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.
Background: Occupational short-latency respiratory disease (SLRD; predominantly asthma, rhinitis, hypersensitivity pneumonitis, and occupational infections) prevalence is difficult to determine but certain occupations may be associated with increased susceptibility. Aims: This study aimed to examine which occupations and industries are currently at high risk for SLRD and determine their respective suspected causal agents. Methods: SLRD cases reported to the SWORD scheme between 1999 and 2019 were analysed to determine directly standardized rate ratios (SRR) by occupation against the average rate for all other occupations combined. Results: ‘Bakers and flour confectioners’ and ‘vehicle spray painters’ showed significantly raised SRR for SLRD in general, mostly due to occupational rhinitis (234.4; 95% CI 200.5–274.0) and asthma (63.5; 95% CI 51.5–78.3), respectively. Laboratory technicians also showed significantly raised SRR for occupational rhinitis (18.7; 95% CI 15.1–23.1), primarily caused by laboratory animals and insects. Metal machining setters and setter-operators showed increased SRR for occupational hypersensitivity pneumonitis (42.0; 95% CI 29.3–60.3), largely due to cutting/soluble oils. The occupation mostly affected by infectious disease was welding trades (12.9; 95% CI 5.7–29.3), mainly attributable to microbial pathogenicity. Conclusions: This study identified the occupational groups at increased risk of developing an SLRD based on data recorded over a recent two-decade period in the UK. Occupational asthma and rhinitis were identified as the prevailing conditions and hypersensitivity pneumonitis as a potentially rising respiratory problem in the metalworking industry.