Understanding plant response and resilience to drought under a high CO₂ environment will be crucial to ensure crop production in the future. Sorghum bicolor is a C₄ plant that resists drought better than other crops, which could make it a good alternative to be grown under future climatic conditions. Here, we analyse the physiological response of sorghum under 350 ppm CO₂ (aCO₂) or 700 ppm CO₂ (eCO₂) with drought (D) or without drought (WW) for 9, 13 and 16 days; as well as its resilience under long (R1: 9D + 7R) or short (R2: 13D + 3R) recovery treatments. Sorghum showed elevated rates of gs under aCO₂ and WW, which resulted in a significant decrease in Ψ_w, gs, E, Φ_PSII, F_v’/F_m′ when exposed to drought. Consequently, A was greatly decreased. When re‐watered, both re‐watering treatments prioritized A recovery by restoring photosynthetic machinery under aCO₂, whereas under eCO₂ plants required little recovery since plant were hardly affected by drought. However, sorghum growth rate for aboveground organs did not reach control values, indicating a slower long‐term recovery. Overall, these results provide information about the resilience of sorghum and its utility as a suitable candidate for the drought episodes of the future.

Environmentally friendly agricultural production necessitates manipulation of microbe–plant interactions, requiring a better understanding of how farming practices influence soil microbiota. We studied the effect of conventional and organic treatment on soil bacterial richness, composition, and predicted functional potential. 16S rRNA sequencing was applied to soils from adjacent plots receiving either a synthetic or organic fertilizer, where two crops were grown within treatment, homogenizing for differences in soil properties, crop, and climate. Conventional fertilizer was associated with a decrease in soil pH, an accumulation of Ag, Mn, As, Fe, Co, Cd, and Ni; and an enrichment of ammonia oxidizers and xenobiotic compound degraders (e.g., Candidatus Nitrososphaera, Nitrospira, Bacillus, Pseudomonas). Soils receiving organic fertilization were enriched in Ti (crop biostimulant), N, and C cycling bacteria (denitrifiers, e.g., Azoarcus, Anaerolinea; methylotrophs, e.g., Methylocaldum, Methanosarcina), and disease-suppression (e.g., Myxococcales). Some predicted functions, such as glutathione metabolism, were slightly, but significantly enriched after a one-time manure application, suggesting the enhancement of sulfur regulation, nitrogen-fixing, and defense of environmental stressors. The study highlights that even a single application of organic fertilization is enough to originate a rapid shift in soil prokaryotes, responding to the differential substrate availability by promoting soil health, similar to recurrent applications.

The increasing global population and the growing frequency of droughts shows the necessity to enhance global food production and meet future food demands. However, achieving long-term food security and effectively mitigating the impact of climate change require a critical emphasis on sustainable systems to increase food production. Hence, automatic estimation of crop production can enable breeders and farmers to make data-driven decisions to optimise resources and maximise efficiency and sustainability. In this work, we have tackled this estimation task by applying deep learning methods to images taken from a digital RGB camera. Moreover, we have improved the results of those models by feeding the models with not only images but also crop features, such as the amount of fertilisers or the amount of water. The proposed data fusion approach can be applied to convolutional- and transformer-based models obtaining good results in both cases. As a result of our work, we have produced a model that estimates crop production of wheat and spelt with an MAE of 0.666, and is a first step towards optimising resources and food production.