Strategies for improving crop comprehensive benefits via a decision-making system based on machine learning in the rice‒rape,rice‒wheat and rice‒garlic rotation systems in Southwest China

Rice‒rape,rice‒wheat and rice‒garlic rotations are common cropping systems in Southwest China,and they have played a significant role in ensuring ecological and economic benefits(EB)and addressing the challenges of China’s food security in the region.However,the crop yields in these rotation systems are 1.25‒14.73%lower in this region than the national averages.Intelligent decision-making with machine learning can analyze the key factors for obtaining better benefits,but it has rarely been used to enhance the probability of obtaining such benefits from rotations in Southwest China.Thus,we used a data-intensive approach to construct an intelligent decision‒making system with machine learning to provide strategies for improving the benefits of rice-rape,rice-wheat,and rice-garlic rotations in Southwest China.The results show that raising the yield and partial fertilizer productivity(PFP)by increasing seed input under high fertilizer application provided the optimal benefits with a 10%probability in the rice-garlic system.Obtaining high yields and greenhouse gas(GHG)emissions by increasing the N application and reducing the K application provided suboptimal benefits with an 8%probability in the rice-rape system.Reducing N and P to enhance PFP and yield provided optimal benefits with the lowest probability(8%)in the rice‒wheat system.Based on the predictive analysis of a random forest model,the optimal benefits were obtained with fertilization regimes by reducing N by 25%and increasing P and K by 8 and 74%,respectively,in the rice-garlic system,reducing N and K by 54 and by 36%,respectively,and increasing P by 38%in rice-rape system,and reducing N by 4%and increasing P and K by 65 and 23%in rice-wheat system.These strategies could be further optimized by 17‒34%for different benefits,and all of these measures can improve the effectiveness of the crop rotation systems to varying degrees.Overall,these findings provide insights into optimal agricultural inputs for higher benefits through an intelligent decision-making system with machine learning analysis in the rice-rape,rice‒wheat,and rice-garlic systems.

Estimating daily actual evapotranspiration of a rice–wheat rotation system in typical farmland in the Huai River Basin using a two-step model and two one-step models

The objective of this study is to evaluate the performance of three models for estimating daily evapotranspiration(ET) by employing flux observation data from three years(2007, 2008 and 2009) during the growing seasons of winter wheat and rice crops cultivated in a farmland ecosystem(Shouxian County) located in the Huai River Basin(HRB), China. The first model is a two-step model(PM-Kc);the other two are one-step models(e.g., Rana-Katerji(R-K) and advection-aridity(AA)). The results showed that the energy closure degrees of eddy covariance(EC) data during winter wheat and rice-growing seasons were reasonable in the HRB, with values ranging from 0.84 to 0.91 and R2 of approximately 0.80. Daily ET of winter wheat showed a slow decreasing trend followed by a rapid increase, while that of rice presented a decreasing trend after an increase. After calibrating the crop coefficient(Kc), the PM–Kc model performed better than the model using the Kc recommended by the Food and Agricultural Organization(FAO). The calibrated key parameters of the R-K model and AA model showed better universality. After calibration, the simulation performance of the PM-Kc model was satisfactory. Both the R-K model and AA model underestimated the daily ET of winter wheat and rice. Compared with that of the R-K model, the simulation result of the AA model was better, especially in the simulation of daily ET of rice. Overall, this research highlighted the consistency of the PM-Kc model to estimate the water demand for rice and wheat crops in the HRB and in similar climatic regions in the world.

Increasing the appropriate seedling density for higher yield in dry direct-seeded rice sown by a multifunctional seeder after wheatstraw return

Dry direct-seeded rice(DDR) sown using a multifunctional seeder that performs synchronous rotary tillage and sowing has received increased attention because it is highly efficient,relatively cheap,and environmentally friendly.However,this method of rice production may produce lower yields in a rice–wheat rotation system because of its poor seedling establishment.To address this problem,we performed field experiments to determine the rice yield at five seedling density levels(B1,B2,B3,B4,and B5=100,190,280,370,and 460 seedlings m-2,respectively) and clarify the physiological basis of yield formation.We selected a representative high-quality rice variety and a multifunctional seeder that used in a typical rice–wheat rotation area in 2016 and 2018.The proportion of main stem panicle increased with increasing seedling density.There was a parabolic relationship between yield and seedling density,and the maximum yield(9.34-9.47 t ha-1) was obtained under B3.The maximum yield was associated with a higher total spikelet number m-2 and greater biomass accumulation from heading to maturity.The higher total spikelet number m-2 under B3 was attributed to an increase in panicle number m-2 compared with B1 and B2.Although the panicle numbers also increased under B4 and B5,these increases were insufficient to compensate for the reduced spikelet numbers per panicle.Lower biomass,smaller leaf area,and lower N uptake per plant from the stem elongation stage to the heading stage were partially responsible for the smaller panicle size at higher seedling density levels such as B5.The higher biomass accumulation under B3 was ascribed to the increases in the photosynthetic rate of the top three leaves m-2 of land,crop growth rate,net assimilation rate,and leaf area index.Furthermore,the B3 rice population was marked by a higher grain–leaf ratio,as well as a lower export ratio and transport ratio of biomass per stem-sheath.A quadratic function predicted that 260-290 seedlings m-2 is the optimum seedling density for achieving maximum yield.Together,these results suggested that appropriately increasing the seedling density,and thereby increasing the proportion of panicles formed by the main stem,is an effective approach for obtaining a higher yield in DDR sown using a multifunctional seeder in a rice–wheat rotation system.

Influence of long-term different fertilization on soil weed seed bank diversity of a paddy soil under rice/rape rotation

A long-term fertilized paddy field under rice/rape rotation in the Taihu Lake Region was selected to investigate the dynamics of soil weed seed diversity.Four fertilizer treatments were performed,including non-fertilizer(NF),chemical fertilizer only(CF),chemical fertilizer combined with pig manure(CMF)and chemical fertilizer plus crop stalk(CSF).We recorded the seed numbers and crop yields,estimated the weed seed bank density and identified the kinds of weed seeds in the top-soil(0-15 cm)in the study area using a stereomicroscope.Based on the records,we analyzed the effect of long-term fertilization on soil weed seed bank diversity and the rela-tionship between weed seed diversity and crop yields.Comparing the four treatments,it was found that in the cultivating seasons of both rice and rape,the density of soil weed seed bank was the lowest with the treatment of chemical fertilizer plus crop stalk.Whereas,the total number of species and the weed seed bank diversity was the highest.Furthermore,the crop yields were at maximum and kept constant with this treatment.There was a definite correlation between fertilizer treatment and soil weed seed bank diversity and crop yields.It was concluded that balancing the fertilizer management was helpful in main-taining soil weed seed bank diversity,increasing crop yields and alleviating crop yield fluctuation.Therefore,among the four fertilizer treatments,chemical fertilizer plus rice crop stalk treatment was the best one to stimulate the productivity of agricultural ecosystems and simulta-neously protect biodiversity.