Comparative Analysis of Deep Learning and Traditional Methods for High-Resolution Cropland Extraction with Different Training Data Characteristics

Dujuan Zhang (), Xiufang Zhu (), Yaozhong Pan, Hengliang Guo, Qiannan Li and Haitao Wei
Additional contact information
Dujuan Zhang: National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou 450001, China
Xiufang Zhu: Institute of Remote Sensing Science and Engineering, Faculty of Geographical Sciences, Beijing Normal University, Beijing 100875, China
Yaozhong Pan: Institute of Remote Sensing Science and Engineering, Faculty of Geographical Sciences, Beijing Normal University, Beijing 100875, China
Hengliang Guo: National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou 450001, China
Qiannan Li: The 27th Research Institute of China Electronics Technology Group Corporation, Zhengzhou 450047, China
Haitao Wei: School of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, China

Land, 2025, vol. 14, issue 10, 1-27

Abstract: High-resolution remote sensing (HRRS) imagery enables the extraction of cropland information with high levels of detail, especially when combined with the impressive performance of deep convolutional neural networks (DCNNs) in understanding these images. Comprehending the factors influencing DCNNs’ performance in HRRS cropland extraction is of considerable importance for practical agricultural monitoring applications. This study investigates the impact of classifier selection and different training data characteristics on the HRRS cropland classification outcomes. Specifically, Gaofen-1 composite images with 2 m spatial resolution are employed for HRRS cropland extraction, and two county-wide regions with distinct agricultural landscapes in Shandong Province, China, are selected as the study areas. The performance of two deep learning (DL) algorithms (UNet and DeepLabv3+) and a traditional classification algorithm, Object-Based Image Analysis with Random Forest (OBIA-RF), is compared. Additionally, the effects of different band combinations, crop growth stages, and class mislabeling on the classification accuracy are evaluated. The results demonstrated that the UNet and DeepLabv3+ models outperformed OBIA-RF in both simple and complex agricultural landscapes, and were insensitive to the changes in band combinations, indicating their ability to learn abstract features and contextual semantic information for HRRS cropland extraction. Moreover, compared with the DL models, OBIA-RF was more sensitive to changes in the temporal characteristics. The performance of all three models was unaffected when the mislabeling error ratio remained below 5%. Beyond this threshold, the performance of all models decreased, with UNet and DeepLabv3+ showing similar performance decline trends and OBIA-RF suffering a more drastic reduction. Furthermore, the DL models exhibited relatively low sensitivity to the patch size of sample blocks and data augmentation. These findings can facilitate the design of operational implementations for practical applications.

Keywords: cropland extraction; high resolution; deep learning; random forest; comparative analysis (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/14/10/2038/pdf (application/pdf)
https://www.mdpi.com/2073-445X/14/10/2038/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:14:y:2025:i:10:p:2038-:d:1769719

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().