The expansion of commercial tomato cultivation creates a pressing need for accurate, automated disease diagnosis to support modern agriculture. To address this, we developed an enhanced AlexNet model integrated with Coordinate and Hybrid Channel-spatial attention (ACHA) for tomato leaf disease recognition. The classical AlexNet was first streamlined to reduce computational overhead, tailored to the characteristics of tomato disease imagery. A coordinate attention module was then inserted after Conv1 and Conv3 to improve spatial localization of lesion areas. Additionally, a hybrid channel-spatial attention module was incorporated after Conv2 and Conv4 to strengthen discriminative feature learning across channels. Experimental results demonstrate that our approach achieves an average test accuracy of 99.62
Integrated phenotyping and multi-omics approaches identified Cu-tolerant safflower genotypes and candidate genes underpinning Cu stress resilience for climate-adaptive breeding. Copper (Cu) contamination threatens agriculture, yet safflower’s genetic basis for Cu tolerance remains unexplored—especially as global warming intensifies risks through night-time warming and soil acidification. We conducted a pot experiment using 94 safflower genotypes under four copper chloride (CuCl₂) concentrations, revealing substantial variation among genotypes and treatments with trait reductions ranging from 1.75
The combined application of S. indica and SA enhances arsenic stress tolerance in O. sanctum by modulating antioxidant defense and stress-responsive physiological mechanisms. Arsenic is a widespread non-essential metalloid contaminant in soil and water that adversely affects plant growth, productivity, and food safety. Developing sustainable strategies to mitigate arsenic toxicity is essential for maintaining crop performance and quality. This study investigated the potential of Serendipita indica inoculation and foliar application of salicylic acid (SA) to alleviate arsenic-induced stress in Ocimum sanctum. O. sanctum plants were exposed to 50 µM/L and 100 µM/L arsenic, either alone or in combination with S. indica inoculation and SA foliar spray. Germination traits, gas exchange parameters, photosynthetic pigments, malondialdehyde (MDA), hydrogen peroxide (H₂O₂), total antioxidant capacity (TAC), osmolyte accumulation, arsenic accumulation, antioxidant enzyme activities, non-enzymatic antioxidants, total phenol content, and flavonoid content were evaluated. A supervised statistical machine-learning analysis used factorial ridge regression to predict 44 physiological and biochemical responses from treatment factors and pairwise interactions. Unsupervised multivariant statistical analysis including principal component analysis (PCA), hierarchical clustering, and Spearman correlation provide complementary descriptive analysis. Arsenic stress significantly (p < 0.05) reduced germination, gas exchange parameters, photosynthetic pigments, TAC, and osmolyte production, while increasing oxidative damage markers (MDA and H₂O₂). However, the application of S. indica and SA significantly (p < 0.05) mitigated arsenic induced toxicity by improving growth and physiological responses while enhancing osmolyte accumulation, phenolic and flavonoid contents, enzymatic, and non-enzymatic antioxidant activities, thereby strengthening the overall antioxidant defence system. Application of S. indica and SA increased superoxide dismutase (SOD) enzyme activity by 2
