Version 1
: Received: 17 March 2023 / Approved: 20 March 2023 / Online: 20 March 2023 (06:24:43 CET)
How to cite:
Wang, Y.; Zhu, D.; Ding, Y. Identification of Winter Wheat-Growing Areas Based on the XGBoost Algorithm. Preprints2023, 2023030346. https://doi.org/10.20944/preprints202303.0346.v1
Wang, Y.; Zhu, D.; Ding, Y. Identification of Winter Wheat-Growing Areas Based on the XGBoost Algorithm. Preprints 2023, 2023030346. https://doi.org/10.20944/preprints202303.0346.v1
Wang, Y.; Zhu, D.; Ding, Y. Identification of Winter Wheat-Growing Areas Based on the XGBoost Algorithm. Preprints2023, 2023030346. https://doi.org/10.20944/preprints202303.0346.v1
APA Style
Wang, Y., Zhu, D., & Ding, Y. (2023). Identification of Winter Wheat-Growing Areas Based on the XGBoost Algorithm. Preprints. https://doi.org/10.20944/preprints202303.0346.v1
Chicago/Turabian Style
Wang, Y., Daoming Zhu and Yuanyuan Ding. 2023 "Identification of Winter Wheat-Growing Areas Based on the XGBoost Algorithm" Preprints. https://doi.org/10.20944/preprints202303.0346.v1
Abstract
Machine learning (ML) is widely used in the field of crop-growing information identification based on high-resolution remote sensing images. With Baoying County in Jiangsu Province, China, as the study area, this paper used Sentinel-2 images during the winter wheat growth period to construct its spectral, textural, and topographic features during its growth period and proposes a winter wheat-growing area extraction method based on the extreme gradient boosting (XGBoost) algorithm, which was compared with traditional ML algorithms such as the support vector machine (SVM), classification and regression tree (CART), and random forest (RF) algorithms. The results indicated that (1) a winter wheat-growing area identification model based on the XGBoost algorithm was successfully constructed based on Sentinel-2 images, considering 27 spectral, textural, and topographic features; (2) the constructed model could effectively extract winter wheat in the study area with an overall accuracy of 93.43% and only a small error compared with the actual winter wheat-growing area in Baoying County, meeting the accuracy requirement for crop identification in the study area; and (3) the deep learning algorithm XGBoost outperformed the three traditional ML algorithms, among which the RF algorithm was better than the SVM and CART algorithms, both of which had poor identification performance and a large error compared with the actual growing area. This paper provides a scientific basis for the accurate extraction of winter wheat-growing areas and further research on winter wheat growth monitoring and yield estimation.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
