Monitoring and Identification of Agricultural Crops through Multitemporal Analysis of Optical Images and Machine Learning Algorithms.

The information about where crops are distributed is useful for agri-environmental assessments, but is chiefly important for food security and agricultural policy managers. The quickness with which this information becomes available, especially over large areas, is important for decision makers. Methodologies have been proposed for the study of crops. Most of them require field survey for ground truth data and a single crop map is generated for the whole season at the end of the crop cycle and for the next crop cycle a new field survey is necessary. Here, we present models for recognizing maize (Zea mays L.), beans (Phaseolus vulgaris L.), and alfalfa (Medicago sativa L.) before the crop cycle ends without current-year field survey for ground truth data. The models were trained with an exhaustive field survey at plot level in a previous crop cycle. The field surveys begin since days before the emergence of crops to maturity. The algorithms used for classification were support vector machine (SVM) and bagged tree (BT), and the spectral information captured in the visible, red-edge, near infrared, and shortwave infrared regions bands of Sentinel 2 images was used. The models were validated within the next crop cycle each fifteen days before the mid-season. The overall accuracies range from 71.9% (38 days after the begin of cycle) to 87.5% (81 days after the begin cycle) and a kappa coefficient ranging from 0.53 at the beginning to 0.74 at mid-season.

Bioaccessibility of potentially toxic elements in mine residue particles.

Mining companies used to abandon tailing heaps in countryside regions of Mexico and other countries. Mine residues (MRs) contain a high concentration of potentially toxic elements (PTE). The wind can disperse dust particles (<100 µm) and once suspended in the atmosphere, can be ingested or inhaled; this is a common situation in arid climates. Nowadays, there is little information on the risk of exposure to PTEs from particulate matter dispersed by wind. The pseudo-total PTE in bulk and fractionated MR after aqua regia digestion, the inhalable bioaccessibility with Gamble solution (pH = 7.4), and the gastric bioaccessibility with 0.4 M glycine solution at pH 1.5 were determined. As and Pb chemical species were identified by X-ray absorption near-edge structure (XANES) spectroscopy. The highest rate of dispersion was observed with 74-100 µm particles (104 mg m-2 s-1); in contrast, particles <44 µm had the lowest rate (26 mg m-2 s-1). The highest pseudo-total As (35 961 mg kg-1), Pb (3326 mg kg-1), Cd (44 mg kg-1) and Zn (up to 4678 mg kg-1) concentration was in the <20 µm particles and As in the 50-74 µm (40 236 mg kg-1) particles. The highest concentration of inhaled bioaccessible As (343 mg kg-1) was observed in the <20 µm fraction and the gastric bioaccessible As was 744 mg kg-1, Pb was 1396 mg kg-1, Cd was 19.2 mg kg-1, and Zn was 2048 mg kg-1. The predominant chemical As species was arsenopyrite (92%), while 54% of Pb was in the adsorbed form. Erodible particle matter is a potential risk for humans in case of inhalation or ingestion.