Prediction of Winter Wheat Yield Based on Multi-Source Data and Machine Learning in China

Abstract

Wheat is one of the main crops in China, and crop yield prediction is important for regional trade and national food security. There are increasing concerns with respect to how to integrate multi-source data and employ machine learning techniques to establish a simple, timely, and accurate crop yield prediction model at an administrative unit. Many previous studies were mainly focused on the whole crop growth period through expensive manual surveys, remote sensing, or climate data. However, the effect of selecting different time window on yield prediction was still unknown. Thus, we separated the whole growth period into four time windows and assessed their corresponding predictive ability by taking the major winter wheat production regions of China as an example in the study. Firstly we developed a modeling framework to integrate climate data, remote sensing data and soil data to predict winter wheat yield based on the Google Earth Engine (GEE) platform. The results show that the models can accurately predict yield 1~2 months before the harvesting dates at the county level in China with an R2 > 0.75 and yield error less than 10%. Support vector machine (SVM), Gaussian process regression (GPR), and random forest (RF) represent the top three best methods for predicting yields among the eight typical machine learning models tested in this study. In addition, we also found that different agricultural zones and temporal training settings affect prediction accuracy. The three models perform better as more winter wheat growing season information becomes available. Our findings highlight a potentially powerful tool to predict yield using multiple-source data and machine learning in other regions and for crops.

Modified Red Blue Vegetation Index for Chlorophyll Estimation and Yield Prediction of Maize from Visible Images Captured by UAV

“…The correlation between SPOT images and SPAD readings was similar to results between aerial images and SPAD readings, indicating that SPOT images may have potential abilities for detecting the chlorophyll levels and nitrogen stress of maize. Meanwhile, it is really a challenge to predict the crop yields in developing countries like China, as the varieties and management practice of crops vary greatly [ 23 , 24 ]. Thus, accurately acquiring the leaf chlorophyll contents and predicting the yields are crucial for agricultural practices, which is of vital importance for stable growth and development of the economy and society.…”

A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches With Special Emphasis on Palm Oil Yield Prediction

“…They achieved higher accuracy and concluded that it would be easier to generate an annual mapping of wheat for using the satellite data as it contributes to the reduction of errors. Han et al [52] investigated a modelling approach for predicting winter wheat yield by integrating soil data, climate data and vegetation index data. The authors employed eight typical machine learning models, and the results showed that SVM, GPR and RF were the top three best techniques to predict yields.…”

Enhancing Coffee Supply Chain towards Sustainable Growth with Big Data and Modern Agricultural Technologies

“…Several technologies and related tools were discovered in solving coffee operations and production problems. Han et al [41] applied SVM to increase production crop through yield prediction (90%). Pinto et al [19] used the image processing technique for sorting defective coffee beans with higher efficiency of 72.4-98.7%.…”

“…The assessment approach implemented in this work has been inspired by Kamilaris et al [41]. The application of big data in agriculture has recently been gaining attention, which is evidently realized from Table 1.…”