An ensemble framework for farmland quality evaluation based on machine learning and physical models.

Farmland quality (FQ) evaluation is crucial to curb agricultural land's "non-grain" behavior and promote ecological nitrogen trade-off in North China. However, a promising approach to obtain the verified spatial distribution of nitrogen emissions remains to be developed, making it difficult to achieve the precise FQ estimation. Facing this issue, we present a Machine Learning (ML) - Nitrogen Export Verification (NEV) ensemble framework for the precise evaluation of FQ, taking the Beijing-Tianjin-Hebei 200 km traffic zone (zone) as the case. This was done by employing physical models for the precisely spatial estimation of Nitrogen Export (NE) values and then using ML methods to compute the spatial distribution of FQ using the Farmland Quality Evaluation System (FQES) indicators. We found: (1) the ML - NEV framework showed promising results, as the relative error of the NEV method was lower than 5.25 %, and the Determination coefficient of the ML method in FQ evaluation was higher than 0.84; (2) the FQ results within the zone were mainly good-quality areas (~47.25 % and primarily concentrated in the southwest-northeast regions) with improvement significance, with Fractal Dimension, NE values, and unbalanced Irrigation or Drainage Capabilities serving as the primary driving factors. Our results would be helpful in offering decision support for improving FQ based on refined grids, benefiting to Agribusiness Revitalization Plans (i.e., safeguarding grain yield, activating agribusiness development, Etc.) in developing countries.

Neonicotinoids residues in cow milk and health risks to the Chinese general population.

The application of neonicotinoid insecticides (NEOs) has increased dramatically in the world since being introduced in 1990s, yet the extent of human exposure and potential health risk is not fully unraveled. In this study, the residues were analyzed of 16 NEOs and their metabolites in 205 commercial cow milk samples circulating in Chinese market. All the milk samples contained at least one quantified NEO, and over 90% of samples contained a cocktail of NEOs. Acetamiprid, N-desmethyl acetamiprid, thiamethoxam, clothianidin and imidaclothiz were the most commonly detected analytes with detection frequencies of 50-88% and medians of 0.011-0.038 ng/mL in milk. Geographical origin was an important factor to influence abundances and levels of NEOs contamination in milk. Chinese local milk bore a significant higher risk from NEOs contamination than the imported milk. In China, the northwest presented the greatest concentrations of the insecticides relative to the north or south. Organic farming, ultra heat treatment and skimming could significantly reduce levels of NEOs contamination in milk. A relative potency factor method was used to evaluate estimated daily intake of NEO insecticides, and found the children had 3.5-5 times higher exposed risk via milk ingestion than the adults. The high frequency of NEOs detection in milk offers us a snapshot of the ubiquity of NEOs in milk, with possible health implications especially for children.

Occurrence and spatiotemporal distribution of PAHs and OPAHs in urban agricultural soils from Guangzhou City, China.

The occurrence of polycyclic aromatic hydrocarbon (PAH) derivatives in the environment is of growing concern because they exhibit higher toxicity than their parent PAHs. This study evaluated the large-scale occurrence and spatiotemporal distribution of 16 PAHs and 14 oxygenated PAHs (OPAHs) in urban agricultural soils from seven districts of Guangzhou City, China. Linear correlation analysis was conducted to explore the relationship between PAH and OPAH occurrence and a series of parameters. The compositional analysis, principal component analysis, diagnostic ratios, and principal component analysis coupled with a multiple linear regression model were used to identify the sources of PAHs and OPAHs in the soils. The average concentrations of ΣPAHs and ΣOPAHs (59.6 ± 31.1-213 ± 115.5 µg/kg) during the flood season were significantly higher than those during the dry season (42.1 ± 13.3-157.2 ± 98.2 µg/kg), which were due to relatively strong wet deposition during the flood season and weak secondary reactions during the dry season. Linear correlation analysis showed that soil properties, industrial activities, and agricultural activities (r = 0.27-0.96, p < 0.05) were responsible for the spatial distribution of PAHs during the dry season. The PAH distribution was mainly affected by precipitation during the flood season. The concentrations of ΣOPAHs were only related to the soil properties during the dry season because their occurrence was sensitive to secondary reactions, climate and meteorological conditions, and their water solubility. Our results further showed that coal combustion and traffic emissions were the dominant origins of PAHs and OPAHs during both the seasons. Wet deposition and runoff-induced transport also contributed to PAH and OPAH occurrence during the flood season. The results of this study can improve our understanding of the environmental risks posed by PAHs and OPAHs.