Early detection of drought stress is essential for preventing permanent plant damage and minimizing yield loss. This study utilized hyperspectral imaging at the leaf level to visualize drought stress in safflower plants ( Car- thamus tinctorius L.). Three safflower genotypes, Palenus, A82, and IL-111, were cultivated under three irrigation levels. Stress conditions were simulated by depleting 50%, 70%, and 90% of soil water content, representing unstressed (US), mild stress (MS), and severe stress (SS) conditions, respectively. Hyperspectral images of leaf samples were captured before any visible signs of water scarcity emerged. Classification analysis was performed using the full mean spectral data with partial least squares discriminant analysis, soft independent modeling of class analogy (SIMCA), support vector machines, and artificial neural network (ANN) classifiers. Feature selection methods were applied to extract the most informative wavebands, and ANN was used to build predictive models. Spatial analysis involved pixel-wise classification using both unsupervised (k-means clustering) and supervised (best classifiers) approaches. ANN outperformed other classifiers using the entire spectral data, effectively distinguishing US, MS, and SS classes in the Palenus, A82, and IL-111 genotypes, achieving F1-scores of 92.22%, 96.01%, and 96.47%, respectively. Among the feature selection methods, SIMCA-based features excelled in monitoring stress conditions in the Palenus and A82 genotypes. In supervised spatial analysis, ANN models clearly depicted the progression of stress in leaves across different genotypes. This study demonstrates the potential of hyperspectral imaging to differentiate various levels of drought stress in safflower, an important oilseed crop.

Climate warming has inevitable impacts on the vegetation and hydrological dynamics of high-latitude permafrost peatlands. These impacts in turn determine the role of these peatlands in the global biogeochemical cycle. Here, we used six active layer peat cores from four permafrost peatlands in Northeast European Russia and Finnish Lapland to investigate permafrost peatland dynamics over the last millennium. Testate amoeba and plant macrofossils were used as proxies for hydrological and vegetation changes. Our results show that during the Medieval Climate Anomaly (MCA), Russian sites experienced short-term permafrost thawing and this induced alternating dry-wet habitat changes eventually followed by desiccation. During the Little Ice Age (LIA) both sites generally supported dry hummock habitats, at least partly driven by permafrost aggradation. However, proxy data suggest that occasionally, MCA habitat conditions were drier than during the LIA, implying that evapotranspiration may create important additionaleco-hydrological feedback mechanisms under warm conditions. All sites showed a tendency towards dry conditions as inferred from both proxies starting either from ca. 100 years ago or in the past few decades after slight permafrost thawing, suggesting that recent warming has stimulated surface desiccation rather than deeper permafrost thawing. This study shows links between two important controls over hydrology and vegetation changes in high-latitude peatlands: direct temperature-induced surface layer response and deeper permafrost layer-related dynamics. These data provide important backgrounds for predictions of Arctic permafrost peatlands and related feedback mechanisms. Our results highlight the importance of increased evapotranspiration and thus provide an additional perspective to understanding of peatland-climate feedback mechanisms. (C) 2018 Elsevier Ltd. All rights reserved.