefore only the second most-produced cereal grain, with 26% of the world share (FAOSTAT, 2017). Around 40% of the global wheat yield

Interannual and local fluctuations in wheat crop yield are majorly explained by abiotic constraints. Heatwaves and drought, which are among the top stressors, commonly co-occur, and their frequency is increasing with global climate change. High-throughput methods were optimised to phenotype wheat plants under controlled water deficit and high temperature, with the aim to identify phenotypic traits conferring adaptative stress responses. Wheat plants of 10 genotypes were grown in a fully automated plant facility under 25/18ºC day/night for 30 days, and then the temperature was increased for seven days (38/31ºC day/night) while maintaining half of the plants well irrigated and half at 30% field capacity. Thermal and multispectral images and pot weights were registered twice daily. At the end of the experiment, key metabolites and enzyme activities from the carbohydrate and antioxidant metabolisms were quantified. Regression machine learning models were successfully established to predict plant biomass using image-extracted parameters. Evapotranspiration traits expressed significant genotype-environment interactions (GxE) when acclimatization to stress was continuously monitored. Consequently, transpiration efficiency was essential to maintain the balance between water-saving strategies and biomass production in wheat under water deficit and high temperature. Stress tolerance included changes in the carbohydrate metabolism, particularly in the sucrolytic and glycolytic pathways, and in the antioxidant metabolism. The observed genetic differences in sensitivity to high temperature and water deficit can be exploited in breeding programs to improve wheat resilience to climate change.