Winter wheat (Triticum aestivum L.) monoculture is conventionally cultivated followed by two to three months of summer fallow in the Loess Plateau. To develop a sustainable cropping system, we conducted a six-year field experiment to investigate the effect of leguminous green manure (LGM) instead of bare fallow on the yield and water use efficiency (WUE) of winter wheat and the soil water balance (SWB) in different precipitation years in a semi-arid region of northwest China. Results confirmed that planting LGM crop consumes soil water in the fallow season can bring varied effects to the subsequent wheat. The effect is positive or neutral when the annual precipitation is adequate, so that there is no significant reduction in the soil water supplied to wheat. If this is not the case, the effect is negative. On average, the LGM crop increased wheat yield and WUE by 13% and 28%, respectively, and had considerable potential for maintaining the SWB (0–200 cm) compared with fallow management. In conclusion, cultivation of the LGM crop is a better option than fallow to improve the productivity and WUE of the next crop and maintain the soil water balance in the normal and wet years in the Loess Plateau.

No abstract

The fluctuations of agricultural commodity prices have a great impact on people's daily lives as well as the inputs and outputs of agricultural production. An accurate forecast of commodity prices is therefore essential if agricultural authorities are to make scientific decisions. To forecast prices more adaptively, this study proposes a novel model selection framework which includes time series features and forecast horizons. Twenty-nine features are used to depict agricultural commodity prices and three intelligent models are specified as the candidate forecast models; namely, artificial neural network (ANN), support vector regression (SVR), and extreme learning machine (ELM). Both random forest (RF) and support vector machine (SVM) are applied to learn the underlying relationships between the features and the performances of the candidate models. Additionally, a minimum redundancy and maximum relevance approach (MRMR) is employed to reduce feature redundancy and further improve the forecast accuracy. The experimental results demonstrate that, firstly, the proposed model selection framework has a better forecast performance compared with the optimal candidate model and simple model average; secondly, feature reduction is a workable approach to further improve the performance of the model selection framework; and thirdly, for bean and pig grain products, different distributions of the time series features lead to a different selection of the optimal models. INDEX TERMS Model selection, agricultural commodity, price forecasting, time series features, forecast horizons.

Green manure and fertilization practices have substantial impacts on soil chemical and biological properties over time. A field experiment was conducted on Cumulic Haplustoll to investigate the effects of leguminous green manure (LGM) crops and nitrogen (N) fertilizer on dry‐stable soil aggregate distributions and stability, the concentrations of organic carbon (OC) and N in the bulk soil and separated aggregate fractions, and soil enzyme activities in dry croplands on the Loess Plateau of China. Species tested as LGM crops were Huai bean (Glycine ussuriensis Regel et Maack.), soybean (G. max (L.) Merr.) and mung bean (Phaseolus radiatus L.). Two rates of N fertilizer (0 and 162 kg N ha−1) applied to winter wheat sown after LGM was incorporated into surface soil. Results showed that the inclusion of LGM crops for 6 years significantly increased the total nitrogen (TN), soil organic carbon (SOC), aggregate‐associated N and OC concentrations, enhanced the values of aggregate content with >0.25 mm size (R0.25) and mean weight diameter (MWD), and boosted soil enzyme (invertase, urease, dehydrogenase and aryl‐sulfatase) activities at the 0–20‐cm depth compared to the bare fallow system under dryland conditions. The long‐term application of N fertilizer substantially increased the proportion of macroaggregates (>5.0 mm), MWD and N contents in the 0.25–5‐mm size aggregates, and promoted the relative activities of invertase, alkaline phosphatase, dehydrogenase and aryl‐sulphatase, but decreased the urease activity. The correlations among macroaggregate fractions and soil chemical properties, aggregate stability and enzyme activities were significant and positive; however, the correlations between small aggregate fractions (<2 mm) and corresponding parameters were negative, or there were no correlations. Overall, combining green manuring practices with suitable N fertilizer application should be recommended to improve the soil quality in dryland regions similar to the Loess Plateau of China. Highlights Green manure crops significantly increased soil enzyme activities, SOC and total N contents. Green manure crops increased macroaggregate (>5 mm) formation and stability. Application of N fertilizer significantly increased the proportions and stability of macroaggregates. Green manure crops along with N fertilizer helped to build better soil quality in a dry loess cropland.

No abstract