Nitrous oxide is a potent greenhouse gas, with a global warming potential 298 times greater than that of CO2. In agricultural soils, N2O emissions are influenced by a large number of environmental characteristics and crop management techniques that are not systematically reported in experiments. Random Forest (RF) is a machine learning method that can handle missing data and ranks input variables on the basis of their importance. We aimed to predict N2O emission on the basis of local information, to rank environmental and crop management variables according to their influence on N2O emission, and to compare the performances of RI: with several regression models. RF outperformed the regression models for predictive purposes, and this approach led to the identification of three important input variables: N fertilization, type of crop, and experiment duration. This method could be used in the future for prediction of N2O emissions from local information. (c) 2013 Elsevier Ltd. All rights reserved.

Studying the toxic risk of pesticide exposure to ladybird beetles is important from an agronomical and ecological perspective since larval and adult ladybirds are dominant predators of herbivorous pest insects (e.g., aphids) in various crops in China. This article mainly deals with the long-term effects of a single application of the insect growth regulator hexaflumuron on Coccinella septempunctata. A 72- h and a 33-day toxicity test with hexaflumuron (single application) were performed, starting with the second instar larvae of C. septempunctata. Exposure doses in the long-term experiment were based on the estimated 72-h acute LR50 (application rate causing 50 % mortality) value of 304 g active ingredient (a.i.) ha-1 for second instar larvae of C. septempunctata. The long-term test used five hexaflumuron doses as treatment levels (1/50, 1/100, 1/200, 1/400, and 1/800 of the 72-h acute LR50), as well as a solvent control and blank control treatment. The measurement endpoints used to calculate no observed effect application rates (NOERs) included development time, hatching, pupation, adult emergence, survival, and number of eggs produced. Analyzing the experimental data with one-way analysis of variance showed that the single hexaflumuron application had significant effects on C. septempunctata endpoints in the 33-day test, including effects on development duration (NOER 1.52 g a.i. ha-1), hatching (NOER 3.04 g a.i. ha-1), pupation (NOER 3.04 g a.i. ha-1), and survival (NOER 1.52 g a.i. ha-1). These NOERs are lower than the reported maximum field application rate of hexaflumuron (135 g a.i. ha-1) in cotton cultivation, suggesting potential risks to beneficial arthropods.