Hyperspectral imaging has many applications. However, the high device costs and low hyperspectral image resolution are major obstacles limiting its wider application in agriculture and other fields. Hyperspectral image reconstruction from a single RGB image fully addresses these two problems. The robust HSCNN-R model with mean relative absolute error loss function and evaluated by the Mean Relative Absolute Error metric was selected through permutation tests from models with combinations of loss functions and evaluation metrics, using tomato as a case study. Hyperspectral images were subsequently reconstructed from single tomato RGB images taken by a smartphone camera. The reconstructed images were used to predict tomato quality properties such as the ratio of soluble solid content to total titratable acidity and normalized anthocyanin index. Both predicted parameters showed very good agreement with corresponding “ground truth” values and high significance in an F test. This study showed the suitability of hyperspectral image reconstruction from single RGB images for fruit quality control purposes, underpinning the potential of the technology—recovering hyperspectral properties in high resolution—for real-world, real time monitoring applications in agriculture any beyond.

Many arable lands have accumulated large reserves of residual phosphorus (P) and a relatively large proportion of soil P is less available for uptake by plants. Root released organic anions are widely documented as a key physiological strategy to enhance P availability, while limited information has been generated on the contribution of rhizosphere organic anions to P utilization by crops grown in agricultural soils that are low in available P and high in extractable Ca, Al and Fe. We studied the role of rhizosphere organic anions in P uptake from residual P in four common crops Triticum aestivum, Avena sativa, Solanum tuberosum and Brassica napus in low- and high-P availability agricultural soils from long-term fertilization field trials in a mini-rhizotron experiment with four replications. Malate was generally the dominant organic anion. More rhizosphere citrate was detected in low P soils than in high P soil. Brassica napus showed 74-103% increase of malate in low P loam, compared with clay loam. Avena sativa had the greatest rhizosphere citrate concentration in all soils (5.3-15.2 mol g-1 root DW). Avena sativa also showed the highest level of root colonization by arbuscular mycorrhizal fungi (36% and 40%), the greatest root mass ratio (0.51 and 0.66) in the low-P clay loam and loam respectively, and the greatest total P uptake (5.92 mg P/mini-rhizotron) in the low-P loam. Brassica napus had 15-44% more rhizosphere APase activity, ~0.1-0.4 units lower rhizosphere pH than other species, the greatest increase in rhizosphere water-soluble P in the low-P soils, and the greatest total P uptake in the low-P clay loam. Shoot P content was mainly explained by rhizosphere APase activity, water-soluble P and pH within low P soils across species. Within species, P uptake was mainly linked to rhizosphere water soluble P, APase and pH in low P soils. The effects of rhizosphere organic anions varied among species and they appeared to play minor roles in improving P availability and uptake.