Plant stress is one of major issues that cause significant economic loss for growers. The labor-intensive conventional methods for identifying the stressed plants constrain their applications. To address this issue, rapid methods are in urgent needs. Developments of advanced sensing and machine learning techniques trigger revolutions for precision agriculture based on deep learning and big data. In this paper, we reviewed the latest deep learning approaches pertinent to the image analysis of crop stress diagnosis. We compiled the current sensor tools and deep learning principles involved in plant stress phenotyping. In addition, we reviewed a variety of deep learning applications/functions with plant stress imaging, including classification, object detection, and segmentation, of which are closely intertwined. Furthermore, we summarized and discussed the current challenges and future development avenues in plant phenotyping.

No abstract

No abstract

A new method combining ultraviolet (UV) spectrophotometry and MoO 3−x nanosheets was developed for the rapid and accurate determination of ascorbic acid (AA) content in fruit and vegetables in this study. MoO 3−x nanosheets were prepared by the liquid exfoliation method using AA as the reducing agent, and the content of AA can be determined by a UV spectrophotometer. Experimental conditions for the MoO 3−x nanosheet method, including grinding time, ethanol concentration, sonication time, and water bath temperature were also optimized.The morphology of MoO 3−x nanosheets was characterized by atomic force microscope. The results showed that the average thickness of MoO 3−x nanosheets was 2.1-5.8 nm. The MoO 3−x nanosheets method had a good linearity in the AA concentration range of 0.01-0.05 mg/ml (R 2 = 0.9996). The limit of detection was 0.031 µg/ml, and the limit of quantitation was 0.095 µg/ml. The spiked recoveries were in the range of 88.79%-116.76%. The MoO 3−x nanosheets method was validated for the determination of AA content in five different fruit and vegetables samples with relative standard deviations less than 2%.

An ultra-performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) method was used for the simultaneous detection of four metabolites of nitrofuran (NF) antibiotics in eight animal-derived foods, namely porcine muscle, chicken, fish, duck, pork liver, crab, shrimp, and egg. Briefly, the sample was first acid-hydrolysed, derivatised, and extracted by ethyl acetate. The extract was then analysed by UPLC-MS/MS. Later, sample pre-treatment and UPLC-MS/MS conditions were optimised. The results showed that the method had good linearity over the range of 0.5~50 μg·kg-1. The average recoveries were 80.3~119.0%, and the relative standard deviations (RSDs) were < 8.1 and < 10.9% for intra-assay and inter-assay precision, respectively. The limits of detection (LODs) for 3-amino-2-oxazolidinone (AOZ), semicarbazide (SEM), 5-morpholino-3-amino-2-oxazolidone (AMOZ), and 1-amino-hydantoin (AHD) were 0.1, 0.2, 0.2, and 0.4~0.5 μg·kg-1, respectively, and the limits of quantification (LOQs) for AOZ, SEM, AMOZ, and AHD were 0.4, 0.5, 0.5, and 0.8~1.0 μg·kg-1, respectively. The proposed method was used to detect NF residues in 100 animal-derived food samples and quality control samples. The results were close to those detected by the China national standard method GB/T 20752-2006, and the results of quality control samples were within the detectable ranges. The results can provide a theoretical basis for the detection of NF residues in different kinds of animal-derived foods.