ABSTRACT
Establishing the remote sensing yield estimation model of wheat-maize rotation cultivated land can timely and accurately estimate the comprehensive grain yield. Taking the winter wheat-summer maize rotation cultivated land in Caoxian County, Shandong Province, as test object, using the Sentinel-2 images from 2018 to 2019, we compared the time-series feature classification based on QGIS platform and support vector machine algorithm to select the best method and extract sowing area of wheat-maize rotation cultivated land. Based on the correlation between wheat and maize vegetation index and the statistical yield, we screened the sensitive vegetation indices and their growth period, and obtained the vegetation index integral value of the sensitive spectral period by using the Newton-trapezoid integration method. We constructed the multiple linear regression and three machine learning (random forest, RF; neural network model, BP; support vector machine model, SVM) models based on the integral value combination to get the best and and optimized yield estimation model. The results showed that the accuracy rate of extracting wheat and maize sowing area based on time-series features using QGIS platform reached 94.6%, with the overall accuracy and Kappa coefficient were 5.9% and 0.12 higher than those of the support vector machine algorithm, respectively. The remote sensing yield estimation in sensitive spectral period was better than that in single growth period. The normalized differential vegetation index and ratio vegetation index integral group of wheat and enhanced vegetation index and structure intensify pigment vegetable index integral group of maize could more effectively aggregate spectral information. The optimal combination of vegetation index integral was difference, and the fitting accuracy of machine learning algorithm was higher than that of empirical statistical model. The optimal yield estimation model was the difference value group-random forest (DVG-RF) model of machine learning algorithm (R2=0.843, root mean square error=2.822 kg·hm-2), with a yield estimation accuracy of 93.4%. We explored the use of QGIS platform to extract the sowing area, and carried out a systematical case study on grain yield estimation method of wheat-maize rotation cultivated land. The established multi-vegetation index integral combination model was effective and feasible, which could improve accuracy and efficiency of yield estimation.
Subject(s)
Triticum , Zea mays , Remote Sensing Technology/methods , Edible Grain , ChinaABSTRACT
It is objective needs during utilization and management of regional cultivated land resource to use remote sensing to accurately and efficiently retrieve the status of cultivated land fertility at county level and realize the gradation of cultivated land rapidly. In this study, with Dongping County as a case, using Landsat TM satellite imagery and cultivated land fertility evaluation data, the moisture vegetation fertility index (MVFI) was constructed based on surface water capacity index (SWCI) and normalized difference vegetation index (NDVI), and then the optimal inversion model was optimized to obtain the best inversion model, which was further applied and verified at the county scale. The results showed that the correlation coefficient between MVFI and integrated fertility index (IFI) was -0.753, which could comprehensively reflect the growth of winter wheat, soil moisture and land fertility, and had clear biophysical significance. The best inversion model was the quadratic model, with high inversion accuracy. This model was suitable for the inversion of cultivated land fertility in the county. The spatial distribution and uniformity of the inversion results were similar to the results of soil fertility evaluation. The area differences between the high, medium and low grades were all less than 2.9%. This study provided a remote sensing inversion method of cultivated land fertility based on the feature space theory, which could effectively improve the evaluation efficiency and prediction accuracy of cultivated land fertility at the county scale.
