Search

In order to eliminate the limitations of traditional winter wheat yield prediction methods, the prediction models based on machine learning are used to improve the accuracy of winter wheat yield prediction. In this study, by collecting a large amount of domestic literature about wheat growth characteristics, the irrigation amount, fertilization amount, soil nutrient status, planting density, maximum leaf area index (LAImax), maximum aboveground dry matter accumulation (Dmax) and yield (Y) were chosen to develop the learning models. Using the data of the irrigation amount, fertilization amount, soil nutrient status and planting density as the training set, the regression prediction models (Gaussian process regression mode, linear regression model, regression tree mode and support vector machine model) were used to train and learn the data of the LAImax, Dmax and Y, respectively. The results show that the Gaussian regression model has the best precision compared to the other models. The coefficients of determination (R2) of the learning results of the Gaussian regression model for the LAImax, Dmax and Y are 0.9, 0.93 and 0.86, and the root mean square error (RMSE) is 0.57, 1125.1 and 640.41. Based on the data of the irrigation amount, nitrogen application amount, potassium application amount, phosphorus application amount, organic matter content, total nitrogen content, alkali-hydrolyzable nitrogen content, available phosphorus content, available potassium content and planting density, the method proposed in this paper can reliably predict the LAImax, the Dmax and Y of winter wheat. The results also have certain reference significance for the yield prediction of other crops. [ABSTRACT FROM AUTHOR]

The application of remote sensing techniques and prediction models for soybean rust (SBR) monitoring may result in different fungicide application timings, control efficacy, and spraying performance. This study aimed to evaluate the applicability of a prediction model as a threshold for disease control decision-making and to identify the effect of different application timings on SBR control as well as on the spraying technology. There were two experimental trials that were conducted in a 2 × 4 factorial scheme: 2 cultivars (susceptible and partially resistant to SBR); and four application timings (conventional chemical control at a calendarized system basis; based on the prediction model; at the appearance of the first visible symptoms; and control without fungicide application). Spray deposit and coverage at each application timing were evaluated in the lower and upper region of the soybean canopy through quantitative analysis of a tracer and water-sensitive papers. The prediction model was calculated based on leaf reflectance data that were collected by remote sensing. Application timings impacted the application technology as well as control efficacy. Calendarized system applications were conducted earlier, promoting different spray performances. Spraying at moments when the leaf area index was higher obtained poorer distribution. None of the treatments were capable of achieving high spray penetration into the canopy. The partially resistant cultivar was effective in holding disease progress during the crop season, whereas all treatments with chemical control resulted in less disease impact. The use of the prediction model was effective and promising to be integrated into disease management programs. [ABSTRACT FROM AUTHOR]